chore: back up Pi environment
This commit is contained in:
544
PI-BACKUP-README.md
Normal file
544
PI-BACKUP-README.md
Normal file
@@ -0,0 +1,544 @@
|
||||
# Бэкап среды Pi Coding Agent
|
||||
|
||||
Файлы рядом:
|
||||
|
||||
- `pi-env-backup.sh` — скрипт создания, проверки и восстановления бэкапа;
|
||||
- `PI-BACKUP-README.md` — эта инструкция.
|
||||
|
||||
Скрипт переносит именно среду Pi, а не проекты.
|
||||
|
||||
## Что сохраняется
|
||||
|
||||
- `~/.pi/agent/settings.json` — глобальные настройки Pi;
|
||||
- `~/.pi/agent/auth.json` — авторизация и API-ключи;
|
||||
- `~/.pi/agent/mcp.json` и `~/.pi/agent/mcp-oauth/` — MCP;
|
||||
- `~/.pi/agent/models.json`, `models.yml` — настройки моделей;
|
||||
- `~/.pi/agent/extensions/`, `skills/`, `npm/`, `git/` — плагины и Pi packages;
|
||||
- `~/.pi/agent/AGENTS.md`, `keybindings.json`, `trust.json`;
|
||||
- `~/.pi/agent/sessions/` — история сессий (**по умолчанию не сохраняется**);
|
||||
- `~/.pi/agent/pi-hermes-memory/` и `projects-memory/` — память;
|
||||
- `~/.pi/context-mode/` — индексы и локальные данные context-mode (**по умолчанию не сохраняются**);
|
||||
- `~/.pi/agent/ayu/checkpoints/` — checkpoints (**по умолчанию не сохраняются**);
|
||||
- `~/.agents/` — дополнительные пользовательские skills;
|
||||
- `~/.pi/local-docs/`, если каталог существует.
|
||||
|
||||
Архив также содержит манифест версий установленных программ и копию самого скрипта для восстановления.
|
||||
|
||||
> **Внимание:** архив содержит секреты из `auth.json`, MCP OAuth и других конфигов. Не выкладывай его в публичное хранилище.
|
||||
|
||||
---
|
||||
|
||||
## 1. Создать полный бэкап
|
||||
|
||||
Закрой все запущенные Pi:
|
||||
|
||||
```bash
|
||||
pkill -f pi-coding-agent || true
|
||||
```
|
||||
|
||||
Создай каталог для архивов и запусти:
|
||||
|
||||
```bash
|
||||
mkdir -p ~/pi-backups
|
||||
cd /home/smog/main
|
||||
./pi-env-backup.sh backup ~/pi-backups
|
||||
```
|
||||
|
||||
Или сразу на внешний диск:
|
||||
|
||||
```bash
|
||||
./pi-env-backup.sh backup /media/smog/SSD
|
||||
```
|
||||
|
||||
На выходе будут два файла:
|
||||
|
||||
```text
|
||||
pi-backup-YYYYMMDD-HHMMSS.tar.zst
|
||||
pi-backup-YYYYMMDD-HHMMSS.tar.zst.sha256
|
||||
```
|
||||
|
||||
По умолчанию архив НЕ включает `ayu/checkpoints`, историю Pi-сессий и `context-mode`: это кэш/история, не нужные для работы плагинов. Поэтому архив обычно будет порядка **0.8–1 ГБ до сжатия** и ориентировочно **0.4–0.8 ГБ после zstd**. Точный размер скрипт покажет в конце.
|
||||
|
||||
---
|
||||
|
||||
## 2. Проверить архив
|
||||
|
||||
Посмотреть содержимое:
|
||||
|
||||
```bash
|
||||
./pi-env-backup.sh list ~/pi-backups/pi-backup-*.tar.zst
|
||||
```
|
||||
|
||||
Проверить контрольную сумму:
|
||||
|
||||
```bash
|
||||
sha256sum -c ~/pi-backups/pi-backup-*.tar.zst.sha256
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 3. Дополнительные варианты бэкапа
|
||||
|
||||
По умолчанию уже создаётся облегчённый бэкап: плагины, настройки, auth, MCP, memory и skills сохраняются, а checkpoints/сессии/context-mode — нет.
|
||||
|
||||
Включить историю старых Pi-сессий:
|
||||
|
||||
```bash
|
||||
PI_BACKUP_INCLUDE_SESSIONS=1 \
|
||||
./pi-env-backup.sh backup ~/pi-backups
|
||||
```
|
||||
|
||||
Включить context-mode индексы:
|
||||
|
||||
```bash
|
||||
PI_BACKUP_INCLUDE_CONTEXT=1 \
|
||||
./pi-env-backup.sh backup ~/pi-backups
|
||||
```
|
||||
|
||||
Включить старые ayu checkpoints (обычно не нужно):
|
||||
|
||||
```bash
|
||||
PI_BACKUP_INCLUDE_AYU=1 \
|
||||
./pi-env-backup.sh backup ~/pi-backups
|
||||
```
|
||||
|
||||
Включить всё сразу:
|
||||
|
||||
```bash
|
||||
PI_BACKUP_INCLUDE_SESSIONS=1 \
|
||||
PI_BACKUP_INCLUDE_CONTEXT=1 \
|
||||
PI_BACKUP_INCLUDE_AYU=1 \
|
||||
./pi-env-backup.sh backup ~/pi-backups
|
||||
```
|
||||
|
||||
Настройки, auth, MCP, memory, плагины и skills сохраняются во всех вариантах.
|
||||
|
||||
---
|
||||
|
||||
## 4. Восстановить на ноутбуке в WSL
|
||||
|
||||
На ноутбуке установи базовые инструменты:
|
||||
|
||||
```bash
|
||||
sudo apt update
|
||||
sudo apt install -y zstd nodejs npm
|
||||
```
|
||||
|
||||
Передай на ноутбук архив и `.sha256` рядом с ним. Если бэкап был скачан из этого Git-репозитория, сначала забери LFS-архив:
|
||||
|
||||
```bash
|
||||
git lfs pull
|
||||
```
|
||||
|
||||
Проверь архив:
|
||||
|
||||
```bash
|
||||
sha256sum -c pi-backup-YYYYMMDD-HHMMSS.tar.zst.sha256
|
||||
```
|
||||
|
||||
Извлеки встроенную копию restore-скрипта:
|
||||
|
||||
```bash
|
||||
zstd -dc pi-backup-YYYYMMDD-HHMMSS.tar.zst \
|
||||
| tar -xOf - meta/pi-env-backup.sh > pi-env-restore.sh
|
||||
|
||||
chmod +x pi-env-restore.sh
|
||||
```
|
||||
|
||||
Запусти восстановление:
|
||||
|
||||
```bash
|
||||
./pi-env-restore.sh restore pi-backup-YYYYMMDD-HHMMSS.tar.zst
|
||||
```
|
||||
|
||||
Скрипт распакует Pi-среду в домашний каталог текущего пользователя WSL. Если `~/.pi/agent` уже существует, он сначала переименует его в каталог вида:
|
||||
|
||||
```text
|
||||
~/.pi/agent.before-restore-YYYYMMDD-HHMMSS
|
||||
```
|
||||
|
||||
Если Pi ещё не установлен, скрипт установит его так:
|
||||
|
||||
```bash
|
||||
npm install -g --ignore-scripts @earendil-works/pi-coding-agent
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 5. Проверить восстановление
|
||||
|
||||
```bash
|
||||
pi --version
|
||||
pi list
|
||||
```
|
||||
|
||||
Запусти Pi в одном из своих проектов:
|
||||
|
||||
```bash
|
||||
cd ~/main/имя-проекта
|
||||
pi
|
||||
```
|
||||
|
||||
Проверь:
|
||||
|
||||
```text
|
||||
/mcp
|
||||
/login # только если OAuth/API-ключ не восстановился
|
||||
```
|
||||
|
||||
Если какие-то внешние программы нужны плагинам, установи их отдельно: `bun`, `pnpm`, `uv`, `gh`, `jj`, `docker` и т.п. Их бинарники не копируются архивом — архив переносит состояние Pi и список обнаруженных инструментов в `meta/MANIFEST.txt`.
