self-improving-agent
Skill1 starsChanged 48 days agoMITView on GitHub
self-improvement capability in the vertical scenarios and business APIs domain. Use when the user wants to 捕获学习、错误和纠正，让 Agent 自动积累经验并持续改进. Triggers: self-improving-agent, session-logs. Not for requests unrelated to self-improvement. Risk level L1. 中文触发：self-improving-agent、session-logs。
Files
自我改进（self-improving-agent）
用途
捕获学习、错误和纠正，让 Agent 自动积累经验并持续改进。
分类：七、垂直场景与商业 API 类（vertical scenarios and business APIs）
技能类型：自我改进
风险等级：中（持久化记忆可能被污染）
门禁档位：L1 — 涉及读写个人数据或外部账号，先列影响面，关键写操作逐项确认。
触发条件
- 用户提到
self-improving-agent、需要自我改进能力，或提出对应诉求时触发。 - 典型触发词：self-improving-agent、捕获学习、错误和纠正，让 Agent 自动积累经验并持续改进。
- 关联技能：session-logs。
何时不要使用
- 与自我改进无关的请求：不要触发，交给更合适的技能或直接回答。
- 前置依赖未就绪（未授权 / 缺 CLI / 缺网络）时：停下并报告，不要降级为让用户粘贴明文凭据。
- 超出本技能声明范围的目标（其他系统、其他账号）：不越权操作。
功能清单
- 捕获学习点、错误与纠正
- 自动积累经验
- 持续优化后续表现
标准操作流程
- 严格区分测试/生产环境，生产密钥绝不明文出现在命令或日志。
- 涉及资金、交易、订单、客户数据的写操作，必须逐项取得明确授权。
- 优先在沙箱/测试账户验证流程，再过渡到生产。
- 遵循最小权限：仅申请业务必需的 scope/权限。
- 每次操作后回报状态、金额/数量、以及异常时的止损步骤。
外部依赖与前置检查
- 依赖：本地记忆/日志存储
- 执行前确认依赖已就绪（账号已授权 / CLI 已安装 / 环境变量已设置）。
- 凭据通过环境变量或密钥管理器注入，不落盘、不进版本控制。
- 详细配置见
references/setup.md。
典型使用场景
- 长期项目的经验沉淀
- 减少重复犯错
使用提示
建议定期审阅积累的经验，避免错误信息被固化。
备注
- 关联技能：session-logs。
- 本技能由规划规格 README 自动落地生成，操作细节（具体 API/CLI/连接）应在接入真实运行时补全。
- 通用铁律：先验证现状 → 列影响面 → 取得确认 → 再执行；不可逆或涉钱/涉密的动作用最高门禁。
Other versions26 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 26
- farm-fe/farm★ 5.6ksame name
- pskoett/self-improving-agent★ 786same name
- peterskoett/self-improving-agent★ 771same name
- OpenMinis/MinisSkills★ 584same name
- YiShu5/claude-skills★ 131same name
- zeroclaw-labs/zeroclaw-skills★ 65same name
- zhouguoqing/QianYuan.AIAgenticFramework★ 35same name
- delorenj/skills★ 18same name
- Hassaan146/claude-skills★ 18same name
- mick-gsk/drift★ 14same name
16 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use tavily-search, proactive-agent and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
caicongyangSkilltavily-search
Tavily 搜索工具，提供 AI 优化的搜索结果。每月免费 1000 次查询。
Also in 5 projects that use this
halthelobsterSkillproactive-agent
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞
Also in 3 projects that use this
LaoK2017Skillskill-vetter
Security review and audit tool for AI agent skills. Use when asked to "vet a skill", "check skill security", "audit a skill", or when reviewing skills before installation to detect malicious code, unauthorized access, and suspicious patterns.
Also in 3 projects that use this
MicrosoftSkillweb-search
Also in 4 projects that use this
VercelSkillfind-skills
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.
Also in 7 projects that use this
OpenAISkillbrainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Also in 5 projects that use this
In this repository60 other files it gives its agents.
- accessibility-auditSkill
- agent-browser-coreSkill
- ai-explainer-videoSkill
- ai-short-video-makerSkill
- ai-video-shortSkill
- AI 工具箱Skill
- antislopSkill
- browser-useSkill
- cangjie-skillSkill
- delivery-no-pseudoblockSkill
- design-reviewSkill
- design-routerSkill
- edge-tts-readSkill
- frontend-designSkill
- frontend-devSkill
- fuheshun-auto-clipSkill
- fullstack-devSkill
- githubSkill
- git-shipSkill
- grillingSkill
- hfut-inspectorSkill
- humanizerSkill
- image-to-editable-pptxSkill
- kdocsSkill
- local-video-pipelineSkill
- markitdown-skillSkill
- pdfSkill
- pptxSkill
- qf-english-polishSkill
- qq-emailSkill
- responsive-designSkill
- sherpa-onnx-ttsSkill
- short-video-script-to-finished-videoSkill
- skill-creatorSkill
- skill-integratorSkill
- tastemakerSkill
- techdebtSkill
- Typography FoundationsSkill
- ui-designSkill
- video-scriptSkill
- web-accessSkill
- web-design-guidelinesSkill
- web-design-layoutSkill
- wechat-article-proSkill
- wechat-article-searchSkill
- weekly-reviewSkill
- word-toolkitSkill
- WorkBuddy 工作原则Skill
- xlsxSkill
- yuketang-harvesterSkill
- 学术研究工具箱Skill
- 安全审查工具箱Skill
- 工程方法论工具箱Skill
- 开发工具箱Skill
- 微信小程序开发套件Skill
- 技能包跨机器打包Skill
- 文档工具箱Skill
- 知识工具箱Skill
- 联网工具箱Skill
- 评审委员会Skill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.