self-improving-agent
Skill35 starsChanged 6 months agoApache-2.0View on GitHub
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.
29 other projects use a version of this, 1 of them edited.
Adopted by
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Most recently taken up by
- Anlide11/claude-skillstheir own version, first seen Nov 16, 2026
- darkweb19/skillstheir own version, first seen Nov 8, 2026
- memi-design/design-skillstheir own version, first seen Nov 8, 2026
- delorenj/skillstheir own version, first seen Nov 7, 2026
- smiling66652/workbuddy-skill-toolkitstheir own version, first seen Nov 1, 2026
- kopp0510/claude-ddtheir own version, first seen Oct 30, 2026
Used with
Projects with it also use tavily-search, skill-vetter and 6 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
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
VercelSkillagent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Also in 4 projects that use this
OpenAISkillverification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Also in 3 projects that use this
OpenAISkillwriting-plans
Use when you have a spec or requirements for a multi-step task, before touching code
Also in 3 projects that use this
- +1 more from openai
Other versions29 projects use a version of this.
Word for word · 2
- farm-fe/farm★ 5.6k100% same
- pengt1993/claude-skills★ 1100% same
Edited · 1
- xiangu152/my_claude_skills★ 252% same
Wrote their own version · 26
- peterskoett/self-improving-agent★ 786same name
- pskoett/self-improving-agent★ 786same name
- OpenMinis/MinisSkills★ 612same name
- YiShu5/claude-skills★ 131same name
- zeroclaw-labs/zeroclaw-skills★ 65same name
- Hassaan146/claude-skills★ 18same name
- delorenj/skills★ 17same name
- mick-gsk/drift★ 14same name
- dglijin-oss/chinese-metaphysics-skills★ 13same name
- kopp0510/claude-dd★ 12same 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.
In this repository18 other files it gives its agents.
- agent-browser-automationSkill
- api-gatewaySkill
- brainstormingSkill
- brainstormSkill
- find-skillsSkill
- git-essentialsSkill
- pdfSkill
- proactive-agentSkill
- skill-creatorSkill
- summarizeSkill
- using-superpowersSkill
- weather-querySkill
- agent-browser-automationSkill
- api-gatewaySkill
- git-essentialsSkill
- proactive-agentSkill
- self-improving-agentSkill
- weather-querySkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 18 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 182
After any skill completes, extract:
- Distinctive: line 233
Update the appropriate skill files with evolution markers:
- Very specific: line 317
Use the validation template in references/appendix.md when reviewing updates.
- Very specific: line 323
Add to Claude Code settings (~/.claude/settings.json):
- Distinctive: line 394
After any skill completes, this agent automatically:
“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Self-Improving Agent
"An AI agent that learns from every interaction, accumulating patterns and insights to continuously improve its own capabilities." — Based on 2025 lifelong learning research
Overview
This is a universal self-improvement system that learns from ALL skill experiences, not just PRDs. It implements a complete feedback loop with:
- Multi-Memory Architecture: Semantic + Episodic + Working memory
- Self-Correction: Detects and fixes skill guidance errors
- Self-Validation: Periodically verifies skill accuracy
- Hooks Integration: Auto-triggers on skill events (before_start, after_complete, on_error)
- Evolution Markers: Traceable changes with source attribution
Research-Based Design
Based on 2025 research:
| Research | Key Insight | Application |
| SimpleMem | Efficient lifelong memory | Pattern accumulation system |
| Multi-Memory Survey | Semantic + Episodic memory | World knowledge + experiences |
| Lifelong Learning | Continuous task stream learning | Learn from every skill use |
| Evo-Memory | Test-time lifelong learning | Real-time adaptation |
The Self-Improvement Loop
┌─────────────────────────────────────────────────────────────────┐
│ UNIVERSAL SELF-IMPROVEMENT │
├─────────────────────────────────────────────────────────────────┤
│ │
│ Skill Event → Extract Experience → Abstract Pattern → Update │
│ │ │ │ │ │
│ ▼ ▼ ▼ ▼ │