|
||||
|
||||
---
|
||||
|
||||
## 6. Важные замечания
|
||||
|
||||
1. Перед созданием архива закрывай Pi, чтобы не копировать активные session/SQLite-файлы.
|
||||
2. Не используй `PI_BACKUP_ALLOW_RUNNING=1`, если нет особой причины.
|
||||
3. Архив — это переносимая копия пользовательской Pi-среды, но не копия всей ОС.
|
||||
4. Проекты не входят в этот архив: они уже есть в WSL отдельно.
|
||||
5. Project-local файлы вроде `project/.pi/`, `project/.agents/`, `AGENTS.md` и `CLAUDE.md` не входят в глобальный архив, если находятся внутри проектов. Их нужно хранить вместе с проектами или отдельно скопировать.
|
||||
6. Некоторые OAuth-провайдеры могут потребовать повторный `/login` на новом ноутбуке.
|
||||
|
||||
---
|
||||
|
||||
<!-- PI-MANUAL-RECOVERY:START -->
|
||||
## 7. Восстановление Pi без бэкап-архива
|
||||
|
||||
Снимок конфигурации создан автоматически **2026-07-14**. В нём нет `auth.json`, OAuth-токенов и API-ключей: после ручной установки потребуется выполнить `/login` или задать свои ключи.
|
||||
|
||||
### Базовая установка
|
||||
|
||||
```bash
|
||||
sudo apt update && sudo apt install -y nodejs npm git
|
||||
npm install -g --ignore-scripts @earendil-works/pi-coding-agent
|
||||
pi --version
|
||||
```
|
||||
|
||||
Текущая версия Pi: `0.80.6`.
|
||||
|
||||
### Pi-пакеты и плагины
|
||||
|
||||
Установить каждый источник через `pi install` (команда добавит его в глобальные настройки Pi):
|
||||
|
||||
```bash
|
||||
pi install npm:@upstash/context7-pi
|
||||
```
|
||||
```bash
|
||||
pi install npm:pi-obsidian
|
||||
```
|
||||
```bash
|
||||
pi install npm:context-mode
|
||||
```
|
||||
```bash
|
||||
pi install npm:pi-subagents
|
||||
```
|
||||
```bash
|
||||
pi install npm:pi-mcp-adapter
|
||||
```
|
||||
```bash
|
||||
pi install npm:@juicesharp/rpiv-ask-user-question
|
||||
```
|
||||
```bash
|
||||
pi install npm:pi-simplify
|
||||
```
|
||||
```bash
|
||||
pi install npm:@juicesharp/rpiv-btw
|
||||
```
|
||||
```bash
|
||||
pi install npm:@plannotator/pi-extension
|
||||
```
|
||||
```bash
|
||||
pi install npm:pi-chrome
|
||||
```
|
||||
```bash
|
||||
pi install git:github.com/rawwerks/ypi@07560b9a0045d6ddbfc142dc02f9eaf58f18eeac
|
||||
```
|
||||
```bash
|
||||
pi install npm:@tmustier/pi-ralph-wiggum
|
||||
```
|
||||
```bash
|
||||
pi install npm:pi-hermes-memory
|
||||
```
|
||||
```bash
|
||||
pi install npm:@hypabolic/pi-hypa
|
||||
```
|
||||
```bash
|
||||
pi install npm:@ayulab/pi-rewind
|
||||
```
|
||||
```bash
|
||||
pi install npm:bigpowers
|
||||
```
|
||||
```bash
|
||||
pi install npm:pi-web-access
|
||||
```
|
||||
```bash
|
||||
pi install npm:@mjasnikovs/pi-task
|
||||
```
|
||||
```bash
|
||||
pi install npm:@sting8k/pi-vcc
|
||||
```
|
||||
|
||||
Зафиксированные версии, установленные на момент создания документа:
|
||||
|
||||
| Источник | Версия |
|
||||
| --- | --- |
|
||||
| `npm:@upstash/context7-pi` | `0.1.1` |
|
||||
| `npm:pi-obsidian` | `0.2.3` |
|
||||
| `npm:context-mode` | `1.0.169` |
|
||||
| `npm:pi-subagents` | `0.34.0` |
|
||||
| `npm:pi-mcp-adapter` | `2.11.0` |
|
||||
| `npm:@juicesharp/rpiv-ask-user-question` | `1.20.0` |
|
||||
| `npm:pi-simplify` | `0.2.2` |
|
||||
| `npm:@juicesharp/rpiv-btw` | `1.20.0` |
|
||||
| `npm:@plannotator/pi-extension` | `0.23.1` |
|
||||
| `npm:pi-chrome` | `0.15.46` |
|
||||
| `git:github.com/rawwerks/ypi@07560b9a0045d6ddbfc142dc02f9eaf58f18eeac` | `0.6.0` |
|
||||
| `npm:@tmustier/pi-ralph-wiggum` | `0.2.2` |
|
||||
| `npm:pi-hermes-memory` | `0.8.0` |
|
||||
| `npm:@hypabolic/pi-hypa` | `0.1.11` |
|
||||
| `npm:@ayulab/pi-rewind` | `0.4.5` |
|
||||
| `npm:bigpowers` | `2.76.3` |
|
||||
| `npm:pi-web-access` | `0.13.0` |
|
||||
| `npm:@mjasnikovs/pi-task` | `0.18.14` |
|
||||
| `npm:@sting8k/pi-vcc` | `0.4.0` |
|
||||
|
||||
### Локальные extensions
|
||||
|
||||
Эти extensions не публикуются как Pi-пакеты — их надо отдельно скопировать из исходной машины/резервной копии в `~/.pi/agent/extensions/`:
|
||||
|
||||
- `codex-limit-watcher.ts`
|
||||
- `herdr-agent-state.ts`
|
||||
- `pi-permission-system`
|
||||
- `rtk.ts`
|
||||
|
||||
### MCP
|
||||
|
||||
Текущий MCP-конфиг (`~/.pi/agent/mcp.json`) содержит один сервер:
|
||||
|
||||
| Имя | Тип | Команда / адрес |
|
||||
| --- | --- | --- |
|
||||
| `chrome-devtools` | stdio | `/home/<user>/.local/bin/chrome-devtools-mcp-hard` |
|
||||
|
||||
На ноутбуке создай `~/.pi/agent/mcp.json` без секретов, например:
|
||||
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
"chrome-devtools": {
|
||||
"command": "/home/<user>/.local/bin/chrome-devtools-mcp-hard"
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Указанный wrapper `chrome-devtools-mcp-hard` — локальный бинарник; его также нужно установить/скопировать и сделать исполняемым.
