[Documentation] Use when generating, smart-merging or refactoring the root AI context (CLAUDE.md, AGENTS.md) and its Claude/Codex projections. Config file only: project-config.
中文简介正在准备中。当前显示原文说明。
duc01226/EasyPlatform122026年10月20日 更新
免费在 GitHub 公开
commit
[Git] Use when asked to commit, stage and commit, or save changes. --push also pushes.
中文简介正在准备中。当前显示原文说明。
查看安装方法包含的文件（1）
- SKILL.md1.6 KB
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
- Commit requested changes only; preserve other work. Load project configuration and matching skill overlays; never reconfirm commit/push. Follow root-linked tracking when present; re-stage its edits before candidate checks and refresh affected evidence; never block on tracking.
- Scan the exact pending commit content for secrets before committing; never commit credentials or .env files, and block on findings with redacted file/line/rule evidence. Run applicable checks; reuse unchanged passing evidence and stop on failures or unavailable required checks.
- Resolve
commit.reviewModewithnode .claude/scripts/lib/commit-review-policy.cjs --operation=commit --risk=<low|medium|high>; follow its selection (default/commit-review --fix-loop, at most two rounds), unless current matching review evidence already exists. - Give the review the exact commit descriptor, including paths and
"amend":truewhen applicable; require a matching review receipt or policy-eligible skip via.claude/hooks/lib/review-receipt.cjsbefore committing, and refresh evidence after changes. - Create and verify a concise conventional commit. Only when
commit.fixOriginTrailer: true, addFix-Origin: feedback(requested fix),regression(earlier defect), ornot-applicable(not a fix) to new commits; never reword history to add it; amend only on an explicit amend request for this task's unpushed commit; push only when requested; route PR requests to/pull-requestand report the result.
评价
还没有评价。欢迎分享你的使用感受。
评论
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
同一仓库的技能
[Code Quality] Use when a workflow step or the user asks for AI code or plan review: LLM calls, prompts, agents, RAG, evals and guardrails. --mode={code|plan}; --report-only is read-only.
中文简介正在准备中。当前显示原文说明。
duc01226/EasyPlatform122026年10月20日 更新
[Architecture] Use when a workflow step or the user asks for architecture design, compliance review, scalability grading or whole-project audit via --mode={design|review|scalability|full}.
中文简介正在准备中。当前显示原文说明。
duc01226/EasyPlatform122026年10月20日 更新
[Content] Use when a workflow step or the user asks for product/feature ideation with ranked opportunities and validation tests. --mode={roadmap|scope}.
中文简介正在准备中。当前显示原文说明。
duc01226/EasyPlatform122026年10月20日 更新
[Content] Use when a workflow step or the user asks for business viability: Business Model Canvas, financials, risks and go-to-market recommendation.
中文简介正在准备中。当前显示原文说明。
duc01226/EasyPlatform122026年10月20日 更新
[Code Quality] Use when a workflow step or the user asks for a focused code-change review: staged, unstaged, branch diff or simple pull request. --fix-loop fixes and re-reviews. Complex pull request: workflow-review-changes; rationale: why-review.
中文简介正在准备中。当前显示原文说明。
duc01226/EasyPlatform122026年10月20日 更新