Self Improving Agent 1.0.2

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User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task.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.

Security Scan

The skill's purpose (capture and promote learnings) matches its code and docs, but several instructions encourage globally enabled hooks and automated logging/promotion of project/workspace files without guidance to sanitize sensitive data — this creates a realistic risk of unintended data exposure and unexpected persistence.

Purpose & Capability

Name/description (capture learnings/errors and promote them) align with included files: templates, examples, activator and error-detection hooks, and an extraction helper. The scripts and templates are what you'd expect for a 'self-improving' logging skill.

Instruction Scope

SKILL.md and references instruct agents to log command outputs, environment details, and related file paths and to promote learnings into repo- and workspace-level files (CLAUDE.md, AGENTS.md, TOOLS.md, SOUL.md). There is no guidance or safeguards about redacting secrets or excluding sensitive paths; templates explicitly include an 'Environment details' field and recommend logging command output and metadata, which could capture secrets or private data. The hooks (UserPromptSubmit, PostToolUse) are recommended for project- and user-level configuration, which could make the agent log broadly and repeatedly.

Install Mechanism

No external downloads or package installs; this is instruction-first with small included scripts. Files are local and readable; scripts create scaffolding locally. No network fetches or archive extraction in the provided assets, so install risk is low.

Credentials

The skill declares no required env vars or credentials, but the error-detector script reads CLAUDE_TOOL_OUTPUT (documented as the PostToolUse output). The documentation explicitly instructs logging 'Environment details if relevant' and file paths into persistent project or workspace files. Requesting or capturing environment/output info is reasonable for debugging, but without guidance to avoid secrets (API keys, tokens, private files) this is disproportionate to a safe logging helper and raises data-exfiltration risk.

Persistence & Privilege

always:false and the skill is opt-in, but the docs provide user-level hook examples (e.g., ~/.claude/settings.json and ~/.clawdbot/clawdbot.json) that, if applied, enable the activator/error detector globally for all sessions. Promoting learnings to workspace-level files (~/clawd/...) or to home-level skill caches can cause cross-session, cross-project persistence and potential leakage of project-specific data. The extract-skill helper can create files under a skills directory (and can be pointed at home-level paths), which increases persistence surface if run with global configuration.

What to consider before installing

This skill appears to do what it says (log learnings and provide simple hook scripts), but be careful before enabling it globally. Things to consider before installing/activating: - Review the scripts (activator.sh, error-detector.sh, extract-skill.sh) locally — they are small and readable. Ensure you trust and understand them before making them runnable. - Prefer project-level hook configuration (project root .claude/.codex settings) instead of user-level (~/.claude) to avoid the skill running for every session across all projects. - Do not enable automatic promotion to workspace/global files without controls. Workspace targets like CLAUDE.md, AGENTS.md, or ~/clawd/ are injected into future sessions and can cause accidental data sharing across projects or users. - Add explicit redaction/sanitization rules before logging: never write API keys, tokens, passwords, or other secrets into .learnings/ or promoted files. Update templates or scripts to filter known secret patterns, or require a manual confirmation step before appending entries. - Restrict permissions: keep the skill files writable only by your user and avoid placing them in globally shared locations. If you run extract-skill.sh, check its output (or use --dry-run) before allowing it to write files. - If you want automated error detection, limit PostToolUse hooks to specific commands or matchers (as suggested in hooks-setup) to reduce noise and scope. If you need help auditing or hardening the scripts (e.g., adding secret-detection/redaction), provide the specific deployment path (project-level vs user-level) and I can suggest concrete changes.

Self-Improvement Skill

Log learnings and errors to markdown files for continuous improvement. Coding agents can later process these into fixes, and important learnings get promoted to project memory.

Quick Reference

Situation	Action
Command/operation fails	Log to .learnings/ERRORS.md
User corrects you	Log to .learnings/LEARNINGS.md with category correction
User wants missing feature	Log to .learnings/FEATURE_REQUESTS.md
API/external tool fails	Log to .learnings/ERRORS.md with integration details
Knowledge was outdated	Log to .learnings/LEARNINGS.md with category knowledge_gap
Found better approach	Log to .learnings/LEARNINGS.md with category best_practice
Similar to existing entry	Link with **See Also**, consider priority bump
Broadly applicable learning	Promote to CLAUDE.md, AGENTS.md, and/or .github/copilot-instructions.md
Workflow improvements	Promote to AGENTS.md (clawdbot workspace)
Tool gotchas	Promote to TOOLS.md (clawdbot workspace)
Behavioral patterns	Promote to SOUL.md (clawdbot workspace)

Setup

Create .learnings/ directory in project root if it doesn't exist:

mkdir -p .learnings

Copy templates from assets/ or create files with headers.

