メニュー
Use when collecting verified project-local coding guidance into .claude/skills based on the project tech stack, with TTL and user-edit protection.
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
| name | Qcollect-skill |
| description | Use when collecting verified project-local coding guidance into .claude/skills based on the project tech stack, with TTL and user-edit protection. |
| invocation_trigger | Use when the user explicitly asks to collect, refresh, or install project-local stack skills. |
| recommendedModel | sonnet |
Foreground-only command that collects verified, project-specific coding guidance into .claude/skills/<name>/SKILL.md.
This skill never schedules background collection, never uses --permission-mode dontAsk, and never offers --force. User-edited generated skills can only be replaced with the explicit --overwrite-user-edits flag, which creates a timestamped .bak first.
.qe/analysis/tech-stack.md, derive stack targets, then collect missing or expired generated local skills.<name>: collect or refresh exactly .claude/skills/<name>/SKILL.md; this path does not require tech-stack.md.--overwrite-user-edits: allow replacing a generated skill whose body hash no longer matches, after the writer creates a timestamped .bak..qe/analysis/tech-stack.md is missing, stop and tell the user to run /Qinit or /Qrefresh. If it is stale, warn and continue..gitignore check..gitignore must contain .claude/skills/; otherwise stop and ask the user to add it.Edeep-researcher using the Local Skill Collection prompt in that agent.published_at for every sourcescripts/lib/skill-collection-writer.mjs. The writer validates frontmatter, blocks unsafe command content, computes content_hash, and writes atomically.Collected skills must use this frontmatter shape:
source: official docs and dated references summary
collected_at: 2026-07-17T12:00:00Z
ttl_days: 90
expires_at: 2026-10-15T12:00:00Z
generated_by: Qcollect-skill
content_hash: sha256:...
verification:
devils_advocate_ran: true
sources:
- url: https://example.com/docs
published_at: 2026-07-01
conflicting_claims: []
.qe/analysis/tech-stack.md for no-argument stack discoverytech-stack.mdEdeep-researcher.claude/skills/ in .gitignore for git repositories--permission-mode dontAsk.qe/skill-collection/index.json--forcetech-stack.md from SessionStart hooksShows QE Framework usage overview. With no arg, prints the full catalog. With a skill name arg (e.g., /Qhelp Qcommit), reads that skill's SKILL.md and summarizes it in the user's language. Also supports find/search skills mode via reference/find-skills.md.
QE framework (Query Executor) initial setup. Creates the QE state directory, client-specific instruction/config artifacts, and .gitignore entries in a new project, then auto-analyzes the project. Use when the user wants to initialize a project or set up the framework.
Diagnoses and repairs QE installation health across qe-framework, MCP client config, and the project .qe directory. Use for 'doctor', 'check QE health', dependency verification, corrupted .qe state, or repair guidance. Distinct from Qupdate, which updates installed assets.
Use when executing a TASK_REQUEST/VERIFY_CHECKLIST or when already-changed code needs the test-review-fix quality loop. With no flag it auto-selects sequential or parallel-wave execution; `-verify` runs verification. Use Qautoresearch for iterative code-optimization loops and Qscenario-test for scenario/E2E.
Use when a plan or task needs spec documents: TASK_REQUEST and VERIFY_CHECKLIST. Use Qplan for roadmap/phases; use Qexecute after the spec exists.
Use when the user invokes Qgs or a Qplan handoff needs TASK_REQUEST + VERIFY_CHECKLIST generation. Alias for Qgenerate-spec. Use Qplan for roadmap; use Qexecute after specs exist.