|
||||
|
||||
### Skills
|
||||
|
||||
Всего найдено: **187**. Skills, поставляемые Pi-пакетами, вернутся после установки соответствующего пакета выше. Skills с источником `local` нужно отдельно скопировать из `~/.agents/skills` или `~/.pi/agent/skills`.
|
||||
|
||||
| Skill | Источник | Описание |
|
||||
| --- | --- | --- |
|
||||
| `caveman` | `local ~/.agents` | > |
|
||||
| `find-skills` | `local ~/.agents` | Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill. |
|
||||
| `brandkit` | `local ~/.agents` | Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts. |
|
||||
| `industrial-brutalist-ui` | `local ~/.agents` | Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints. |
|
||||
| `gpt-taste` | `local ~/.agents` | Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing. |
|
||||
| `image-to-code` | `local ~/.agents` | Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop. |
|
||||
| `imagegen-frontend-mobile` | `local ~/.agents` | Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured surfaces, image-led composition, tasteful custom iconography, and clean phone mockup framing. By default, screens should be shown inside a subtle premium iPhone or similar phone mockup with a visible frame, while the main focus stays on the app content itself. This skill generates images only. It does not write code. |
|
||||
| `imagegen-frontend-web` | `local ~/.agents` | Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate. |
|
||||
| `minimalist-ui` | `local ~/.agents` | Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows. |
|
||||
| `full-output-enforcement` | `local ~/.agents` | Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output. |
|
||||
| `redesign-existing-projects` | `local ~/.agents` | Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS. |
|
||||
| `high-end-visual-design` | `local ~/.agents` | Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic. |
|
||||
| `stitch-design-taste` | `local ~/.agents` | Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance. |
|
||||
| `design-taste-frontend-v1` | `local ~/.agents` | The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is \`design-taste-frontend\` (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility. |
|
||||
| `design-taste-frontend` | `local ~/.agents` | Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check. |
|
||||
| `context7-docs` | `npm:@upstash/context7-pi` | >- |
|
||||
| `align-grid` | `npm:bigpowers` | Build editorial/magazine/report webpages on a GENUINE Müller-Brockmann modular grid (International Typographic Style) — not a decorative one. Encodes the discipline (columns + modules + baseline, grotesque type, flush-left, restrained black/white/red palette) AND the hard-won front-end engineering to make the grid real, visible, and verified: one CSS-variable source of truth, an interactive grid-toggle overlay that lives in the SAME content box as the content, subgrid \"bands\" so every element snaps to a column line, an 8px baseline lock, and runtime OPTICAL ALIGNMENT that puts display type's ink (not its box) on the line. Ships with a scaffold generator and a Puppeteer verification harness that proves 0px adherence. |
|
||||
| `assess-impact` | `npm:bigpowers` | Analyze the blast radius of a proposed change before any code is written. Maps dependents, affected stories, and test coverage. Produces specs/IMPACT_LATEST.md. Use before plan-work on any non-trivial change, when touching a shared module, or when the user asks \"what does this break?\". |
|
||||
| `audit-code` | `npm:bigpowers` | Self-review checklist for the coding agent to run before dispatching a reviewer. Checks CONVENTIONS.md compliance, Boy Scout Rule, test coverage, types, and SOLID. Produces a pass/fail checklist. Use before request-review, before committing, or when user asks for a code quality check. |
|
||||
| `audit-plan` | `npm:bigpowers` | Evaluate an incoming project plan against bigpowers principles and conventions, surface gaps, and produce a READY/NOT READY verdict before engagement begins. Use when a new project arrives, when adapting a foreign plan, or before running seed-conventions on an unfamiliar codebase. |
|
||||
| `build-epic` | `npm:bigpowers` | Eight-step epic build cycle — reads state.yaml, execution-status.yaml, and one epic capsule; updates status via bp-yaml-set or direct edit. Resume mode runs one step per invocation. Use instead of ad-hoc execute-plan for release work. |
|
||||
| `change-request` | `npm:bigpowers` | Add a new requirement or reorder epics by WSJF against specs/release-plan.yaml and epic capsule directories. Modes Add and Reorder. Use when a new requirement arrives mid-release or the plan needs prioritization. |
|
||||
| `commit-message` | `npm:bigpowers` | Reviews working-tree changes, then drafts a Conventional Commits title/body and states the semantic-release version bump a single such commit would imply. Also notes which defensive-code categories were touched. Use when the user wants to commit recent work, prepare a Conventional Commits message, or asks for semantic-release / semver-consistent messaging before git commit. |
|
||||
| `compose-workflow` | `npm:bigpowers` | Chain multiple bigpowers skills into a custom workflow recipe saved in specs/. Use when a project repeats a non-standard skill sequence, or user wants a documented playbook beyond orchestrate-project modes. |
|
||||
| `context7-mcp` | `npm:bigpowers` | Fetch current library docs via Context7 MCP instead of training data. Use when user asks about frameworks, APIs, setup, or code examples for React, Next.js, Prisma, etc. |
|
||||
| `craft-skill` | `npm:bigpowers` | Create new bigpowers skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill for the bigpowers lifecycle. |
|
||||
| `deepen-architecture` | `npm:bigpowers` | Find deepening opportunities in a codebase, informed by the domain language in specs/tech-architecture/tech-stack.md and the decisions in specs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable. |
|
||||
| `define-language` | `npm:bigpowers` | Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to specs/UBIQUITOUS_LANGUAGE_LATEST.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions \"domain model\" or \"DDD\". |
|
||||
| `define-success` | `npm:bigpowers` | Convert an imperative task statement into explicit \"step → verify: <cmd>\" pairs before implementation begins. Use before plan-work when success criteria are unclear, when a task lacks verifiable checkpoints, or when user says \"how will we know this is done?\". |
|
||||
| `delegate-task` | `npm:bigpowers` | Delegate one complex task to a single subagent, review its work in two stages before merging back. Sequential — one agent at a time, with oversight. Use when a task is complex and requires careful review before the result is accepted. Distinct from dispatch-agents (no parallelism here; reviewer sees full diff before proceeding). |
|
||||
| `deploy` | `npm:bigpowers` | Build → verify artifact → deploy → wait → smoke deployment pipeline. Platform-agnostic (MCP or CLI), with configurable timeout, retry with exponential backoff, and integrated health-check. The deploy half of CI/CD: run after build to push to production. |
|
||||
| `design-interface` | `npm:bigpowers` | Generate multiple radically different interface designs for a module using parallel sub-agents, then compare trade-offs. Based on \"Design It Twice\" from A Philosophy of Software Design. Use when user wants to design an API, explore interface options, compare module shapes, or mentions \"design it twice\". |
|
||||
| `develop-tdd` | `npm:bigpowers` | Test-driven development with red-green-refactor loop using vertical slices. Use for features (epic tasks) or bugs (specs/bugs/BUG-*.md). |
|
||||
