commit-context
此技能能够将代码文件、函数或特定行追溯到生成其当前提交的 AI Agent 会话。当用户需要了解“这段代码为何在此”、“Agent 在更改时做了什么”或需要代码库特定位置的上下文时,该 Skill 能提供关键的历史背景和决策依据,极大地提升代码理解和问题排查效率。
npx skills add https://github.com/rohitg00/agentmemory --skill commit-contextBefore / After 效果对比
1 组在没有此技能之前,用户或开发者需要手动执行 `git blame` 或 `git log` 等命令,然后尝试从 commit message 中推断代码变更的意图,或者花费大量时间查找相关文档和沟通,这不仅效率低下,还容易遗漏关键的 Agent 决策信息。
此技能能够快速将代码变更追溯到生成该 commit 的 AI Agent 会话,直接提供变更的上下文、目的和相关观察记录,大幅减少手动分析和沟通的时间,确保开发者能准确理解 Agent 的行为逻辑。
The user wants commit context for: $ARGUMENTS
Quick start
git blame -L 40,52 src/auth/refresh.ts # -> SHA 9a1b2c3d
memory_commit_lookup { "sha": "9a1b2c3d4e5f60718293a4b5c6d7e8f901234567" }
Expected output:
9a1b2c3 on main by dev: "rotate refresh tokens"
Linked session 7f3a9c2 "Auth refresh rework", 14 obs.
Why
Report only what git and the lookup return. When the lookup gives commit: null,
the commit predates session linking; do not invent intent.
Workflow
- Find the SHA:
git blame -L <start>,<end> <file>for a line range;git log -L :<function>:<file>for a function;git log -n 1 -- <file>for a bare path. - Look it up:
memory_commit_lookup { "sha": "<full-sha>" }. - Present the commit (sha, short sha, branch, author, message), the linked
session(s) (id, project, started/ended, observation count, summary), and the
importance >= 7 observations via
memory_recallwhen available.
Anti-patterns
WRONG: lookup returns { "commit": null }, you narrate "the agent was
refactoring auth" from the diff alone.
RIGHT: "This commit predates session linking, so there is no recorded agent
session. From git show: it changed token rotation in refresh.ts."
Checklist
- SHA came from git blame/log, not a guess.
commit: nullreported as "predates linking", no fabricated session.- Session details quote the lookup response verbatim.
- No intent claimed beyond what observations state.
See also
commit-history: list many agent-linked commits at once.recall: dig deeper into the linked session's observations.
Troubleshooting
See ../_shared/TROUBLESHOOTING.md if memory_commit_lookup is not available.
用户评价 (0)
发表评价
暂无评价
统计数据
用户评分
为此 Skill 评分