メニュー
Use this skill to split large plans into smaller chunks. This skill manages your context window for large tasks. Use it when a task will take a long time and cause context issues.
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
Check papers/ structure for completeness and accuracy — every PDF has text extraction, every paper is indexed in PAPER_INDEX.md and summarized in PAPER_SUMMARIES.md, summaries are factually accurate. Prompts the user for discrepancies.
Use when you want to clean up accumulated git worktrees in a repo. Lists all worktrees with status, verifies data symlinks, ensures code and docs are committed, copies non-symlinked data files to main worktree, asks which to merge or keep, runs post-merge audits on new docs/papers, and removes merged worktrees.
Use after creating or modifying decision documents in docs/ to keep DOCS_INDEX.md and DOCS_SUMMARY.md consistent. Also use as a standalone audit to find coverage gaps, broken links, and ADR format issues. Works across any repo with a docs/ directory. Run alongside updating-noridocs when finishing a branch that includes decision docs.
IMMEDIATELY USE THIS SKILL when creating or develop anything and before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning, alternative exploration, and incremental validation
End a research session — runs update-docs to checkpoint all progress, then commits and pushes. Use update-docs for mid-session checkpoints without ending the session.
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
| name | Handle-Large-Tasks |
| description | Use this skill to split large plans into smaller chunks. This skill manages your context window for large tasks. Use it when a task will take a long time and cause context issues. |
Use subagents to manage your context. Each subagent has its own limited context window. Subagents perform best when they have clear implementation guidelines. Each subagent should be given a small and precise task. Create tests for each subagent and explicitly tell the subagent that it is responsible for making sure that test passes. The tests should test behavior. You are responsible for the final output. That means you MUST ensure that everything runs as expected. You should create high level tests that validate overall behavior.