| `diagnose-root` | `npm:bigpowers` | Run 4-phase root cause analysis — reproduce, isolate, hypothesize, verify. Use when a bug is confirmed but root cause is unclear, after investigate-bug, or when user mentions root cause analysis. |
|
||||
| `diagnose-stall` | `npm:bigpowers` | Diagnose why agent orchestration stopped producing progress — silent stalls in /loop, dispatch-agents, or execute-plan. Use when work appears hung, no output for several minutes, or a subagent never returned. |
|
||||
| `dispatch-agents` | `npm:bigpowers` | Dispatch multiple subagents in parallel on independent tasks. No waiting between them — all run concurrently. Use when tasks are truly decoupled and speed matters. Distinct from delegate-task (concurrent here, no inter-task review gate). |
|
||||
| `edit-document` | `npm:bigpowers` | Edit and improve documents by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, restructure, or improve any document — including specs/ files, articles, READMEs, or technical writing. |
|
||||
| `elaborate-spec` | `npm:bigpowers` | Refine a rough idea into a clear, detailed specification through dialogue. Does not produce code. Use when user has a vague idea, wants to think through a feature before planning, or needs to turn \"I want X\" into a concrete spec. |
|
||||
| `enforce-first` | `npm:bigpowers` | Apply the F.I.R.S.T test quality rubric (per CONVENTIONS.md §Tests) to a test suite or individual tests. Use when develop-tdd is writing tests, when test quality needs to be checked, or when user mentions F.I.R.S.T or \"test quality\". |
|
||||
| `evolve-skill` | `npm:bigpowers` | Benchmark-gated skill evolution — consume bigpowers-benchmark report, propose plan-work change, edit skill via craft-skill, re-run benchmark, record ADR. Use when a skill underperforms on benchmark or stocktake finds systemic gap. |
|
||||
| `execute-plan` | `npm:bigpowers` | Batch-execute tasks from the active epic capsule sequentially, with a human checkpoint after each step. Use when user has an approved plan and wants step-by-step oversight. |
|
||||
| `extract-design` | `npm:bigpowers` | Extract a Google DESIGN.md file from an HTML prototype (claude.ai/design or any styled page) using Puppeteer, producing machine-readable tokens and AI-generated prose. Use when the user has an HTML prototype and wants a DESIGN.md to anchor their project's visual identity, or when seed-conventions has just scaffolded a new project. |
|
||||
| `fix-bug` | `npm:bigpowers` | Bug fix orchestrator — active_flow fix_bug; reads specs/bugs/BUG-*.md; chains investigate-bug, develop-tdd, validate-fix. Use when user reports a defect. |
|
||||
| `gate-trace` | `npm:bigpowers` | Deterministic traceability quality gate — reads coverage matrix + blind-spot data, applies decision rules with oracle confidence downgrade, emits PASS/CONCERNS/FAIL/WAIVED verdict. Use before release-branch to gate merges on traceability. |
|
||||
| `grill-me` | `npm:bigpowers` | Interactive assumption-surfacing Q&A that stress-tests a plan through relentless questioning until every decision is resolved. Use when user wants to challenge a plan, validate decisions from conversation/context, or mentions \"grill me\". For doc-grounded variant, use grill-with-docs. |
|
||||
| `grill-with-docs` | `npm:bigpowers` | Doc-grounded variant of grill-me — stress-tests plan assumptions by fetching and citing real library or API documentation. Every challenge must cite a real URL. Use when the plan depends on a specific library or external API. |
|
||||
| `guard-git` | `npm:bigpowers` | Block dangerous git commands (push, force push, reset --hard, clean, branch -D, checkout/restore .) and enforce Conventional Commits & Branch Protection before an AI agent runs them. Installs hook scripts for Claude Code, Cursor, Cursor CLI, and Gemini CLI; documents Google Antigravity Terminal deny lists. Use when the user wants git safety hooks, to block git push or destructive git in agents, or to mirror the same policy across AI coding tools. |
|
||||
| `hook-commits` | `npm:bigpowers` | Set up pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing. |
|
||||
| `inspect-quality` | `npm:bigpowers` | Interactive QA session where user reports bugs or issues conversationally, and the agent logs them to specs/bugs/registry.yaml with a structured audit schema. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, or mentions \"QA session\". |
|
||||
| `investigate-bug` | `npm:bigpowers` | Investigate a bug or issue by exploring the codebase to find root cause, then write a TDD-based fix plan to specs/bugs/BUG-*.md. Use when user reports a bug, wants to investigate a problem, mentions \"triage\", or wants to plan a fix. |
|
||||
| `kickoff-branch` | `npm:bigpowers` | Create a git worktree and feature branch, then verify a clean test baseline before any code is written. Use when starting a new feature or task, when user wants to work in isolation from main, or mentions \"start a branch\" or \"new worktree\". |
|
||||
| `maintain-wiki` | `npm:bigpowers` | Agent-maintained OKF wiki — INGEST source docs, LINT for issues, QUERY across concept pages. Run as part of build-epic Step 8 and verify-work Phase 3. |
|
||||
| `map-codebase` | `npm:bigpowers` | Derives the tech-stack doc from scratch by scanning the codebase — analyzes stack, architecture, and gray areas (error handling, API shapes) and persists findings into specs/tech-architecture/tech-stack.md. Run when the tech doc doesn't exist yet; use survey-context to consume it once it does. |
|
||||
| `migrate-spec` | `npm:bigpowers` | Detect GSD, spec-kit, or BMAD spec artifacts and transform them into bigpowers YAML layout (state.yaml, release-plan.yaml, epics/, requirements/, plans/, ADRs). Use when migrating foreign spec docs. |
|
||||
| `model-domain` | `npm:bigpowers` | Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates specs/tech-architecture/tech-stack.md and specs/adr/ inline as decisions crystallise. Use when user wants to stress-test a plan against their project's domain language and documented decisions. |
|
||||
| `orchestrate-project` | `npm:bigpowers` | Meta-skill that enforces the 6-phase core loop (discover → elaborate → plan → build → verify → release) with hard gates. Use to coordinate multi-phase projects with guaranteed quality checkpoints. One-time command for the entire project lifecycle. |
|
||||
| `organize-workspace` | `npm:bigpowers` | Scans the active workspace for disposable artifacts—logs, caches, stale build output, and stray draft markdown—and proposes consolidation of scattered assets. Produces a reviewable list, asks for explicit confirmation before any delete or move, and optionally revises .gitignore. Use when the user says \"clean my room\", \"organize workspace\", \"workspace cleanup\", \"remove temp files\", \"organize assets\", \"gitignore\", or wants a safe tidy pass. |
|
||||
| `plan-refactor` | `npm:bigpowers` | Create a detailed refactor plan with tiny commits via user interview, then save it as specs/REFACTOR_LATEST.md. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps. |
|
||||
| `plan-release` | `npm:bigpowers` | RELEASE-INDEX BUILDER — Sequence elaborated epics into specs/release-plan.yaml with WSJF ordering and BCP baselines. NOT a planning-spine substitute: it does not scope work (scope-work) or write story tasks (plan-work). Use after elaborate-spec when the user wants a versioned release index of epics. |
|
||||
| `plan-tests` | `npm:bigpowers` | Design a risk-scaled test architecture for an epic before implementation begins. Produces prioritized scenarios, test level distribution, and fixture plans based on TEA and bigpowers principles. |
|
||||
| `plan-work` | `npm:bigpowers` | PLANNING SPINE STEP 3 of 3 — Plan the work: write detailed implementation tasks into the active epic capsule (specs/epics/eNN-slug/). Produces countable-story-format .md specs and runnable -tasks.yaml files. Use after slice-tasks (step 2). Not a substitute for scope-work (step 1) or slice-tasks (step 2). |
