25 hyhmrright
new-skill Skill
在 Logic-Lens 仓库中搭建一个新的 logic-* 技能,并接入所有需要注册该技能的位置,确保不漏步骤。用于向 Logic-Lens 添加第七个(或更晚的)技能。
安装方式:把技能目录放入 ~/.claude/skills/(Claude Code)或在 claude.ai 设置中启用;也可复制右侧安装命令一键添加。
技能指令原文(SKILL.md)
new-skill
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- (ask the user for if not in $ARGUMENTS):
skills/logic-/SKILL.md— copy the frontmatter shape fromskills/logic-review/SKILL.md(name+description). ThedescriptionMUST 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 perskills/_shared/common.md§13.skills/logic-/logic--guide.md— numbered steps (Step 1, 2, …), each explaining the why, concrete examples over abstractions.commands/logic-.md— mirrorcommands/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) — addlogic-to BOTH thefor skill in …loop and the printed skill list:
grep -n "for skill in" hooks/session-start
- Eval cases (CLAUDE.md step 7 — easy to miss) — add 3–5 content cases to
evals/content/v2/evals-v2.json. Trigger cases underevals/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 fromskills/, but the file also enumerates each skill+command undercontribution. If you want that list complete, addlogic-entries to bothcontribution.skillsandcontribution.commands. (Not checked byvalidate-repo.sh.)- Validate — run
npm run validateand confirm all checks pass.