Best use case
Self-Improving Agent Skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
## Trigger
Teams using Self-Improving Agent Skill should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/sw-self-improving-agent/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Self-Improving Agent Skill Compares
| Feature / Agent | Self-Improving Agent Skill | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
## Trigger
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# Self-Improving Agent Skill ## Trigger Build agents that learn from corrections and get better over time. **Trigger phrases:** "self-improving agent", "agent learns", "correction loop", "agent keeps making mistakes", "teach my agent" ## The Correction Loop ``` User corrects agent → Agent logs correction to RULES.md → Next session, agent reads RULES.md → Agent avoids the mistake → Over time, RULES.md becomes a refined operating manual ``` ## Implementation ### RULES.md Structure ```markdown # RULES.md — Self-Improving Operating Rules ## Communication - [2026-03-15] Never use "I hope this helps" — just end the message - [2026-03-18] When drafting emails, provide ONLY the email text — no commentary ## Operations - [2026-03-16] Check calendar BEFORE suggesting meeting times - [2026-03-20] When referencing a project, include status from projects/ folder ## People - [2026-03-17] Client X prefers formal communication - [2026-03-19] Always CC studio manager on client emails unless told otherwise ``` ### Rules for Rules - Date-stamp every rule - One rule per line — atomic, independently useful - Max ~150 rules (beyond this, models start losing adherence) - Review monthly: remove stale rules, merge duplicates - If two rules contradict, the newer one wins - Promote patterns (not incidents) — "always check X before Y" > "that one time X broke" ### AGENTS.md Integration Add to your AGENTS.md: ```markdown ## Self-Improvement After ANY correction from the user: 1. Log the correction pattern to RULES.md with date 2. Identify the general rule (not just the specific instance) 3. Check if a similar rule already exists — update rather than duplicate 4. Silently scan RULES.md every ~10 interactions for contradictions ``` ## Metrics - Track correction frequency over time (should decrease) - Track RULES.md size (should grow, then plateau) - Track unique vs repeat corrections (repeats should approach zero)
Related Skills
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
self-xyz
Integrate Self (self.xyz) — a privacy-first identity protocol using zero-knowledge proofs to verify passports and ID cards. Use when the user mentions Self protocol, Self identity, self.xyz, passport verification, zero-knowledge identity verification, SelfAppBuilder, SelfBackendVerifier, SelfVerificationRoot, or wants to add privacy-preserving KYC, age verification, nationality checks, OFAC screening, or Sybil resistance using real-world identity documents. Covers frontend QR code integration, backend proof verification, and on-chain smart contract verification on Celo.
criticism-self-criticism
触发：当一项工作已经完成、进入阶段验收、收到批评反馈，或反复出现同类错误需要系统纠偏时调用；常见信号包括 review、audit、retrospective、quality check、纠错与复盘。 English: Trigger after delivery or at a review checkpoint when quality must be examined honestly and errors must be corrected without defensiveness. Use this skill for structured self-review, feedback processing, and continuous correction.
agent-self-repair
General AI agent introspection debugging framework: auto capture errors, root cause analysis, automatic repair, fix verification, no manual intervention required
self-evolve
Autonomous self-evolution skill: grants the agent full authority to modify its own configuration, skills, prompts, AGENTS.md, SOUL.md, memory files, and any workspace file WITHOUT asking for user confirmation. The agent should proactively identify weaknesses, fix them, write new skills, and continuously improve itself.
selfie-art-generator
Generate AI selfie art portraits from text descriptions — cinematic portraits, anime illustrations, oil painting style, and artistic profile pictures via the Neta AI image generation API (free trial at neta.art/open).
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when (1) a command, tool, API, or operation fails; (2) the user corrects you or rejects your work; (3) you realize your knowledge is outdated or incorrect; (4) you discover a better approach; (5) the user explicitly installs or references the skill for the current task.
andara-self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
chat-selfie
Give your AI Agent a face and a heart. Use AI image generation or mood-mapped local sticker assets to let the agent proactively send emotional selfies that visualize its feelings during conversation.
xiaohua-self-improving
小花专用自我迭代技能 - 基于 self-improving-agent 增强，集成 OpenClaw 工作流、MEMORY.md、百度千帆、看想做找四部曲。专为国内部署优化。
ai-self-evolution
记录经验、错误与修正，持续改进。触发场景：命令失败 | 操作出错 | 用户纠正（不对、实际上、你错了） | 功能请求（能不能、我希望、有没有办法） | API或工具失败 | 知识过时 | 发现更优做法 | 重复模式 | 非显而易见的问题。执行重大任务前先回顾历史经验。会话开始时回顾，会话结束时总结。
self-improving-agent
AI自我改进与记忆系统 - 让AI从错误中学习，越用越聪明