|
||||
| `publish-package` | `npm:bigpowers` | Package registry publishing for npm, crates.io, PyPI, and Homebrew. Verifies prerequisites, runs the publish command, confirms success, and surfaces actionable error hints on failure. |
|
||||
| `quick-fix` | `npm:bigpowers` | Streamlined fast-path for trivial data-only fixes — no TDD, no branching ceremony. Collapses 6 skills into 2 for changes that are purely data with no logic risk. Aborts with fallback to investigate-bug if guardrails trigger. |
|
||||
| `release-branch` | `npm:bigpowers` | Make the merge/PR/keep/discard decision for a feature branch, verify coverage gates, create the PR with gh, and clean up the worktree. Use when a feature is done and ready to ship, or when user says \"release\", \"merge\", or \"open a PR\". |
|
||||
| `request-review` | `npm:bigpowers` | Dispatch a fresh reviewer agent with a clean context to critique the code after audit-code passes. The reviewer has no shared state with the coding agent and gives a genuine second opinion. Use after audit-code passes, before committing, or when user wants an independent code review. |
|
||||
| `research-first` | `npm:bigpowers` | Look-before-build — search registries, repo, existing skills, and web for prior art before implementing. Appends Prior Art to the spec. Use after survey-context and before elaborate-spec, when adding dependencies, or when the task may already be solved. |
|
||||
| `reset-baseline` | `npm:bigpowers` | Restore the project to a known clean state between agent runs or experiments. Use between benchmark runs, after a failed spike, or when user wants a clean working tree. |
|
||||
| `respond-review` | `npm:bigpowers` | Act on a reviewer agent's feedback systematically — categorize findings, apply fixes, verify tests still pass. Use after request-review returns a report, or when user wants to work through code review findings. |
|
||||
| `run-benchmark` | `npm:bigpowers` | Run skill quality benchmarks from specs/benchmarks/ definitions — N-run with/without-skill delta grading, train/validation split, pass@k + benchmark.json reports. Use before and after evolve-skill to prove quality changes are improvements, not regressions. |
|
||||
| `run-evals` | `npm:bigpowers` | Eval-Driven Development — define capability and regression evals before building; code graders use verify commands, model graders use explicit rubrics; log pass@k. Use before develop-tdd on new features, or when measuring agent capability over runs. |
|
||||
| `run-planning` | `npm:bigpowers` | DISCOVER-PHASE ADVANCER — Drive the discover-phase checklist (specs/planning-status.yaml) through survey-context → scope-work → research-first → elaborate-spec → plan-release → slice-tasks. NOT a duplicate of plan-work or the planning spine; it orchestrates the pre-coding discover phase only. |
|
||||
| `scope-work` | `npm:bigpowers` | PLANNING SPINE STEP 1 of 3 — Scope the work: define what is in and out of scope and save as specs/product/SCOPE_LATEST.yaml. Use before slice-tasks or plan-release on any new initiative. Not a substitute for slice-tasks (step 2) or plan-work (step 3). |
|
||||
| `search-skills` | `npm:bigpowers` | Find the right bigpowers skill from natural-language intent using a local lexical index over SKILL.md frontmatter. Use when unsure which skill to invoke, or at start of research-first. |
|
||||
| `security-review` | `npm:bigpowers` | AI-powered security analysis of code changes — traces data flow, detects injection, auth bypass, secrets exposure, and unsafe deserialization across files. Use when reviewing pending changes, before release-branch, during verify-work Phase 5, during build-epic Step 0 threat modeling, or when the user says \"security review\" or \"scan for vulns\". |
|
||||
| `seed-conventions` | `npm:bigpowers` | Generate CLAUDE.md and CONVENTIONS.md for a brand-new project through a brief interview, and create the specs/ directory with evolved bigpowers structure (product/, tech-architecture/, verifications/, epics/archive/). Entry point for greenfield projects. Use when starting a new project from scratch, when user asks to set up AI agent conventions, or when there is no CLAUDE.md yet. |
|
||||
| `session-state` | `npm:bigpowers` | Track implementation decisions and progress in specs/state.yaml to prevent context rot. Use at the start of a session to load context, and whenever a significant decision is made or a milestone is reached. |
|
||||
| `setup-environment` | `npm:bigpowers` | Pre-install dependencies and configure tools before development work begins. Use at session start on a fresh clone, before kickoff-branch, or when user says setup environment or install deps. |
|
||||
| `simulate-agents` | `npm:bigpowers` | Run Mock User and Auditor agents against a feature in fresh contexts before human review. Use after verify-work, before request-review, when user wants pre-review simulation. |
|
||||
| `slice-tasks` | `npm:bigpowers` | PLANNING SPINE STEP 2 of 3 — Slice the work: break a scoped PRD into vertical-slice stories in specs/epics/. Use after scope-work (step 1), before plan-work (step 3). Not a substitute for scope-work or plan-work. |
|
||||
| `smoke-test` | `npm:bigpowers` | Post-deploy health-check against a live URL. Validates HTTP status, response content, and critical endpoints. Runnable standalone OR as the final step of the deploy skill. |
|
||||
| `spike-prototype` | `npm:bigpowers` | Throw-away prototype for unknown problem spaces. Output is learning notes in specs/archive/spikes/SPIKE-<name>.md, not production code. Use when the domain or technology is unexplored, when estimates are impossible without experimentation, or when user says \"spike\", \"prototype\", or \"proof of concept\". |
|
||||
| `stocktake-skills` | `npm:bigpowers` | Sequential subagent batch audit of the bigpowers skill catalog — Quick Scan (changed only) or Full (all skills). Use during sustain phase, before a major release, or when catalog drift is suspected. |
|
||||
| `survey-context` | `npm:bigpowers` | Per-task context bootstrap — reads existing specs/ and tech-architecture docs to map the current lifecycle phase and suggest the next skill. Use at the start of any task, when returning after a break, or when unsure what to do next. For deriving a tech-stack doc from scratch, use map-codebase first. |
|
||||
| `terse-mode` | `npm:bigpowers` | Fallback ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use ONLY when context is critically long and compressing output is necessary to continue. Not a strategy — token discipline comes from code shape (small functions, unique names, headless tests), not terser prompts. Use when user says \"caveman mode\", \"terse mode\", \"less tokens\", \"be brief\", or invokes /terse-mode. |
|
||||
| `trace-requirement` | `npm:bigpowers` | Link story IDs from specs/release-plan.yaml + epic capsule directories to the implementing code and tests. Produces specs/TRACEABILITY_LATEST.md. Use when you want to verify coverage of a release plan, audit which stories are implemented, or find \"dark\" stories with no code. |
|
||||
| `using-bigpowers` | `npm:bigpowers` | One-time bootstrap that introduces the bigpowers skills system, the PMBOK lifecycle arc, and tells you which skill to call first for your situation. Use when starting with bigpowers for the first time, when user asks \"where do I start?\", or when the skills system needs to be explained. |
|
||||
| `validate-contracts` | `npm:bigpowers` | Assert data shape consistency across system boundaries — live API responses against JSON Schema, key-set comparison across layers, data shape validation for migrations and exports. Catches silent data corruption before deploy. |