│ ┌─────────────────────────────────────────────────────┐ │
│ │ MULTI-MEMORY SYSTEM │ │
│ ├─────────────────────────────────────────────────────┤ │
│ │ Semantic Memory │ Episodic Memory │ Working Memory │ │
│ │ (Patterns/Rules) │ (Experiences) │ (Current) │ │
│ │ memory/semantic/ │ memory/episodic/ │ memory/working/│ │
│ └─────────────────────────────────────────────────────┘ │
│ │
│ ┌─────────────────────────────────────────────────────┐ │
│ │ FEEDBACK LOOP │ │
│ │ User Feedback → Confidence Update → Pattern Adapt │ │
│ └─────────────────────────────────────────────────────┘ │
│ │
└─────────────────────────────────────────────────────────────────┘When This Activates
Automatic Triggers (via hooks)
| Event | Trigger | Action |
| before_start | Any skill starts | Log session start |
| after_complete | Any skill completes | Extract patterns, update skills |
| on_error | Bash returns non-zero exit | Capture error context, trigger self-correction |
Manual Triggers
- User says "自我进化", "self-improve", "从经验中学习"
- User says "分析今天的经验", "总结教训"
- User asks to improve a specific skill
Evolution Priority Matrix
Trigger evolution when new reusable knowledge appears:
| Trigger | Target Skill | Priority | Action |
| New PRD pattern discovered | prd-planner | High | Add to quality checklist |
| Architecture tradeoff clarified | architecting-solutions | High | Add to decision patterns |
| API design rule learned | api-designer | High | Update template |
| Debugging fix discovered | debugger | High | Add to anti-patterns |
| Review checklist gap | code-reviewer | High | Add checklist item |
| Perf/security insight | performance-engineer, security-auditor | High | Add to patterns |
| UI/UX spec issue | prd-planner, architecting-solutions | High | Add visual spec requirements |
| React/state pattern | debugger, refactoring-specialist | Medium | Add to patterns |
| Test strategy improvement | test-automator, qa-expert | Medium | Update approach |
| CI/deploy fix | deployment-engineer | Medium | Add to troubleshooting |
Multi-Memory Architecture
1. Semantic Memory (memory/semantic-patterns.json)
Stores abstract patterns and rules reusable across contexts:
{
"patterns": {
"pattern_id": {
"id": "pat-2025-01-11-001",
"name": "Pattern Name",
"source": "user_feedback|implementation_review|retrospective",
"confidence": 0.95,
"applications": 5,
"created": "2025-01-11",
"category": "prd_structure|react_patterns|async_patterns|...",
"pattern": "One-line summary",
"problem": "What problem does this solve?",
"solution": { ... },
"quality_rules": [ ... ],
"target_skills": [ ... ]
}
}
}2. Episodic Memory (memory/episodic/)
Stores specific experiences and what happened:
memory/episodic/
├── 2025/
│ ├── 2025-01-11-prd-creation.json
│ ├── 2025-01-11-debug-session.json
│ └── 2025-01-12-refactoring.json{
"id": "ep-2025-01-11-001",
"timestamp": "2025-01-11T10:30:00Z",
"skill": "debugger",
"situation": "User reported data not refreshing after form submission",
"root_cause": "Empty callback in onRefresh prop",
"solution": "Implement actual refresh logic in callback",
"lesson": "Always verify callbacks are not empty functions",
"related_pattern": "callback_verification",
"user_feedback": {
"rating": 8,
"comments": "This was exactly the issue"
}
}3. Working Memory (memory/working/)
Stores current session context:
memory/working/
├── current_session.json # Active session data
├── last_error.json # Error context for self-correction
└── session_end.json # Session end markerSelf-Improvement Process
Phase 1: Experience Extraction
After any skill completes, extract:
What happened:
skill_used: {which skill}
task: {what was being done}
outcome: {success|partial|failure}
Key Insights:
what_went_well: [what worked]
what_went_wrong: [what didn't work]
root_cause: {underlying issue if applicable}
User Feedback:
rating: {1-10 if provided}
comments: {specific feedback}Phase 2: Pattern Abstraction
Convert experiences to reusable patterns:
| Concrete Experience | Abstract Pattern | Target Skill |
| "User forgot to save PRD notes" | "Always persist thinking to files" | prd-planner |
| "Code review missed SQL injection" | "Add security checklist item" | code-reviewer |
| "Callback was empty, didn't work" | "Verify callback implementations" | debugger |
