self-improvement
Mulch Self Improver — Let your agents grow 🌱. Captures learnings with Mulch so expertise compounds across sessions. Use when: command/tool fails, user corrects you, missing feature, API fails, knowledge was wrong, or better approach found. Run mulch prime at session start; mulch record before finishing. Benefits: better and more consistent coding, improved experience, less hallucination.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/austindixson/mulchMulch Self Improver — Let your agents grow 🌱
Structured expertise that accumulates over time, lives in git, and works with any agent. Agents start each session from zero; the pattern discovered yesterday is forgotten today. This skill uses Mulch: agents call mulch record to write learnings and mulch query to read them. Expertise compounds across sessions, domains, and teammates. Mulch is a passive layer — it does not contain an LLM. Agents use Mulch; Mulch does not use agents.
Benefits: Better and more consistent coding · Improved experience · Less hallucination (grounding in project expertise)
When to use: Command/tool fails, user corrects you, user wants a missing feature, your knowledge was wrong, or you found a better approach — record with Mulch and promote proven patterns to project memory. Auto-detection: The hook now detects errors and corrections automatically and prompts to record.
Mechanics: One learning store — .mulch/ (append-only JSONL, git-tracked, queryable). Session start: mulch prime. Recording: mulch record <domain> --type <type> .... No .learnings/ markdown files.
Qualification (features, benefits, pain points): See QUALIFICATION.md. Benchmark (token efficiency, troubleshooting skill improvement): See BENCHMARK.md — e.g. ~54% fewer chars to get same resolutions; find rate same or better; less context → fewer tokens, less noise, lower risk of wrong fix.
New Features (v1.1)
Auto-Detection
The hook now automatically detects learning moments:
- Errors/failures — When commands fail or return errors
- Corrections — When you say "no", "actually", "wrong", etc.
- Retries — When you ask to try again
The agent will prompt: "Want me to record this for next time?"
Pre-loaded Domains
24 preset domains included in config/domains.json:
api, database, testing, frontend, backend, infra, docs, config,
security, performance, deployment, auth, errors, debugging,
workflow, customer, system, marketing, sales, content,
competitors, crypto, automation, openclaw
Notifications
When a learning is recorded, you're notified via Telegram.
Quick Reference
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-austindixson-mulch": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
what-just-happened
When the gateway comes back online, check recent logs and post a short message about what happened (restart, SIGUSR1, auth change, reconnect). User sees the response in TUI or Telegram.
agent-loops
Multi-agent workflow orchestrator. Use when the user asks to build, create, make, ship, develop, or launch any software (apps, webapps, websites, mobile apps, APIs, tools, bots, dashboards, SaaS, MVPs); fix or debug bugs; review or audit code; research topics; refactor code; or publish skills.
composio-composer-xskill
Enables posting tweets to Twitter/X through Composio's integration platform via HTTP and BeautifulSoup. Use when posting tweets or integrating with Composio.
creative-agents
Integration scripts for the creative agent swarm managed by overstory (Claude Code). Use when configuring or running researcher, social media, blog, or scribe agents.
skill-doc-formatter
Formats SKILL.md (OpenClaw/Cursor skill docs) for optimal display on ClawHub. Produces a consistent structure—Description, Installation, Usage with benefit-focused examples, and Commands—so skill pages are clear and scannable.