菜单
Project-specific commit message format (verb-led, sentence case, single line, no conventional-commits prefix). Use when drafting a commit message, staging changes for commit, amending, squashing, or when user asks to commit, or runs git commit.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Evaluate, benchmark, compare, and optimize descriptions for existing skills. Use when users want to run evals to test a skill, benchmark skill performance with variance analysis, do blind A/B comparisons between skill versions, or optimize a skill's description for better triggering accuracy. Do NOT use for creating skills from scratch — see write-a-skill for that.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in docs/plans/. Use when user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions "tracer bullets".
Write a structured PRD from design decisions, rough ideas, or conversation context. Use when user wants to write a PRD, create requirements, document a feature spec, or bridge design decisions into a product requirements document. Bridges the gap between design exploration (grill-me) and implementation planning (prd-to-plan).
Fix vulnerabilities identified by /security:review using the Fix-Verify Loop. Use when: user says "fix security findings", "remediate vulnerabilities", or invokes /security:fix with a report path. Requires an existing security review report as input. Modifies source code — explicit opt-in only.
Load when performing dual-source security review, cross-validating Semgrep findings with Codex, or resolving conflicting vulnerability assessments. Trigger on: security audit, scan vulnerabilities, cross-validate findings, conflict resolution, confidence scoring.
| name | commit-style |
| description | Project-specific commit message format (verb-led, sentence case, single line, no conventional-commits prefix). Use when drafting a commit message, staging changes for commit, amending, squashing, or when user asks to commit, or runs git commit. |
<Verb> <what changed>
type: or type(scope): formatWhy: This matches the project's existing git history. Consistent verb-led messages make git log --oneline scannable without extra ceremony.
Use commas to list related changes in one commit:
Consolidate rules: add examples, merge TDD/error sections, reduce overlap
A colon separates the high-level intent from the details when a commit touches multiple concerns.
| Verb | Use when |
|---|---|
| Add | Introducing something new |
| Fix | Correcting broken behavior |
| Update | Changing existing content or config |
| Remove | Deleting code, files, or features |
| Refactor | Restructuring without behavior change |
| Rework | Significant redesign of an existing piece |
| Standardize | Making things consistent |
| Harden | Strengthening security or robustness |
| Trim | Removing unnecessary parts |
This skill applies only when the user asks for a commit. Claude does not create commits unsolicited (see workflow.md). The format here applies to commit subjects — not PR titles, branch names, or tag annotations unless the user asks for consistency.
🤖 Generated with Claude Code footers or Co-Authored-By: trailers unless the user explicitly requests them — the project's git log is clean and this repo's convention is trailer-freegit log --oneline -20 and mirror recent style rather than guessing