Create a structured Markdown handoff from the current conversation, covering scope, relevant files, discoveries, completed work, status, and next steps so another agent or a later session can resume the task.
中文简介正在准备中。当前显示英语简介。
Generate a structured handoff document from the current session. Captures scope, relevant files with line numbers, key discoveries, work completed, current status, next steps, and code snippets. Use before ending a session or handing work to another agent.
安装前可以查看交给 AI 代理的指令内容。
Generate a structured handoff document from our current conversation and save it to claudedocs/handoffs/handoff_YYYYMMDD_HHMMSS.md (or use the filename provided as $ARGUMENTS[0] if given).
Create the claudedocs/handoffs/ directory if it does not exist.
Include exactly these sections:
# Handoff: [Task Name] - [YYYY-MM-DD HH:MM]
## Task
[One sentence: what is being accomplished]
## Scope
[In-scope behavior and exclusions. Include the contract revision, base commit and relevant working-tree state, acceptance criteria, applicable ADRs, blockers, permitted actions, and next owner. Mark unknowns explicitly.]
## Files
[All relevant files touched or needed. Format: `path/to/file:line` when a specific line matters]
- `src/auth/middleware.ts:45` - token validation logic
- `tests/auth.spec.ts` - test suite for this change
- `docs/api.md` - needs update after implementation
## Discoveries
[Key findings and insights from the work so far. Things the next agent needs to know that are not obvious from the code]
- [Discovery 1]
- [Discovery 2]
## Work Done
[Historical completion claims. Append-only: never remove prior entries. Include revisions, checks actually run, and evidence links when available.]
- [x] Task A completed (commit: abc1234)
- [x] Task B completed
## Status
[Last observed state and observation time: what is done, what remains, checks and their scope, blockers. Distinguish ticket state, run state, and acceptance.]
## Next Steps
[Actionable checklist of remaining tasks, in order]
1. [ ] Step 1
2. [ ] Step 2
3. [ ] Step 3
## Code
[Relevant code snippets with context. Focus on the parts a resuming agent needs to understand immediately]
\`\`\`typescript
// Key implementation detail
\`\`\`
:line only when verified at the recorded revision.After saving, confirm the file path.
还没有评价。欢迎分享你的使用感受。
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。
Evaluate Claude Code agents, skills, and commands with weighted quality criteria. Get scores, readiness grades, template comparisons, and practical improvement suggestions in Markdown or JSON reports to guide reviews before release.
中文简介正在准备中。当前显示英语简介。
Assess a codebase across seven areas, including exposed credentials, security, dependencies, structure, and tests. Receive category scores, findings tied to file locations, and a prioritized improvement plan with smaller tasks that can be completed quickly.
中文简介正在准备中。当前显示英语简介。
Measure code patterns such as casts to any or disabled lint rules, then run repeated, targeted edits. Keep changes that improve the chosen metric, revert unsuccessful changes, and track results for each improvement loop.
中文简介正在准备中。当前显示英语简介。
Generate several separate solutions, compare them against criteria fixed in advance, and verify the selected result through executable checks or an independent reviewer. Keep a proof log documenting candidates, evidence, failures, and remaining limits.
中文简介正在准备中。当前显示英语简介。
Monitor a live application after deployment and compare it with a saved baseline, a record of its earlier state. Check page responses, loading times, and new errors, flag persistent changes, and produce a per-page health report.
中文简介正在准备中。当前显示英语简介。
Rebuild project context after clearing a conversation or returning to work. Review recent Git history, uncommitted changes, and TODO markers to get a structured summary of project status and suggested next steps.
中文简介正在准备中。当前显示英语简介。