|
||||
| `validate-fix` | `npm:bigpowers` | Prove a fix works before declaring done — re-run the failing test, run the full suite, typecheck, lint, and harden against recurrence. Use after implementing a bug fix, when user says \"is this fixed?\", or before closing an investigation. |
|
||||
| `verify-work` | `npm:bigpowers` | Multi-phase UAT gate — cold-start smoke, build, typecheck, lint, tests, step-by-step manual verification, gaps-closure loop. Use after execute-plan or develop-tdd, before audit-code. |
|
||||
| `visual-dashboard` | `npm:bigpowers` | Start a browser-based dashboard that visualizes architecture, implementation plans, and project status. Persists artifacts in .bigpowers/dashboard/. Reads specs/state.yaml, release-plan.yaml, epics, and planning-status via HTTP API or opencode panel. |
|
||||
| `wire-ci` | `npm:bigpowers` | CI pipeline setup with pre-built templates and local validation. Generates GitHub Actions workflows, validates YAML syntax and permissions, supports dry-run via act/gh. The CI equivalent of wire-observability. |
|
||||
| `wire-observability` | `npm:bigpowers` | Add structured JSON logging, observability commands, and idempotent setup scripts to a project. Use when a project needs production-readiness instrumentation, when user wants structured logging, or as a production-readiness gate at any phase of development. |
|
||||
| `write-document` | `npm:bigpowers` | Write, organize, and sync high-integrity technical documents using the BMAD methodology. Ensures every document is Bold, Minimal, Actionable, and Durable. Use when creating architectural docs, technical guides, or organizing the specs/ directory. |
|
||||
| `broken-link` | `npm:bigpowers` | Fixture with broken skill link. |
|
||||
| `missing-verify` | `npm:bigpowers` | Fixture missing verify command. |
|
||||
| `valid-skill` | `npm:bigpowers` | A valid fixture skill for parser tests. |
|
||||
| `align-grid` | `npm:bigpowers` | Build editorial/magazine/report webpages on a GENUINE Müller-Brockmann modular grid (International Typographic Style) — not a decorative one. Encodes the discipline (columns + modules + baseline, grotesque type, flush-left, restrained black/white/red palette) AND the hard-won front-end engineering to make the grid real, visible, and verified: one CSS-variable source of truth, an interactive grid-toggle overlay that lives in the SAME content box as the content, subgrid \"bands\" so every element snaps to a column line, an 8px baseline lock, and runtime OPTICAL ALIGNMENT that puts display type's ink (not its box) on the line. Ships with a scaffold generator and a Puppeteer verification harness that proves 0px adherence. |
|
||||
| `assess-impact` | `npm:bigpowers` | Analyze the blast radius of a proposed change before any code is written. Maps dependents, affected stories, and test coverage. Produces specs/IMPACT_LATEST.md. Use before plan-work on any non-trivial change, when touching a shared module, or when the user asks "what does this break?". |
|
||||
| `story: e51s04` | `npm:bigpowers` | Описание в SKILL.md |
|
||||
| `audit-plan` | `npm:bigpowers` | Evaluate an incoming project plan against bigpowers principles and conventions, surface gaps, and produce a READY/NOT READY verdict before engagement begins. Use when a new project arrives, when adapting a foreign plan, or before running seed-conventions on an unfamiliar codebase. |
|
||||
| `build-epic` | `npm:bigpowers` | Eight-step epic build cycle — reads state.yaml, execution-status.yaml, and one epic capsule; updates status via bp-yaml-set or direct edit. Resume mode runs one step per invocation. Use instead of ad-hoc execute-plan for release work. |
|
||||
| `change-request` | `npm:bigpowers` | Add a new requirement or reorder epics by WSJF against specs/release-plan.yaml and epic capsule directories. Modes Add and Reorder. Use when a new requirement arrives mid-release or the plan needs prioritization. |
|
||||
| `commit-message` | `npm:bigpowers` | Reviews working-tree changes, then drafts a Conventional Commits title/body and states the semantic-release version bump a single such commit would imply. Also notes which defensive-code categories were touched. Use when the user wants to commit recent work, prepare a Conventional Commits message, or asks for semantic-release / semver-consistent messaging before git commit. |
|
||||
| `compose-workflow` | `npm:bigpowers` | Chain multiple bigpowers skills into a custom workflow recipe saved in specs/. Use when a project repeats a non-standard skill sequence, or user wants a documented playbook beyond orchestrate-project modes. |
|
||||
| `context7-mcp` | `npm:bigpowers` | Fetch current library docs via Context7 MCP instead of training data. Use when user asks about frameworks, APIs, setup, or code examples for React, Next.js, Prisma, etc. |
|
||||
| `story: e45s02` | `npm:bigpowers` | Описание в SKILL.md |
|
||||
| `story: e45s31` | `npm:bigpowers` | Описание в SKILL.md |
|
||||
| `define-language` | `npm:bigpowers` | Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to specs/UBIQUITOUS_LANGUAGE_LATEST.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD". |
|
||||
| `Define Success` | `npm:bigpowers` | Описание в SKILL.md |
|
||||
| `delegate-task` | `npm:bigpowers` | Delegate one complex task to a single subagent, review its work in two stages before merging back. Sequential — one agent at a time, with oversight. Use when a task is complex and requires careful review before the result is accepted. Distinct from dispatch-agents (no parallelism here; reviewer sees full diff before proceeding). |
|
||||
| `Deploy` | `npm:bigpowers` | Описание в SKILL.md |
|
||||
| `design-interface` | `npm:bigpowers` | Generate multiple radically different interface designs for a module using parallel sub-agents, then compare trade-offs. Based on "Design It Twice" from A Philosophy of Software Design. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice". |
|
||||
| `story: e51s04` | `npm:bigpowers` | Описание в SKILL.md |
|
||||
| `diagnose-root` | `npm:bigpowers` | Run 4-phase root cause analysis — reproduce, isolate, hypothesize, verify. Use when a bug is confirmed but root cause is unclear, after investigate-bug, or when user mentions root cause analysis. |
|
||||
| `story: e45s38` | `npm:bigpowers` | Описание в SKILL.md |
|
||||
| `dispatch-agents` | `npm:bigpowers` | Dispatch multiple subagents in parallel on independent tasks. No waiting between them — all run concurrently. Use when tasks are truly decoupled and speed matters. Distinct from delegate-task (concurrent here, no inter-task review gate). |
|
||||
| `edit-document` | `npm:bigpowers` | Edit and improve documents by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, restructure, or improve any document — including specs/ files, articles, READMEs, or technical writing. |
|
||||
| `elaborate-spec` | `npm:bigpowers` | Refine a rough idea into a clear, detailed specification through dialogue. Does not produce code. Use when user has a vague idea, wants to think through a feature before planning, or needs to turn "I want X" into a concrete spec. |
|
||||
| `enforce-first` | `npm:bigpowers` | Apply the F.I.R.S.T test quality rubric (per CONVENTIONS.md §Tests) to a test suite or individual tests. Use when develop-tdd is writing tests, when test quality needs to be checked, or when user mentions F.I.R.S.T or "test quality". |
|
||||
| `evolve-skill` | `npm:bigpowers` | Benchmark-gated skill evolution — consume bigpowers-benchmark report, propose plan-work change, edit skill via craft-skill, re-run benchmark, record ADR. Use when a skill underperforms on benchmark or stocktake finds systemic gap. |
|
||||
| `execute-plan` | `npm:bigpowers` | Batch-execute tasks from the active epic capsule sequentially, with a human checkpoint after each step. Use when user has an approved plan and wants step-by-step oversight. |
