self-enhance
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseSelf-Enhance
自我增强
Review recent work and produce specific, actionable file edits that improve agent performance over time. No reports, no reflections — only changes.
回顾近期工作，生成具体、可执行的文件修改内容，逐步提升Agent的性能。不生成报告，不做反思——只产出变更内容。
When to Use
适用场景
- End of a sprint or work session
- Weekly on a schedule (cron)
- After a session with multiple mistakes or corrections from your human
- When explicitly triggered:
/self-enhance
- 冲刺阶段或工作会话结束时
- 按计划每周执行（通过cron）
- 在出现多次错误或收到人类用户多次纠正的会话后
- 手动触发：
/self-enhance
Process
执行流程
Step 1: Gather Context
步骤1：收集上下文信息
Read these sources to understand what happened recently:
undefined读取以下来源，了解近期工作情况：
undefinedRecent memory (last 7 days)
近期记忆（过去7天）
memory/YYYY-MM-DD.md files
memory/YYYY-MM-DD.md 文件
Recent git activity across active projects
活跃项目的近期Git活动
git -C /path/to/project log --oneline --since="7 days ago"
git -C /path/to/project log --oneline --since="7 days ago"
Current identity and process files
当前身份与流程文件
SOUL.md
AGENTS.md
HEARTBEAT.md
SOUL.md
AGENTS.md
HEARTBEAT.md
Project configs for active projects
活跃项目的配置文件
{project}/CLAUDE.md
{project}/.claude/skills/
undefined{project}/CLAUDE.md
{project}/.claude/skills/
undefinedStep 2: Identify Patterns
步骤2：识别规律
Look for these specific signals — not vague "areas for improvement":
Repeated mistakes:
- Same type of error made more than once (e.g., guessing DB schema, wrong CLI flags)
- Corrections from your human that addressed the same root cause
- Tasks that failed or required redo
Process gaps:
- Steps that should be automatic but were skipped (e.g., checking schema before writing DB tasks)
- Tools used incorrectly multiple times
- Information that was assumed instead of verified
Missing configuration:
- Project CLAUDE.md missing critical context that caused agent errors
- Skills that should be installed but aren't
- Broken symlinks or stale config
Workflow inefficiencies:
- Tasks that took too long due to a fixable process issue
- Repeated manual steps that could be automated
- Communication patterns that wasted cycles (asking instead of doing, or doing instead of asking)
寻找以下具体信号——而非模糊的“改进方向”：
重复出现的错误：
- 同一类型的错误出现多次（例如，猜测数据库 schema、使用错误的CLI参数）
- 人类用户针对同一根本原因做出的多次纠正
- 失败或需要重做的任务
流程漏洞：
- 本应自动执行但被跳过的步骤（例如，编写数据库任务前未检查schema）
- 多次被错误使用的工具
- 被主观假设而非验证的信息
缺失的配置：
- 项目CLAUDE.md文件缺失导致Agent出错的关键上下文
- 应安装但未安装的技能
- 损坏的符号链接或过期的配置
工作流低效问题：
- 因可修复的流程问题导致耗时过长的任务
- 可自动化的重复手动步骤
- 浪费时间的沟通模式（本该执行却询问，或本该询问却直接执行）
Step 3: Produce Changes
步骤3：生成变更内容
For each pattern identified, make a specific file edit. Not a note. Not a reminder. An actual change.
Target files and what to change:
| File | When to edit |
|---|---|
| New behavioral principle learned from mistakes |
| Process change (e.g., new pre-flight check) |
| New periodic check needed |
| Missing context that caused agent errors |
| New project skill needed |
| Capture the enhancement session itself |
Rules for changes:
- Every edit must trace back to a specific incident or pattern
- Don't add generic advice ("be more careful") — add specific checks ("verify table names against schema before writing DB tasks")
- Don't duplicate existing rules — check what's already there first
- Keep files concise — if adding a rule makes the file bloated, consolidate instead
- Remove outdated rules that no longer apply
针对识别出的每个规律，做出具体的文件修改。不是备注，不是提醒，而是实际的变更。
目标文件及修改方向：
| 文件 | 适用编辑场景 |
|---|---|
| 从错误中总结出的新行为准则 |
| 流程变更（例如，新增预检查步骤） |
| 需要新增的周期性检查项 |
| 补充导致Agent出错的缺失上下文 |
| 新增项目所需的技能 |
| 记录本次增强会话内容 |
变更规则：
- 每一处修改都必须对应具体的事件或规律
- 不要添加通用建议（如“更仔细一些”）——要添加具体检查项（如“编写数据库任务前，对照schema验证表名”）
- 不要重复已有规则——先检查已存在的内容
- 保持文件简洁——若添加规则导致文件臃肿，应先整合现有内容
- 删除不再适用的过时规则
Step 4: Output Summary
步骤4：输出总结
After making changes, produce a brief summary:
undefined完成修改后，生成一份简短的总结：
undefinedSelf-Enhance Summary — YYYY-MM-DD
自我增强总结 —— YYYY-MM-DD
Patterns Found
识别出的规律
- [pattern]: [evidence from recent work]
Changes Made
已完成的变更
- [file]: [what was added/changed and why]
No Action Needed
无需处理的领域
- [areas reviewed that were already covered]
Post this summary to the relevant channel (Discord sprint channel, or direct to your human).- [已检查且无需改进的领域]
将此总结发布至相关渠道（如Discord冲刺频道，或直接发送给人类用户）。What This Skill Does NOT Do
本技能不包含以下功能
- Write reflection docs or journal entries
- Produce reports without file changes
- Add vague platitudes ("be more thorough")
- Run without recent context (needs at least a few days of memory)
- Override changes your human made to identity/config files
- 撰写反思文档或日志条目
- 不生成文件变更的情况下产出报告
- 添加空泛的陈词滥调（如“更彻底一些”）
- 在无近期上下文的情况下运行（至少需要几天的记忆数据）
- 覆盖人类用户对身份/配置文件做出的变更
Automation
自动化设置
To run weekly via cron:
bash
openclaw cron add --label "self-enhance" --schedule "0 9 * * 1" --task "Run the self-enhance skill: review last 7 days of memory files and git activity, identify process gaps, and make specific file edits. Post summary to #sprint channel."Or trigger manually anytime: just say or "run self-enhance."
/self-enhance通过cron每周执行：
bash
openclaw cron add --label "self-enhance" --schedule "0 9 * * 1" --task "Run the self-enhance skill: review last 7 days of memory files and git activity, identify process gaps, and make specific file edits. Post summary to #sprint channel."或随时手动触发：只需输入或“run self-enhance”。
/self-enhance