| "Net APY position ambiguous" | "UI specs need exact relative positions" | prd-planner |
Abstraction Rules:
If experience_repeats 3+ times:
pattern_level: critical
action: Add to skill's "Critical Mistakes" section
If solution_was_effective:
pattern_level: best_practice
action: Add to skill's "Best Practices" section
If user_rating >= 7:
pattern_level: strength
action: Reinforce this approach
If user_rating <= 4:
pattern_level: weakness
action: Add to "What to Avoid" sectionPhase 3: Skill Updates
Update the appropriate skill files with evolution markers:
<!-- Evolution: 2025-01-12 | source: ep-2025-01-12-001 | skill: debugger -->
## Pattern Added (2025-01-12)
**Pattern**: Always verify callbacks are not empty functions
**Source**: Episode ep-2025-01-12-001
**Confidence**: 0.95
### Updated Checklist
- [ ] Verify all callbacks have implementations
- [ ] Test callback execution pathsCorrection Markers (when fixing wrong guidance):
<!-- Correction: 2025-01-12 | was: "Use callback chain" | reason: caused stale refresh -->
## Corrected Guidance
Use direct state monitoring instead of callback chains:
```typescript
// ✅ Do: Direct state monitoring
const prevPendingCount = usePrevious(pendingCount);
### Phase 4: Memory Consolidation
1. **Update semantic memory** (`memory/semantic-patterns.json`)
2. **Store episodic memory** (`memory/episodic/YYYY-MM-DD-{skill}.json`)
3. **Update pattern confidence** based on applications/feedback
4. **Prune outdated patterns** (low confidence, no recent applications)
## Self-Correction (on_error hook)
Triggered when:
- Bash command returns non-zero exit code
- Tests fail after following skill guidance
- User reports the guidance produced incorrect results
**Process:**
```markdown
## Self-Correction Workflow
1. Detect Error
- Capture error context from working/last_error.json
- Identify which skill guidance was followed
2. Verify Root Cause
- Was the skill guidance incorrect?
- Was the guidance misinterpreted?
- Was the guidance incomplete?
3. Apply Correction
- Update skill file with corrected guidance
- Add correction marker with reason
- Update related patterns in semantic memory
4. Validate Fix
- Test the corrected guidance
- Ask user to verifyExample:
<!-- Correction: 2025-01-12 | was: "useMemo for claimable ids" | reason: stale data at click time -->
## Self-Correction: Click-Time Computation
**Issue**: Using useMemo for claimable IDs caused stale data
**Fix**: Compute at click time for always-fresh data
**Pattern**: click_time_vs_open_time_computationSelf-Validation
Use the validation template in references/appendix.md when reviewing updates.
Hooks Integration
Wiring Hooks in Claude Code Settings
Add to Claude Code settings (~/.claude/settings.json):
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash|Write|Edit",
"hooks": [
{
"type": "command",
"command": "bash ${SKILLS_DIR}/self-improving-agent/hooks/pre-tool.sh \"$TOOL_NAME\" \"$TOOL_INPUT\""
}
]
}
],
"PostToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "bash ${SKILLS_DIR}/self-improving-agent/hooks/post-bash.sh \"$TOOL_OUTPUT\" \"$EXIT_CODE\""
}
]
}
],
"Stop": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "bash ${SKILLS_DIR}/self-improving-agent/hooks/session-end.sh"
}
]
}
]
}
}Replace ${SKILLS_DIR} with your actual skills path.
Additional References
See references/appendix.md for memory structure, workflow diagrams, metrics, feedback templates, and research links.
Best Practices
DO
- ✅ Learn from EVERY skill interaction
- ✅ Extract patterns at the right abstraction level
- ✅ Update multiple related skills
- ✅ Track confidence and apply counts
- ✅ Ask for user feedback on improvements
- ✅ Use evolution/correction markers for traceability
- ✅ Validate guidance before applying broadly
DON'T
- ❌ Over-generalize from single experiences
- ❌ Update skills without confidence tracking
- ❌ Ignore negative feedback
- ❌ Make changes that break existing functionality
- ❌ Create contradictory patterns
- ❌ Update skills without understanding context
Quick Start
After any skill completes, this agent automatically:
- Analyzes what happened
- Extracts patterns and insights
- Updates relevant skill files
- Logs to memory for future reference
- Reports summary to user
References
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