|
||||
| `extract-design` | `npm:bigpowers` | Extract a Google DESIGN.md file from an HTML prototype (claude.ai/design or any styled page) using Puppeteer, producing machine-readable tokens and AI-generated prose. Use when the user has an HTML prototype and wants a DESIGN.md to anchor their project's visual identity, or when seed-conventions has just scaffolded a new project. |
|
||||
| `story: e51s04` | `npm:bigpowers` | Описание в SKILL.md |
|
||||
| `story: e45s05` | `npm:bigpowers` | Описание в SKILL.md |
|
||||
| `grill-me` | `npm:bigpowers` | Interactive assumption-surfacing Q&A that stress-tests a plan through relentless questioning until every decision is resolved. Use when user wants to challenge a plan, validate decisions from conversation/context, or mentions "grill me". For doc-grounded variant, use grill-with-docs. |
|
||||
| `grill-with-docs` | `npm:bigpowers` | Doc-grounded variant of grill-me — stress-tests plan assumptions by fetching and citing real library or API documentation. Every challenge must cite a real URL. Use when the plan depends on a specific library or external API. |
|
||||
| `guard-git` | `npm:bigpowers` | Block dangerous git commands (push, force push, reset --hard, clean, branch -D, checkout/restore .) and enforce Conventional Commits & Branch Protection before an AI agent runs them. Installs hook scripts for Claude Code, Cursor, Cursor CLI, and Gemini CLI; documents Google Antigravity Terminal deny lists. Use when the user wants git safety hooks, to block git push or destructive git in agents, or to mirror the same policy across AI coding tools. |
|
||||
| `hook-commits` | `npm:bigpowers` | Set up pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing. |
|
||||
| `inspect-quality` | `npm:bigpowers` | Interactive QA session where user reports bugs or issues conversationally, and the agent logs them to specs/bugs/registry.yaml with a structured audit schema. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, or mentions "QA session". |
|
||||
| `investigate-bug` | `npm:bigpowers` | Investigate a bug or issue by exploring the codebase to find root cause, then write a TDD-based fix plan to specs/bugs/BUG-*.md. Use when user reports a bug, wants to investigate a problem, mentions "triage", or wants to plan a fix. |
|
||||
| `kickoff-branch` | `npm:bigpowers` | Create a git worktree and feature branch, then verify a clean test baseline before any code is written. Use when starting a new feature or task, when user wants to work in isolation from main, or mentions "start a branch" or "new worktree". |
|
||||
| `maintain-wiki` | `npm:bigpowers` | Agent-maintained OKF wiki — INGEST source docs, LINT for issues, QUERY across concept pages. Run as part of build-epic Step 8 and verify-work Phase 3. |
|
||||
| `map-codebase` | `npm:bigpowers` | Derives the tech-stack doc from scratch by scanning the codebase — analyzes stack, architecture, and gray areas (error handling, API shapes) and persists findings into specs/tech-architecture/tech-stack.md. Run when the tech doc doesn't exist yet; use survey-context to consume it once it does. |
|
||||
| `migrate-spec` | `npm:bigpowers` | Detect GSD, spec-kit, or BMAD spec artifacts and transform them into bigpowers YAML layout (state.yaml, release-plan.yaml, epics/, requirements/, plans/, ADRs). Use when migrating foreign spec docs. |
|
||||
| `model-domain` | `npm:bigpowers` | Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates specs/tech-architecture/tech-stack.md and specs/adr/ inline as decisions crystallise. Use when user wants to stress-test a plan against their project's domain language and documented decisions. |
|
||||
| `orchestrate-project` | `npm:bigpowers` | Meta-skill that enforces the 6-phase core loop (discover → elaborate → plan → build → verify → release) with hard gates. Use to coordinate multi-phase projects with guaranteed quality checkpoints. One-time command for the entire project lifecycle. |
|
||||
| `organize-workspace` | `npm:bigpowers` | Scans the active workspace for disposable artifacts—logs, caches, stale build output, and stray draft markdown—and proposes consolidation of scattered assets. Produces a reviewable list, asks for explicit confirmation before any delete or move, and optionally revises .gitignore. Use when the user says "clean my room", "organize workspace", "workspace cleanup", "remove temp files", "organize assets", "gitignore", or wants a safe tidy pass. |
|
||||
| `plan-refactor` | `npm:bigpowers` | Create a detailed refactor plan with tiny commits via user interview, then save it as specs/REFACTOR_LATEST.md. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps. |
|
||||
| `plan-release` | `npm:bigpowers` | RELEASE-INDEX BUILDER — Sequence elaborated epics into specs/release-plan.yaml with WSJF ordering and BCP baselines. NOT a planning-spine substitute: it does not scope work (scope-work) or write story tasks (plan-work). Use after elaborate-spec when the user wants a versioned release index of epics. |
|
||||
| `plan-tests` | `npm:bigpowers` | Design a risk-scaled test architecture for an epic before implementation begins. Produces prioritized scenarios, test level distribution, and fixture plans based on TEA and bigpowers principles. |
|
||||
| `story: e45s04` | `npm:bigpowers` | Описание в SKILL.md |
|
||||
| `publish-package` | `npm:bigpowers` | Package registry publishing for npm, crates.io, PyPI, and Homebrew. Verifies prerequisites, runs the publish command, confirms success, and surfaces actionable error hints on failure. |
|
||||
| `story: e51s04` | `npm:bigpowers` | Описание в SKILL.md |
|
||||
| `release-branch` | `npm:bigpowers` | Make the merge/PR/keep/discard decision for a feature branch, verify coverage gates, create the PR with gh, and clean up the worktree. Use when a feature is done and ready to ship, or when user says "release", "merge", or "open a PR". |
|
||||
| `story: e45s07` | `npm:bigpowers` | Описание в SKILL.md |
|
||||
| `research-first` | `npm:bigpowers` | Look-before-build — search registries, repo, existing skills, and web for prior art before implementing. Appends Prior Art to the spec. Use after survey-context and before elaborate-spec, when adding dependencies, or when the task may already be solved. |
|
||||
| `reset-baseline` | `npm:bigpowers` | Restore the project to a known clean state between agent runs or experiments. Use between benchmark runs, after a failed spike, or when user wants a clean working tree. |
|
||||
| `respond-review` | `npm:bigpowers` | Act on a reviewer agent's feedback systematically — categorize findings, apply fixes, verify tests still pass. Use after request-review returns a report, or when user wants to work through code review findings. |
|
||||
| `run-benchmark` | `npm:bigpowers` | Run skill quality benchmarks from specs/benchmarks/ definitions — N-run with/without-skill delta grading, train/validation split, pass@k + benchmark.json reports. Use before and after evolve-skill to prove quality changes are improvements, not regressions. |
|
||||
| `story: e45s37` | `npm:bigpowers` | Описание в SKILL.md |
|
||||
| `run-planning` | `npm:bigpowers` | DISCOVER-PHASE ADVANCER — Drive the discover-phase checklist (specs/planning-status.yaml) through survey-context → scope-work → research-first → elaborate-spec → plan-release → slice-tasks. NOT a duplicate of plan-work or the planning spine; it orchestrates the pre-coding discover phase only. |
|
||||
| `scope-work` | `npm:bigpowers` | PLANNING SPINE STEP 1 of 3 — Scope the work: define what is in and out of scope and save as specs/product/SCOPE_LATEST.yaml. Use before slice-tasks or plan-release on any new initiative. Not a substitute for slice-tasks (step 2) or plan-work (step 3). |
