# self-improving-agent

This skill keeps a markdown log of agent errors, corrections and findings so useful fixes survive between sessions.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 353 installs · ★ 779
- Author: pskoett
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/pskoett/self-improving-agent/tree/HEAD/self-improving-agent/SKILL.md
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/skills/pskoett-self-improving-agent

## What it does

Everything worth keeping goes into three files under `.learnings/`: `LEARNINGS.md` for corrections, knowledge gaps and good practices, `ERRORS.md` for failed commands and integration errors, `FEATURE_REQUESTS.md` for capabilities the user asked for. On first use the directory and files are created; existing ones are never overwritten. Before a big task the agent reads back what it saved and reuses whatever fits.

Entries that turn out to be broadly useful get promoted into workspace files: behavioural patterns into `SOUL.md`, workflow tweaks into `AGENTS.md`, tool gotchas into `TOOLS.md`. Recurring cases carry a `Pattern-Key` so duplicates don't pile up, and a repeat only counts when it's a genuinely new occurrence. Revalidation is tied to what could change — the source, the decision, a dependency, the task — not to how old a note is.

Secrets, tokens and environment variables stay out of the log; short summaries or redacted excerpts are preferred. Automatic reminders and end-of-session error sweeps come from an optional hook, and it only runs where `.learnings/` already exists. This build targets OpenClaw; for other agents the author points to the original multi-agent version in a separate repo.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add pskoett/self-improving-agent --skill self-improving-agent -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/self-improving-agent/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/self-improving-agent/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add pskoett/self-improving-agent --skill self-improving-agent -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/self-improving-agent/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add pskoett/self-improving-agent --skill self-improving-agent -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/self-improving-agent/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install pskoett/self-improving-agent self-improving-agent
```

2. **Manually: put the files in place**
- File: `.github/skills/self-improving-agent/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add pskoett/self-improving-agent --skill self-improving-agent -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/pskoett/self-improving-agent --path self-improving-agent
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/self-improving-agent/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add pskoett/self-improving-agent --skill self-improving-agent -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/pskoett/self-improving-agent/tree/HEAD/self-improving-agent/SKILL.md

## When to use it
- log a failed command so it doesn't bite twice
- save a user correction as a working rule
- record a missing capability and revisit it later
- pull a good approach from an earlier session into the current task
- move a recurring tool gotcha into workspace notes

## Example prompts
- log this failure to `.learnings/ERRORS.md`
- the user corrected my assumption — record it as a correction
- check `.learnings/LEARNINGS.md` before you start the refactor

## Similar
- [self-learning](https://affpapa.org/en/nevibecode/skills/kulaxyz-self-learning.md) — skill · 850 installs
- [blueprint](https://affpapa.org/en/nevibecode/skills/blueprint.md) — skill · 4600 installs
- [planning-with-files](https://affpapa.org/en/nevibecode/skills/zhaono1-planning-with-files.md) — skill · 1200 installs
- [desk-open](https://affpapa.org/en/nevibecode/skills/desk-open.md) — skill · 23 installs
- [self-hosted-funnel-launch](https://affpapa.org/en/nevibecode/skills/self-hosted-funnel-launch.md) — skill · 103000 installs
- [convex-self-heal](https://affpapa.org/en/nevibecode/skills/convex-self-heal.md) — skill · 35800 installs

## Other versions with the same name
- [self-improving-agent · alirezarezvani](https://affpapa.org/en/nevibecode/skills/self-improving-agent.md) — 1078 installs
- [self-improving-agent · zhaono1](https://affpapa.org/en/nevibecode/skills/zhaono1-self-improving-agent.md) — 35100 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md