Captures learnings, errors, and corrections to enable continuous improvement across sessions.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionself-improving-agentExecute the skills CLI command in your project's root directory to begin installation:
Fetches self-improving-agent from kimasplund/clawdbot-skills-pack and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate self-improving-agent. Access via /self-improving-agent in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
1
total installs
1
this week
0
upvotes
Run in your terminal
1
installs
1
this week
—
stars
Captures learnings, errors, and corrections to enable continuous improvement across sessions.
This skill automatically activates when:
| Trigger | What Gets Logged | Location |
|---|---|---|
| Command fails | Error type, context, recovery suggestion | logs/failures_detailed.jsonl |
| User corrects | "No, that's wrong...", "Actually..." | logs/corrections.jsonl |
| Missing capability | "Can you X?" where X isn't available | logs/missing_capabilities.jsonl |
| API/tool fails | Failure pattern, suggested fix | logs/failures_detailed.jsonl |
| Better approach found | Optimization learned | logs/learnings.jsonl |
PostToolUse → enhanced-failure-logger.js → logs failures with context
UserMessage → correction-detector.js → detects "wrong/actually/try again"
Response → capability-tracker.js → detects unfulfilled requests
All learnings flow to logs/learnings.jsonl:
{
"timestamp": "2026-01-26T12:00:00Z",
"type": "user_correction|tool_failure|missing_capability",
"category": "factual_error|command_failed|web_browsing",
"description": "what was learned",
"source": "which detector"
}
On each session start, recent learnings are shown:
=== Learning Review ===
[Learnings] 47 total entries
[Recent]
• [tool_failure] Bash failed: timeout - WebFetch to external API...
• [user_correction] User corrected: "No, use the other file..."
[Corrections] 12 user corrections logged
[Capability Gaps] Top requested:
• send emails (5x)
• browse web (3x)
Successful learnings boost Q-values for related memories, improving future retrieval.
# Show all learnings
cat ~/.claude/logs/learnings.jsonl | tail -20
# Show corrections only
cat ~/.claude/logs/corrections.jsonl | jq -s 'group_by(.correction_type) | map({type: .[0].correction_type, count: length})'
# Show capability gaps report
node ~/.claude/scripts/hooks/capability-tracker.js --report
# Test correction detector
node ~/.claude/scripts/hooks/correction-detector.js
# Test failure logger
node ~/.claude/scripts/hooks/enhanced-failure-logger.js
# Test capability tracker
node ~/.claude/scripts/hooks/capability-tracker.js
factual_error - Wrong information providedretry_request - User asked to try againmisunderstanding - Misinterpreted the requestfailed_solution - Solution didn't workpermission_error - Access deniednot_found - File/resource missingtimeout - Operation timed outnetwork_error - Connection issuessyntax_error - Invalid syntaxapi_error - External API failedcommand_failed - Shell command failedagent_failed - Subagent failedweb_browsing - Internet access requestsimage_processing - Image/photo handlingcommunication - Email/messagingdatabase_access - SQL/database queriesexternal_api - Third-party servicesmemory_persistence - Long-term memoryIn settings.json, these hooks enable self-improvement:
{
"hooks": {
"SessionStart": [...], // Reviews learnings
"PostToolUse": [
{"matcher": "Bash", "hooks": [{"command": "enhanced-failure-logger.js"}]},
{"matcher": "Task", "hooks": [{"command": "enhanced-failure-logger.js"}]}
]
}
}
| Skill | Integration |
|---|---|
| QAVR | Successful learnings boost memory Q-values |
| Memory Consolidation | Periodic cleanup of old learnings |
| Confidence Check | Review learnings before major tasks |
| IR-v2 | Use learnings to inform pattern selection |
~/.claude/
├── logs/
│ ├── learnings.jsonl # All learnings
│ ├── corrections.jsonl # User corrections
│ ├── failures_detailed.jsonl # Enhanced failure logs
│ ├── missing_capabilities.jsonl # Capability requests
│ └── capability_gaps.json # Aggregated gaps
└── scripts/hooks/
├── correction-detector.js
├── enhanced-failure-logger.js
├── capability-tracker.js
└── session-start.js (reviews learnings)
Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
mattpocock/skills
self-improving-agent is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
I recommend self-improving-agent for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
self-improving-agent fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
self-improving-agent fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
I recommend self-improving-agent for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Useful defaults in self-improving-agent — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
self-improving-agent fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
I recommend self-improving-agent for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Solid pick for teams standardizing on skills: self-improving-agent is focused, and the summary matches what you get after install.
Solid pick for teams standardizing on skills: self-improving-agent is focused, and the summary matches what you get after install.
showing 1-10 of 60