|
||||
| `search-skills` | `npm:bigpowers` | Find the right bigpowers skill from natural-language intent using a local lexical index over SKILL.md frontmatter. Use when unsure which skill to invoke, or at start of research-first. |
|
||||
| `security-review` | `npm:bigpowers` | > |
|
||||
| `seed-conventions` | `npm:bigpowers` | Generate CLAUDE.md and CONVENTIONS.md for a brand-new project through a brief interview, and create the specs/ directory with evolved bigpowers structure (product/, tech-architecture/, verifications/, epics/archive/). Entry point for greenfield projects. Use when starting a new project from scratch, when user asks to set up AI agent conventions, or when there is no CLAUDE.md yet. |
|
||||
| `session-state` | `npm:bigpowers` | Track implementation decisions and progress in specs/state.yaml to prevent context rot. Use at the start of a session to load context, and whenever a significant decision is made or a milestone is reached. |
|
||||
| `setup-environment` | `npm:bigpowers` | Pre-install dependencies and configure tools before development work begins. Use at session start on a fresh clone, before kickoff-branch, or when user says setup environment or install deps. |
|
||||
| `simulate-agents` | `npm:bigpowers` | Run Mock User and Auditor agents against a feature in fresh contexts before human review. Use after verify-work, before request-review, when user wants pre-review simulation. |
|
||||
| `slice-tasks` | `npm:bigpowers` | PLANNING SPINE STEP 2 of 3 — Slice the work: break a scoped PRD into vertical-slice stories in specs/epics/. Use after scope-work (step 1), before plan-work (step 3). Not a substitute for scope-work or plan-work. |
|
||||
| `smoke-test` | `npm:bigpowers` | Post-deploy health-check against a live URL. Validates HTTP status, response content, and critical endpoints. Runnable standalone OR as the final step of the deploy skill. |
|
||||
| `spike-prototype` | `npm:bigpowers` | Throw-away prototype for unknown problem spaces. Output is learning notes in specs/archive/spikes/SPIKE-<name>.md, not production code. Use when the domain or technology is unexplored, when estimates are impossible without experimentation, or when user says "spike", "prototype", or "proof of concept". |
|
||||
| `stocktake-skills` | `npm:bigpowers` | Sequential subagent batch audit of the bigpowers skill catalog — Quick Scan (changed only) or Full (all skills). Use during sustain phase, before a major release, or when catalog drift is suspected. |
|
||||
| `survey-context` | `npm:bigpowers` | Per-task context bootstrap — reads existing specs/ and tech-architecture docs to map the current lifecycle phase and suggest the next skill. Use at the start of any task, when returning after a break, or when unsure what to do next. For deriving a tech-stack doc from scratch, use map-codebase first. |
|
||||
| `terse-mode` | `npm:bigpowers` | Fallback ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use ONLY when context is critically long and compressing output is necessary to continue. Not a strategy — token discipline comes from code shape (small functions, unique names, headless tests), not terser prompts. Use when user says "caveman mode", "terse mode", "less tokens", "be brief", or invokes /terse-mode. |
|
||||
| `trace-requirement` | `npm:bigpowers` | Link story IDs from specs/release-plan.yaml + epic capsule directories to the implementing code and tests. Produces specs/TRACEABILITY_LATEST.md. Use when you want to verify coverage of a release plan, audit which stories are implemented, or find "dark" stories with no code. |
|
||||
| `using-bigpowers` | `npm:bigpowers` | One-time bootstrap that introduces the bigpowers skills system, the PMBOK lifecycle arc, and tells you which skill to call first for your situation. Use when starting with bigpowers for the first time, when user asks "where do I start?", or when the skills system needs to be explained. |
|
||||
| `validate-contracts` | `npm:bigpowers` | Assert data shape consistency across system boundaries — live API responses against JSON Schema, key-set comparison across layers, data shape validation for migrations and exports. Catches silent data corruption before deploy. |
|
||||
| `story: e45s08` | `npm:bigpowers` | Описание в SKILL.md |
|
||||
| `verify-work` | `npm:bigpowers` | Multi-phase UAT gate — cold-start smoke, build, typecheck, lint, tests, step-by-step manual verification, gaps-closure loop. Use after execute-plan or develop-tdd, before audit-code. |
|
||||
| `visual-dashboard` | `npm:bigpowers` | Start a browser-based dashboard that visualizes architecture, implementation plans, and project status. Persists artifacts in .bigpowers/dashboard/. Reads specs/state.yaml, release-plan.yaml, epics, and planning-status via HTTP API or opencode panel. |
|
||||
| `wire-ci` | `npm:bigpowers` | CI pipeline setup with pre-built templates and local validation. Generates GitHub Actions workflows, validates YAML syntax and permissions, supports dry-run via act/gh. The CI equivalent of wire-observability. |
|
||||
| `wire-observability` | `npm:bigpowers` | Add structured JSON logging, observability commands, and idempotent setup scripts to a project. Use when a project needs production-readiness instrumentation, when user wants structured logging, or as a production-readiness gate at any phase of development. |
|
||||
| `write-document` | `npm:bigpowers` | Write, organize, and sync high-integrity technical documents using the BMAD methodology. Ensures every document is Bold, Minimal, Actionable, and Durable. Use when creating architectural docs, technical guides, or organizing the specs/ directory. |
|
||||
| `context-mode` | `npm:context-mode` | Mandatory routing rules for Antigravity CLI. Invoke when exploring a codebase, reading files for analysis, listing context-mode tools, searching, parsing, counting, comparing, summarizing, fetching web content, or running data-heavy commands. |
|
||||
| `context-mode` | `npm:context-mode` | MANDATORY routing rules for context-mode. Invoke whenever you analyze, count, filter, compare, search, parse, or transform data; fetch a URL; or run a data-heavy command — so raw bytes stay out of the context window. |
|
||||
| `context-mode` | `npm:context-mode` | \| |
|
||||
| `ctx-doctor` | `npm:context-mode` | \| |
|
||||
| `ctx-index` | `npm:context-mode` | \| |
|
||||
| `ctx-insight` | `npm:context-mode` | \| |
|
||||
| `ctx-purge` | `npm:context-mode` | \| |
|
||||
| `ctx-search` | `npm:context-mode` | \| |
|
||||
| `ctx-stats` | `npm:context-mode` | \| |
|
||||
| `ctx-upgrade` | `npm:context-mode` | \| |
|
||||
| `obsidian` | `npm:pi-obsidian` | You have access to tools for reading, writing, searching, visualizing, and managing projects in Obsidian vaults. Use these tools to help the user build and maintain their knowledge base. |
|
||||
| `pi-subagents` | `npm:pi-subagents` | \| |
|
||||
| `librarian` | `npm:pi-web-access` | Research open-source libraries with evidence-backed answers and GitHub permalinks. Use when the user asks about library internals, needs implementation details with source code references, wants to understand why something was changed, or needs authoritative answers backed by actual code. Excels at navigating large open-source repos and providing citations to exact lines of code. |
|
||||
| `graphify` | `local ~/.pi/agent` | Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools. |
|
||||
|
||||
### Текущие глобальные настройки
|
||||
|
||||
- Provider по умолчанию: `codex-lb`
|
||||
- Model по умолчанию: `gpt-5.6-terra`
|
||||
- Thinking: `high`
|
||||
- Theme: `dark`
|
||||
|
||||
После установки проверь состояние:
|
||||
|
||||
```bash
|
||||
pi list
|
||||
pi config
|
||||
```
|
||||
|
||||
<!-- PI-MANUAL-RECOVERY:END -->
|
||||
Reference in New Issue
Block a user