MCPInstall

self-improving-agent

AI自我改进与记忆系统 - 解决'同类错误反复犯、用户纠正不长记性'的痛点。自动捕获错误、用户纠正、最佳实践,并转化为长期记忆。

Installs
1.4K
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://skills.volces.com --skill self-improving-agent
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads self-improving-agent automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Self-Improving Agent

让AI从错误中学习,越用越聪明。

核心解决的问题

✅ 命令/操作莫名失败,下次还用同样的错方式
✅ 反复纠正AI的写法、偏好、风格,它下个会话又忘了
✅ 同一个项目里反复踩同一个坑
✅ 发现更好的做法/更优解法,却没有系统化记住
✅ 外部工具/API变动,AI还在用旧知识
✅ 重要经验只存在于当前会话,跨天/跨项目就丢失

安装

# 创建记忆目录
mkdir -p ~/.openclaw/memory/self-improving

# 使用本skill
cat ~/.openclaw/skills/self-improving-agent/SKILL.md

使用方法

1. 记录错误(自动)

当命令失败时,自动记录到错误库:

# 脚本会自动捕获并记录
python3 ~/.openclaw/skills/self-improving-agent/log_error.py \
  --command "npm install xxx" \
  --error "permission denied" \
  --fix "use sudo or check permissions"

2. 记录用户纠正

当用户说:

  • "不对,应该..."
  • "错了,要用..."
  • "不对,我之前说过..."

自动记录:

python3 ~/.openclaw/skills/self-improving-agent/log_correction.py \
  --topic "代码风格" \
  --wrong "用了双引号" \
  --correct "项目要求单引号" \
  --context "AGENTS.md 第23行"

3. 记录最佳实践

发现更好的做法时:

python3 ~/.openclaw/skills/self-improving-agent/log_best_practice.py \
  --category "security" \
  --practice "安装skill前必须审计代码" \
  --reason "防止供应链投毒"

4. 查看记忆(执行前自动检查)

# 执行命令前,先检查是否有相关记忆
python3 ~/.openclaw/skills/self-improving-agent/check_memory.py \
  --command "npm install"

输出示例:

⚠️ 发现相关记忆:
  [错误] 2026-03-05: npm install 权限失败 → 改用 sudo 或在用户目录安装
  [纠正] 2026-03-04: 项目使用单引号而非双引号

文件结构

~/.openclaw/memory/self-improving/
├── errors.jsonl          # 错误记录
├── corrections.jsonl     # 用户纠正
├── best_practices.jsonl  # 最佳实践
├── knowledge_gaps.jsonl  # 知识盲区
└── index.json           # 快速索引

自动触发场景

场景自动记录触发词
命令失败✅ errors退出码非0
用户纠正✅ corrections"不对" "错了" "应该"
更好的方法✅ best_practices"更好的" "更高效" "最优"
知识过时✅ knowledge_gaps"过时了" "已废弃" "新版是"

跨项目同步

重要记忆自动同步到:

  • ~/.openclaw/memory/self-improving/ (全局)
  • 当前项目 .learnings/ (项目级)
  • AGENTS.md (用户偏好)
  • MEMORY.md (长期记忆)

与现有Skill对比

功能原self-improvement本skill
记录错误✅✅
记录纠正✅✅ 增强版
自动触发❌ 手动✅ 自动
跨项目记忆❌ 项目级✅ 全局+项目
执行前检查❌✅
知识过时检测❌✅

示例工作流程

场景1:用户纠正代码风格

用户: "不对,我说过项目里要用单引号"

AI动作:

  1. 自动记录纠正到 corrections.jsonl
  2. 更新 AGENTS.md 添加代码风格规则
  3. 回复: "已记录,下次会使用单引号"

场景2:命令反复失败

AI: 执行 npm install -g xxx 结果: 权限失败

AI动作:

  1. 记录错误到 errors.jsonl
  2. 下次执行前检查记忆
  3. 自动改用: sudo npm install -g xxx 或本地安装

场景3:发现更好做法

用户: "其实用 pip install -e . 更高效"

AI动作:

  1. 记录最佳实践到 best_practices.jsonl
  2. 后续安装Python包时优先使用 editable 模式

注意事项

  • 记忆文件定期备份到git
  • 敏感信息脱敏后记录
  • 定期review并清理过时记忆

Created: 2026-03-05 by 老二

FAQ

What does the self-improving-agent skill do?

AI自我改进与记忆系统 - 解决'同类错误反复犯、用户纠正不长记性'的痛点。自动捕获错误、用户纠正、最佳实践,并转化为长期记忆。

How do I install self-improving-agent?

Run npx skills add https://skills.volces.com --skill self-improving-agent in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/self-improving-agent/ (personal) or .claude/skills/self-improving-agent/ (project).

Which AI agents can use self-improving-agent?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is self-improving-agent safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains self-improving-agent?

It is published by skills.volces.com in skills.volces.com. It has 1,415 recorded installs.

More from skills.volces.com

View all →

byted-web-search

skills.volces.com

火山引擎豆包搜索 API(原联网搜索/融合信息搜索),返回网页/图片结果。联网搜索场景优先使用本 skill。触发词包括:豆包搜索、查/搜/找、真的吗/靠谱吗/确认/核实、最近/今天/最新/近期、出处/来源/链接、Agent Plan、融合信息搜索、Harness、有什么/有哪些/推荐、价格/政策/汇率/行情、对比/区别/哪个好、听说/据说/不太确定、热搜/热门/火、帮我看/了解一下、求证/辟谣、值不值得/该不该。任务依赖在线事实或时效性时优先使用。若回答可能依赖外部事实,优先调用本 skill 再作答。

byted-supabase

skills.volces.com

火山引擎 Supabase . 管理 AIDAP Supabase 项目、工作区、数据库、分支、Auth、Realtime、Edge Functions、Storage、API Keys、SQL、Schema 变更、TypeScript 类型生成和 MCP 集成。

Data & Databases11.1K installs

find-skills

skills.volces.com

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Backend & APIs1.6K installs

byted-util-ark-cua

skills.volces.com

Delegate broad computer-use tasks to ARK CUA for Volcengine AgentPlan users through an authenticated cloud desktop, and synchronize explicit credentials to a caller-owned CUA through Credential Agent. Use for web or desktop-app operation, file workflows, reusable task contexts, artifacts, temporary CUA App URLs, desktop shutdown/start/recovery, inspection, or exact browser, environment, secret, Credential Set, and managed-file credential setup/sync/status/reset. Do not use when local reasoning or a purpose-built local/API tool can complete the request more directly.

agent-browser

skills.volces.com

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

ocr-document-processor

skills.volces.com

Extract text from images and scanned PDFs using OCR. Supports 100+ languages, table detection, structured output (markdown/JSON), and batch processing.

Docs & Writing1.2K installs

Popular other skills

View category →

hyperframes-cli

heygen-com/hyperframes

The HyperFrames CLI by job - scaffold, check, look at frames, edit the timeline, preview, render locally or in the cloud, publish, project history - plus reading its JSON and recovering from build or render failures.

1.3M installs

triage

mattpocock/skills

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

1M installs

ask-matt

mattpocock/skills

Ask which skill or flow fits your situation. A router over the skills in this repo.

778.4K installs

to-questionnaire

mattpocock/skills

Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

508.9K installs

wait-what

mattpocock/skills

Stop. That last message did not land: re-pitch it.

459.7K installs

loop-me

mattpocock/skills

Grill me about specs for the workflows I want to build, within this workspace.

447.9K installs