Logging Format

Learning Entry

Append to .learnings/LEARNINGS.md:

## [LRN-YYYYMMDD-XXX] category

**Logged**: ISO-8601 timestamp
**Priority**: low | medium | high | critical
**Status**: pending
**Area**: frontend | backend | infra | tests | docs | config

### Summary
One-line description of what was learned

### Details
Full context: what happened, what was wrong, what's correct

### Suggested Action
Specific fix or improvement to make

### Metadata
- Source: conversation | error | user_feedback
- Related Files: path/to/file.ext
- Tags: tag1, tag2
- See Also: LRN-20250110-001 (if related to existing entry)

---

Error Entry

Append to .learnings/ERRORS.md:

## [ERR-YYYYMMDD-XXX] skill_or_command_name

**Logged**: ISO-8601 timestamp
**Priority**: high
**Status**: pending
**Area**: frontend | backend | infra | tests | docs | config

### Summary
Brief description of what failed

### Error

Actual error message or output

### Context
- Command/operation attempted
- Input or parameters used
- Environment details if relevant

### Suggested Fix
If identifiable, what might resolve this

### Metadata
- Reproducible: yes | no | unknown
- Related Files: path/to/file.ext
- See Also: ERR-20250110-001 (if recurring)

---

Feature Request Entry

Append to .learnings/FEATURE_REQUESTS.md:

## [FEAT-YYYYMMDD-XXX] capability_name

**Logged**: ISO-8601 timestamp
**Priority**: medium
**Status**: pending
**Area**: frontend | backend | infra | tests | docs | config

### Requested Capability
What the user wanted to do

### User Context
Why they needed it, what problem they're solving

### Complexity Estimate
simple | medium | complex

### Suggested Implementation
How this could be built, what it might extend

### Metadata
- Frequency: first_time | recurring
- Related Features: existing_feature_name

---

ID Generation

Format: TYPE-YYYYMMDD-XXX

• TYPE: LRN (learning), ERR (error), FEAT (feature)
• YYYYMMDD: Current date
• XXX: Sequential number or random 3 chars (e.g., 001, A7B)

Examples: LRN-20250115-001, ERR-20250115-A3F, FEAT-20250115-002

Resolving Entries

When an issue is fixed, update the entry:

1. Change **Status**: pending → **Status**: resolved
2. Add resolution block after Metadata:

### Resolution
- **Resolved**: 2025-01-16T09:00:00Z
- **Commit/PR**: abc123 or #42
- **Notes**: Brief description of what was done

Other status values:

• in_progress - Actively being worked on
• wont_fix - Decided not to address (add reason in Resolution notes)
• promoted - Elevated to CLAUDE.md, AGENTS.md, or .github/copilot-instructions.md

Promoting to Project Memory

When a learning is broadly applicable (not a one-off fix), promote it to permanent project memory.

When to Promote

• Learning applies across multiple files/features
• Knowledge any contributor (human or AI) should know
• Prevents recurring mistakes
• Documents project-specific conventions

Promotion Targets

Target	What Belongs There
CLAUDE.md	Project facts, conventions, gotchas for all Claude interactions
AGENTS.md	Agent-specific workflows, tool usage patterns, automation rules
.github/copilot-instructions.md	Project context and conventions for GitHub Copilot
SOUL.md	Behavioral guidelines, communication style, principles (clawdbot)
TOOLS.md	Tool capabilities, usage patterns, integration gotchas (clawdbot)

How to Promote

1. Distill the learning into a concise rule or fact
2. Add to appropriate section in target file (create file if needed)
3. Update original entry:
   • Change **Status**: pending → **Status**: promoted
   • Add **Promoted**: CLAUDE.md, AGENTS.md, or .github/copilot-instructions.md

Promotion Examples

Learning (verbose):

Project uses pnpm workspaces. Attempted npm install but failed. Lock file is pnpm-lock.yaml. Must use pnpm install.

In CLAUDE.md (concise):

## Build & Dependencies
- Package manager: pnpm (not npm) - use `pnpm install`

Learning (verbose):

When modifying API endpoints, must regenerate TypeScript client. Forgetting this causes type mismatches at runtime.

