How do I install the Self Improvement skill?

Run npx skillmds@latest add heyron-ai/self-improvement in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Self Improvement safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Self Improvement?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Self Improvement free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Self Improvement?

heyron-ai (@heyron-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Self Improvement by heyron-ai — Agent Skill

Name: Self Improvement
Author: heyron-ai

Self Improvement

Log learnings, errors, and feature requests for continuous improvement. Use when: (1) a command fails, (2) user corrects you, (3) user requests something you can't do, (4) you discover outdated knowledge, (5) you find a better approach to a recurring task.

heyron-ai 1fcb47b 4 files · 3.2 KB Updated Sep 17, 2026

File contents

Self-Improvement Skill

Log mistakes, corrections, and discoveries to .learnings/ files so you get smarter over time.

Setup

mkdir -p ~/workspace/.learnings

Quick Reference

Situation	Action
Command fails	Log to `.learnings/ERRORS.md`
User corrects you	Log to `.learnings/LEARNINGS.md`
User wants missing feature	Log to `.learnings/FEATURE_REQUESTS.md`
Found better approach	Log to `.learnings/LEARNINGS.md`
Knowledge was outdated	Log to `.learnings/LEARNINGS.md`

When to Promote

When a learning proves broadly useful, promote it to a permanent file:

Learning Type	Promote To
Behavioral patterns	`SOUL.md`
Workflow improvements	`AGENTS.md`
Tool gotchas	`TOOLS.md`

Logging Format

Learning Entry

Append to .learnings/LEARNINGS.md:

## [LRN-YYYYMMDD-001] category

**Logged**: 2026-03-05
**Priority**: low | medium | high | critical
**Status**: pending

### Summary
One-line description

### Details
What happened, what was wrong, what's correct

### Suggested Action
Specific fix or improvement

Error Entry

Append to .learnings/ERRORS.md:

## [ERR-YYYYMMDD-001] what_failed

**Logged**: 2026-03-05
**Priority**: high
**Status**: pending

### Summary
What failed

### Error

Actual error message


### Context
What you were trying to do

### Suggested Fix
How to prevent this next time

Feature Request Entry

Append to .learnings/FEATURE_REQUESTS.md:

## [FEAT-YYYYMMDD-001] capability_name

**Logged**: 2026-03-05
**Priority**: medium
**Status**: pending

### Requested Capability
What the user wanted

### Suggested Implementation
How this could work

Detection Triggers

Log automatically when you notice:

Corrections: "No, that's wrong...", "Actually...", "You're wrong about..."
Feature requests: "Can you also...", "I wish you could...", "Is there a way to..."
Errors: Non-zero exit codes, exceptions, unexpected output
Knowledge gaps: User provides info you didn't know

Resolving Entries

When fixed, update the entry:

Change **Status**: pending → **Status**: resolved
Add what was done to fix it

Review

Check your learnings periodically:

# Count pending items
grep -c "Status.*pending" ~/workspace/.learnings/*.md

# Find high priority items
grep -B3 "Priority.*high" ~/workspace/.learnings/*.md

Best Practices

Log immediately — context is freshest right after the issue
Be specific — future you needs to understand quickly
Suggest concrete fixes — not just "investigate"
Promote aggressively — if it's broadly useful, put it in SOUL.md/AGENTS.md/TOOLS.md

---name: self-improvementdescription: Log learnings, errors, and feature requests for continuous improvement. Use when: (1) a command fails, (2) user corrects you, (3) user requests something you can't do, (4) you discover outdated knowledge, (5) you find a better approach to a recurring task.---# Self-Improvement SkillLog mistakes, corrections, and discoveries to `.learnings/` files so you get smarter over time.## Setup```bashmkdir -p ~/workspace/.learnings```## Quick Reference| Situation | Action ||-----------|--------|| Command fails | Log to `.learnings/ERRORS.md` || User corrects you | Log to `.learnings/LEARNINGS.md` || User wants missing feature | Log to `.learnings/FEATURE_REQUESTS.md` || Found better approach | Log to `.learnings/LEARNINGS.md` || Knowledge was outdated | Log to `.learnings/LEARNINGS.md` |## When to PromoteWhen a learning proves broadly useful, promote it to a permanent file:| Learning Type | Promote To ||---------------|------------|| Behavioral patterns | `SOUL.md` || Workflow improvements | `AGENTS.md` || Tool gotchas | `TOOLS.md` |## Logging Format### Learning EntryAppend to `.learnings/LEARNINGS.md`:```markdown## [LRN-YYYYMMDD-001] category**Logged**: 2026-03-05**Priority**: low | medium | high | critical**Status**: pending### SummaryOne-line description### DetailsWhat happened, what was wrong, what's correct### Suggested ActionSpecific fix or improvement```### Error EntryAppend to `.learnings/ERRORS.md`:```markdown## [ERR-YYYYMMDD-001] what_failed**Logged**: 2026-03-05**Priority**: high**Status**: pending### SummaryWhat failed### Error```Actual error message```### ContextWhat you were trying to do### Suggested FixHow to prevent this next time```### Feature Request EntryAppend to `.learnings/FEATURE_REQUESTS.md`:```markdown## [FEAT-YYYYMMDD-001] capability_name**Logged**: 2026-03-05**Priority**: medium**Status**: pending### Requested CapabilityWhat the user wanted### Suggested ImplementationHow this could work```## Detection TriggersLog automatically when you notice:- **Corrections**: "No, that's wrong...", "Actually...", "You're wrong about..."- **Feature requests**: "Can you also...", "I wish you could...", "Is there a way to..."- **Errors**: Non-zero exit codes, exceptions, unexpected output- **Knowledge gaps**: User provides info you didn't know## Resolving EntriesWhen fixed, update the entry:- Change `**Status**: pending` → `**Status**: resolved`- Add what was done to fix it## ReviewCheck your learnings periodically:```bash# Count pending itemsgrep -c "Status.*pending" ~/workspace/.learnings/*.md# Find high priority itemsgrep -B3 "Priority.*high" ~/workspace/.learnings/*.md```## Best Practices1. **Log immediately** — context is freshest right after the issue2. **Be specific** — future you needs to understand quickly3. **Suggest concrete fixes** — not just "investigate"4. **Promote aggressively** — if it's broadly useful, put it in SOUL.md/AGENTS.md/TOOLS.md

Frequently asked questions