ワンクリックで
ratchet-help
Show Ratchet help — available commands, output locations, skill and strategy structure, and usage tips.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Show Ratchet help — available commands, output locations, skill and strategy structure, and usage tips.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Collect Ratchet local pipeline debug evidence. Use when a run is failed, stuck, stale, stopped, missing outputs, has confusing LLM behavior, or needs local evidence from pipeline traces, events.jsonl, worker.log, raw LLM artifacts, and a debug bundle directory.
Show local Ratchet setup status and optional host-agent configuration.
Evaluate and enhance a ratchet skill using LLM-as-judge A/B testing with an iterative improvement loop.
Run the Ratchet skill extraction pipeline to analyze project sessions and generate reusable skills and strategies.
View or update your Ratchet developer profile (language, level, style) to personalise skill extraction.
Show Ratchet status including pending skills, strategies, and recent pipeline runs.
| name | ratchet-help |
| description | Show Ratchet help — available commands, output locations, skill and strategy structure, and usage tips. |
| argument-hint | |
| allowed-tools | Read |
| Command | Description |
|---|---|
/ratchet:login | Show local setup status |
/ratchet:wisdom-gen | Run skill extraction pipeline |
/ratchet:skill-enhance | Evaluate and enhance a skill with A/B testing |
/ratchet:wisdom-curate | Curate a wisdom-backed workflow with skill installation |
/ratchet:status | Show pending items and status |
/ratchet:debug | Collect local pipeline evidence and write a debug bundle directory |
/ratchet:stop | Stop a running pipeline |
/ratchet:profile | View or update your developer profile |
/ratchet:help | Show this help |
| Type | Pending Location | Installed Location |
|---|---|---|
| Skills | ~/.local/ratchet/data/pending-skills/{name}/ | .claude/skills/{name}/SKILL.md |
| Strategies | ~/.local/ratchet/data/pending-strategies/{name}.md | .claude/rules/ratchet/{name}.md |
| Curated Skills | — | {data_dir}/skills/{name}/SKILL.md |
| Curations | {data_dir}/curations/pending/{session_id}.json | {data_dir}/curations/completed/{session_id}.json |
Generated skills follow this structure:
~/.local/ratchet/data/pending-skills/{skill-name}/
├── SKILL.md # Main skill content
├── injection.json # Auto-trigger rules
├── evidence.json # Source evidence
└── metadata.json # Generation info
Strategies are modular rules saved as:
---
paths: **/*.py
---
# Strategy Title
Clear statement of the preference or convention.
Ratchet defaults to deterministic local embeddings and structured heuristic generation. Optional host-agent generation can be enabled with:
ratchet configure --llm-mode host-cli --host-agent codex
/plugin marketplace update mind-ai-ratchet