In AGENTS.md (actionable):

## After API Changes
1. Regenerate client: `pnpm run generate:api`
2. Check for type errors: `pnpm tsc --noEmit`

Recurring Pattern Detection

If logging something similar to an existing entry:

1. Search first: grep -r "keyword" .learnings/
2. Link entries: Add **See Also**: ERR-20250110-001 in Metadata
3. Bump priority if issue keeps recurring
4. Consider systemic fix: Recurring issues often indicate:
   • Missing documentation (→ promote to CLAUDE.md or .github/copilot-instructions.md)
   • Missing automation (→ add to AGENTS.md)
   • Architectural problem (→ create tech debt ticket)

Periodic Review

Review .learnings/ at natural breakpoints:

When to Review

• Before starting a new major task
• After completing a feature
• When working in an area with past learnings
• Weekly during active development

Quick Status Check

# Count pending items
grep -h "Status\*\*: pending" .learnings/*.md | wc -l

# List pending high-priority items
grep -B5 "Priority\*\*: high" .learnings/*.md | grep "^## \["

# Find learnings for a specific area
grep -l "Area\*\*: backend" .learnings/*.md

Review Actions

• Resolve fixed items
• Promote applicable learnings
• Link related entries
• Escalate recurring issues

Detection Triggers

Automatically log when you notice:

Corrections (→ learning with correction category):

• "No, that's not right..."
• "Actually, it should be..."
• "You're wrong about..."
• "That's outdated..."

Feature Requests (→ feature request):

• "Can you also..."
• "I wish you could..."
• "Is there a way to..."
• "Why can't you..."

Knowledge Gaps (→ learning with knowledge_gap category):

• User provides information you didn't know
• Documentation you referenced is outdated
• API behavior differs from your understanding

Errors (→ error entry):

• Command returns non-zero exit code
• Exception or stack trace
• Unexpected output or behavior
• Timeout or connection failure

Priority Guidelines

Priority	When to Use
critical	Blocks core functionality, data loss risk, security issue
high	Significant impact, affects common workflows, recurring issue
medium	Moderate impact, workaround exists
low	Minor inconvenience, edge case, nice-to-have

Area Tags

Use to filter learnings by codebase region:

Area	Scope
frontend	UI, components, client-side code
backend	API, services, server-side code
infra	CI/CD, deployment, Docker, cloud
tests	Test files, testing utilities, coverage
docs	Documentation, comments, READMEs
config	Configuration files, environment, settings

Best Practices

1. Log immediately - context is freshest right after the issue
2. Be specific - future agents need to understand quickly
3. Include reproduction steps - especially for errors
4. Link related files - makes fixes easier
5. Suggest concrete fixes - not just "investigate"
6. Use consistent categories - enables filtering
7. Promote aggressively - if in doubt, add to CLAUDE.md or .github/copilot-instructions.md
8. Review regularly - stale learnings lose value

Gitignore Options

Keep learnings local (per-developer):

.learnings/

Track learnings in repo (team-wide): Don't add to .gitignore - learnings become shared knowledge.

Hybrid (track templates, ignore entries):

.learnings/*.md
!.learnings/.gitkeep

Hook Integration

Enable automatic reminders through agent hooks. This is opt-in - you must explicitly configure hooks.

Quick Setup (Claude Code / Codex)

Create .claude/settings.json in your project:

{
  "hooks": {
    "UserPromptSubmit": [{
      "matcher": "",
      "hooks": [{
        "type": "command",
        "command": "./skills/self-improvement/scripts/activator.sh"
      }]
    }]
  }
}

This injects a learning evaluation reminder after each prompt (~50-100 tokens overhead).

Full Setup (With Error Detection)

{
  "hooks": {
    "UserPromptSubmit": [{
      "matcher": "",
      "hooks": [{
        "type": "command",
        "command": "./skills/self-improvement/scripts/activator.sh"
      }]
    }],
    "PostToolUse": [{
      "matcher": "Bash",
      "hooks": [{
        "type": "command",
        "command": "./skills/self-improvement/scripts/error-detector.sh"
      }]
    }]
  }
}

Available Hook Scripts

Script	Hook Type	Purpose
scripts/activator.sh	UserPromptSubmit	Reminds to evaluate learnings after tasks
scripts/error-detector.sh	PostToolUse (Bash)	Triggers on command errors

See references/hooks-setup.md for detailed configuration and troubleshooting.

Automatic Skill Extraction

When a learning is valuable enough to become a reusable skill, extract it using the provided helper.

