菜单
Review session work and optionally update agent memory. Use to capture decisions, patterns, or insights - or just to reflect without changing anything.
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
Create logically grouped, atomic git commits with well-formatted commit messages following best practices. Use this skill when you need to commit changes to a git repository with proper message formatting and atomic grouping. Before creating commits, reflect on the work just completed and surface any open questions or unresolved decisions (judgment calls made without checking, deferred edge cases, defaults picked when multiple options were viable, trade-offs that could reasonably go the other way) via AskUserQuestion so they get discussed with the user rather than silently committed.
Review code with grug-brain anti-complexity philosophy. Use when reviewing PRs, diffs, or code changes to identify unnecessary complexity.
Implement an epic's beads in a worktree with logical commits, multi-agent review, fix pipeline, and PR description generation. Use when you want to implement this epic, burn down the beads, execute the plan, or start working on an epic.
Comprehensive branch review using parallel background agents with Codex validation. Each reviewer runs as an independent background task - results are collected only after all agents complete, eliminating premature synthesis. Use for thorough pre-PR review of any branch size.
Implement fixes for code review findings using a parallel agent team. Accepts a review report (from /team-branch-review, /team-commit-review, or pasted), interviews the user on which findings to fix (or runs autonomously with --auto), then spawns agents to implement fixes in parallel with Codex validation.
Comprehensive branch review using a parallel agent team with Codex validation. Use when reviewing all commits on a branch before creating a PR, especially for large or complex branches that benefit from multi-perspective review. Trigger on "review my branch", "check before I PR", "full code review", "pre-PR review", "team review", or "review before merge".
| name | remember |
| description | Review session work and optionally update agent memory. Use to capture decisions, patterns, or insights - or just to reflect without changing anything. |
The user has triggered a memory review. They may have provided context, or they may just want you to reflect on the session.
$ARGUMENTS
Your auto memory directory path is in your system prompt, in a line like:
You have a persistent auto memory directory at
~/.claude/projects/<project>/memory/.
Extract that path. If you cannot find it, use ~/.claude/projects/ and look for a subdirectory matching the current working directory.
Create the directory if it does not exist yet.
Summarize what happened this session - briefly, 2-3 sentences max.
Read your current memory index at <memory-dir>/MEMORY.md (it may not exist yet - that is fine).
Read any topic files referenced in MEMORY.md that are relevant to this session's work.
Assess whether memory needs updating. Consider:
Report your assessment. Show one of:
If no changes needed:
"Memory is current. Nothing from this session warrants an update."
Done. Stop here.
If changes are warranted: Show exactly what you would add or modify, which file it goes in, and why. Format as a diff-like preview. Then ask: "Want me to apply this?"
Wait for approval. Only write to memory files if the user confirms. If they say no or suggest edits, adjust accordingly.
