agentleFS
zhouguoqingzhouguoqing/QianYuan.AIAgenticFramework/.agents/skills/self-improving-agent/SKILL.md

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

Week of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projectsWeek of Oct 25: 0 new projectsWeek of Nov 1: 0 new projectsWeek of Nov 8: 0 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 0 in all, so this is a hint, not a trend.

Most recently taken up by

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.
  • caicongyangSkill

    tavily-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

  • LaoK2017Skill

    skill-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

  • MicrosoftSkill

    web-search

    Also in 4 projects that use this

  • VercelSkill

    agent-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

  • OpenAISkill

    verification-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

  • OpenAISkill

    writing-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

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
  1. Distinctive:

    After any skill completes, extract:

    line 182
  2. Distinctive:

    Update the appropriate skill files with evolution markers:

    line 233
  3. Very specific:

    Use the validation template in references/appendix.md when reviewing updates.

    line 317
  4. Very specific:

    Add to Claude Code settings (~/.claude/settings.json):

    line 323
  5. Distinctive:

    After any skill completes, this agent automatically:

    line 394

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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:

ResearchKey InsightApplication
SimpleMemEfficient lifelong memoryPattern accumulation system
Multi-Memory SurveySemantic + Episodic memoryWorld knowledge + experiences
Lifelong LearningContinuous task stream learningLearn from every skill use
Evo-MemoryTest-time lifelong learningReal-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)

EventTriggerAction
before_startAny skill startsLog session start
after_completeAny skill completesExtract patterns, update skills
on_errorBash returns non-zero exitCapture 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:

TriggerTarget SkillPriorityAction
New PRD pattern discoveredprd-plannerHighAdd to quality checklist
Architecture tradeoff clarifiedarchitecting-solutionsHighAdd to decision patterns
API design rule learnedapi-designerHighUpdate template
Debugging fix discovereddebuggerHighAdd to anti-patterns
Review checklist gapcode-reviewerHighAdd checklist item
Perf/security insightperformance-engineer, security-auditorHighAdd to patterns
UI/UX spec issueprd-planner, architecting-solutionsHighAdd visual spec requirements
React/state patterndebugger, refactoring-specialistMediumAdd to patterns
Test strategy improvementtest-automator, qa-expertMediumUpdate approach
CI/deploy fixdeployment-engineerMediumAdd 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 marker

Self-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 ExperienceAbstract PatternTarget 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" section

Phase 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 paths

Correction 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 verify

Example:

<!-- 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_computation

Self-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:

  1. Analyzes what happened
  2. Extracts patterns and insights
  3. Updates relevant skill files
  4. Logs to memory for future reference
  5. Reports summary to user

References

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.