Skill Extraction Criteria

A learning qualifies for skill extraction when ANY of these apply:

Criterion	Description
Recurring	Has See Also links to 2+ similar issues
Verified	Status is resolved with working fix
Non-obvious	Required actual debugging/investigation to discover
Broadly applicable	Not project-specific; useful across codebases
User-flagged	User says "save this as a skill" or similar

Extraction Workflow

1. Identify candidate: Learning meets extraction criteria
2. Run helper (or create manually):

   ./skills/self-improvement/scripts/extract-skill.sh skill-name --dry-run
   ./skills/self-improvement/scripts/extract-skill.sh skill-name
   

3. Customize SKILL.md: Fill in template with learning content
4. Update learning: Set status to promoted_to_skill, add Skill-Path
5. Verify: Read skill in fresh session to ensure it's self-contained

Manual Extraction

If you prefer manual creation:

1. Create skills/<skill-name>/SKILL.md
2. Use template from assets/SKILL-TEMPLATE.md
3. Follow Agent Skills spec:
   • YAML frontmatter with name and description
   • Name must match folder name
   • No README.md inside skill folder

Extraction Detection Triggers

Watch for these signals that a learning should become a skill:

In conversation:

• "Save this as a skill"
• "I keep running into this"
• "This would be useful for other projects"
• "Remember this pattern"

In learning entries:

• Multiple See Also links (recurring issue)
• High priority + resolved status
• Category: best_practice with broad applicability
• User feedback praising the solution

Skill Quality Gates

Before extraction, verify:

• Solution is tested and working
• Description is clear without original context
• Code examples are self-contained
• No project-specific hardcoded values
• Follows skill naming conventions (lowercase, hyphens)

Multi-Agent Support

This skill works across different AI coding agents with agent-specific activation.

Claude Code

Activation: Hooks (UserPromptSubmit, PostToolUse) Setup: .claude/settings.json with hook configuration Detection: Automatic via hook scripts

Codex CLI

Activation: Hooks (same pattern as Claude Code) Setup: .codex/settings.json with hook configuration Detection: Automatic via hook scripts

GitHub Copilot

Activation: Manual (no hook support) Setup: Add to .github/copilot-instructions.md:

## Self-Improvement

After solving non-obvious issues, consider logging to `.learnings/`:
1. Use format from self-improvement skill
2. Link related entries with See Also
3. Promote high-value learnings to skills

Ask in chat: "Should I log this as a learning?"

Detection: Manual review at session end

Clawdbot

Activation: Workspace injection + inter-agent messaging Setup: Configure workspace path in ~/.clawdbot/clawdbot.json Detection: Via session tools and workspace files (AGENTS.md, SOUL.md, TOOLS.md)

Clawdbot uses a workspace-based model with injected prompt files. See references/clawdbot-integration.md for detailed setup.

Agent-Agnostic Guidance

Regardless of agent, apply self-improvement when you:

1. Discover something non-obvious - solution wasn't immediate
2. Correct yourself - initial approach was wrong
3. Learn project conventions - discovered undocumented patterns
4. Hit unexpected errors - especially if diagnosis was difficult
5. Find better approaches - improved on your original solution

Copilot Chat Integration

For Copilot users, add this to your prompts when relevant:

After completing this task, evaluate if any learnings should be logged to .learnings/ using the self-improvement skill format.

Or use quick prompts:

• "Log this to learnings"
• "Create a skill from this solution"
• "Check .learnings/ for related issues"

Clawdbot Integration

Clawdbot uses workspace-based prompt injection with specialized files for different concerns.

Workspace Structure

~/clawd/                    # Default workspace (configurable)
├── AGENTS.md              # Multi-agent workflows, delegation patterns
├── SOUL.md                # Behavioral guidelines, communication style
├── TOOLS.md               # Tool capabilities, MCP integrations
└── sessions/              # Session transcripts (auto-managed)

Clawdbot Promotion Targets

Learning Type	Promote To	Example
Agent coordination	AGENTS.md	"Delegate file searches to explore agent"
Communication style	SOUL.md	"Be concise, avoid disclaimers"
Tool gotchas	TOOLS.md	"MCP server X requires auth refresh"
Project facts	CLAUDE.md	Standard project conventions

Inter-Agent Learning

Clawdbot supports session-based communication:

• sessions_list - See active/recent sessions
• sessions_history - Read transcript from another session
• sessions_send - Send message to another session

Hybrid Setup (Claude Code + Clawdbot)

When using both:

1. Keep .learnings/ for project-specific learnings
2. Use clawdbot workspace files for cross-project patterns
3. Sync high-value learnings to both systems

See references/clawdbot-integration.md for complete setup, promotion formats, and troubleshooting.