メニュー
Scaffold a new logic-* skill in the Logic-Lens repo and wire it into every place a skill must be registered, so no step is missed. Use when adding a seventh (or later) skill to Logic-Lens.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
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。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/hyhmrright/logic-lens --skill new-skillコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Sync the Logic-Lens working-copy skills/ into the installed plugin cache so content-evals test the EDITED skill, not the last published one. ALWAYS run this after editing any skills/**/SKILL.md or guide/_shared file and BEFORE running content-evals — otherwise the eval silently grades stale content and every token is wasted. Also use to verify the cache is in sync ("is the cache fresh?", "did my edit take effect in evals?", "check skill cache drift").
Find logic bugs in a single file or function via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Trigger when a user shares code and suspects something is wrong without naming a concrete failure — phrases like "review this", "does this look right", "check this function", "audit this code", "tests pass but prod fails". SCOPE HARD RULE: one file or one function only. For a directory or whole module use logic-health; for a confirmed failure (stack trace, failing test, specific wrong value) use logic-locate; for two versions use logic-diff; for repo-wide autonomous fixing use logic-fix-all. Do NOT trigger for: style/formatting, security scanning, performance, test generation, architecture or design questions.
Autonomous repository-wide audit-and-fix pipeline: health → review → locate/explain → fix → diff-verify → iterate until clean. Starts with a mandatory consent prompt (token-intensive); after consent runs hands-free. Trigger when the user wants ALL logic issues found and fixed — "fix everything", "fix all logic issues", "fix all logic issues in this code", "clean up all logic issues", "audit and fix the whole repo", "fix all bugs automatically", or frustration with recurring bugs wanting a one-shot pass. SCOPE RULE: repo-wide by default; also trigger for a pasted code snippet when the user says "fix all" — produce the full Fix Report (Fix Log, before/after Logic Score). Analysis-only requests use logic-health or logic-review. Single failure uses logic-locate. Two versions uses logic-diff. One path explanation uses logic-explain. Do NOT trigger for: analysis-only ("show me the bugs"), style/lint/format concerns, or fixing a single named finding.
SOC 職業分類に基づく
SKILL.md を表示中
| name | new-skill |
| description | Scaffold a new logic-* skill in the Logic-Lens repo and wire it into every place a skill must be registered, so no step is missed. Use when adding a seventh (or later) skill to Logic-Lens. |
| disable-model-invocation | true |
CLAUDE.md → "Adding a New Skill" is the authoritative checklist. This skill exists to make sure every step actually runs — the session-start loop and the eval cases are the ones most often forgotten.
Read CLAUDE.md's "Adding a New Skill" section now, then execute its steps for logic-<NAME> (ask the user for <NAME> if not in $ARGUMENTS):
skills/logic-<NAME>/SKILL.md — copy the frontmatter shape from skills/logic-review/SKILL.md (name + description). The description MUST include a "Do NOT trigger for:" clause and a "SCOPE … RULE" line distinguishing it from the other skills. Process section = 5–7 numbered items, each citing a guide step. Follow lazy-loading per skills/_shared/common.md §13.skills/logic-<NAME>/logic-<NAME>-guide.md — numbered steps (Step 1, 2, …), each explaining the why, concrete examples over abstractions.commands/logic-<NAME>.md — mirror commands/logic-review.md:
---
description: <one line>
allowed-tools: Skill
---
Use the Skill tool to invoke `logic-lens:logic-<NAME>`, then follow its instructions exactly. $ARGUMENTS
hooks/session-start (CLAUDE.md step 6 — easy to miss) — add logic-<NAME> to BOTH the for skill in … loop and the printed skill list:
grep -n "for skill in" hooks/session-start
evals/content/v2/evals-v2.json. Trigger cases under evals/trigger/v2/ are optional and only catch description regressions (positive cases always score 0% — see CLAUDE.md → Gotchas).gemini-extension.json — CLAUDE.md says Gemini auto-discovers from skills/, but the file also enumerates each skill+command under contribution. If you want that list complete, add logic-<NAME> entries to both contribution.skills and contribution.commands. (Not checked by validate-repo.sh.)npm run validate and confirm all checks pass.