Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· AI
Mulch
Mulch Self Improver β Let your agents grow π±. Captures learnings with Mulch so expertise compounds across sessions. Use when: command/tool fails, user corre...
skill openclawclawhub Free
Mulch Self Improver β Let your agents grow π±. Captures learnings with Mulch so expertise compounds across sessions. Use when: command/tool fails, user corre...
β¬ 0 downloads β
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- BENCHMARK.md, QUALIFICATION.md, README.md, SKILL.md, _meta.json, assets/LEARNINGS.md
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.0.5
Provenance
- Publisher
- RuneweaverStudios
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Mulch Self Improver β Let your agents grow π±
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 β it does not contain an LLM. Agents use Mulch; Mulch does not use agents. Benefits: Better and more consistent coding Β· Improved experience Β· 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 β 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 β .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 β e.g. ~54% fewer chars to get same resolutions; find rate same or better; less context β fewer tokens, less noise, lower risk of wrong fix.
Auto-Detection
The hook now automatically detects learning moments: Errors/failures β When commands fail or return errors Corrections β When you say "no", "actually", "wrong", etc. Retries β 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
SituationActionCommand/operation or API failsmulch record <domain> --type failure --description "..." --resolution "..."User corrects you / knowledge was wrongmulch record <domain> --type convention "..." or --type pattern --name "..." --description "..."Found better approach, best practicemulch record <domain> --type convention "..." or --type guide --name "..." --description "..."Architectural or tech decisionmulch record <domain> --type decision --title "..." --rationale "..."Feature request (tracking)mulch record <domain> --type decision --title "..." --rationale "..."Key file/endpoint to remembermulch record <domain> --type reference --name "..." --description "..."Similar to existing recordUse --relates-to <domain>:<id> or --supersedes; run mulch search "..." firstBroadly applicable patternPromote to CLAUDE.md, AGENTS.md, SOUL.md, TOOLS.md; use mulch onboard for snippetsSession start (project has .mulch/)Run mulch prime to load expertise into context
Mulch Setup
Install (optional; npx works without install): npm install -g mulch-cli # or: npx mulch-cli <command> Initialize in project: mulch init # Quick: add all preset domains at once cat config/domains.json | jq -r '.domains[].name' | xargs -I {} mulch add {} # Or add individually: mulch add api mulch add database mulch add testing # add domains that match your areas: frontend, backend, infra, docs, config Provider hooks (remind agent to record): mulch setup cursor # or: claude, codex, gemini, windsurf, aider Onboarding snippet for AGENTS.md/CLAUDE.md: mulch onboard
Record Types (Mulch)
TypeRequiredUse Casefailuredescription, resolutionWhat went wrong and how to avoid itconventioncontent"Use pnpm not npm"; "Always WAL mode for SQLite"patternname, descriptionNamed patterns, optional --filedecisiontitle, rationaleArchitecture, tech choices, feature trackingreferencename, descriptionKey files, endpoints, resourcesguidename, descriptionStep-by-step procedures Optional on any record: --classification (foundational | tactical | observational), --tags, --relates-to, --supersedes, --evidence-commit, --evidence-file, --outcome-status (success | failure).
Workflow
Session start: If .mulch/ exists, run mulch prime (or mulch prime <domain> for focus). During work: When something fails or you learn something, run mulch record <domain> --type <type> .... Before finishing: Review; record any remaining insights with mulch record. Promote: When a pattern is proven and broadly applicable, add to CLAUDE.md / AGENTS.md / SOUL.md / TOOLS.md; use mulch onboard to generate snippets.
Finding Domain
Use existing domains from mulch status or mulch query --all. Run mulch learn to get domain suggestions from changed files. Common domains: api, database, testing, frontend, backend, infra, docs, config.
Recurring Patterns and Linking
Search first: mulch search "keyword" or mulch query <domain>. Link records: mulch record ... --relates-to <domain>:<id> or --supersedes <domain>:<id>. Recurring issues β promote to CLAUDE.md/AGENTS.md or add to TOOLS.md/SOUL.md so all agents see them.
Simplify & Harden Feed
For candidates from the simplify-and-harden skill: Use pattern_key as a stable tag: mulch record <domain> --type pattern --name "<pattern_key>" --description "..." --tags "simplify-and-harden". Search first: mulch search "<pattern_key>"; if found, use --relates-to or add to existing via mulch edit if needed. When recurrence is high, promote to CLAUDE.md/AGENTS.md/SOUL.md/TOOLS.md as short prevention rules.
Periodic Review
When: Before major tasks, after features, weekly. Commands: mulch status, mulch ready --since 7d, mulch query --all. Actions: Promote high-value records to project memory; run mulch prune for stale tactical/observational entries if desired; mulch doctor --fix for health.
Promotion Targets
Learning TypePromote ToBehavioral patternsSOUL.md (OpenClaw workspace)Workflow improvementsAGENTS.mdTool gotchasTOOLS.md (OpenClaw workspace)Project facts, conventionsCLAUDE.mdCopilot context.github/copilot-instructions.md Use mulch onboard to generate AGENTS.md/CLAUDE.md snippets.
Detection Triggers
Record when you notice: User corrects you ("No, that's not right...", "Actually...") β convention or pattern Command/API/tool fails β failure (description + resolution) User wants missing capability β decision (title + rationale) Your knowledge was wrong or outdated β convention You found a better approach β convention or guide
OpenClaw Setup
OpenClaw injects workspace files; use Mulch for learnings.
Installation
clawdhub install self-improving-agent # or: git clone ... ~/.openclaw/skills/self-improving-agent
Workspace and Mulch
Session start: Run mulch prime when the project (or workspace) has .mulch/. Optionally add mulch prime output to workspace context if your setup supports it. Recording: Use mulch record from the project or workspace directory that contains .mulch/. Promotion: SOUL.md, AGENTS.md, TOOLS.md live in ~/.openclaw/workspace/; add promoted rules there.
Enable Hook (reminder at bootstrap)
cp -r hooks/openclaw ~/.openclaw/hooks/self-improvement openclaw hooks enable self-improvement See references/openclaw-integration.md.
Generic Setup (Other Agents)
In project: mulch init and mulch add <domain> as needed. Use mulch setup <provider> (cursor, claude, codex, etc.) for hooks. Add to CLAUDE.md/AGENTS.md: "Run mulch prime at session start. Record learnings with mulch record <domain> --type failure|convention|decision|pattern|guide|reference." Run mulch onboard and paste the snippet into your agent docs.
Multi-Agent Safety
Mulch is safe for concurrent use: advisory file locking, atomic writes, and merge=union in .gitattributes for JSONL. Multiple agents can run mulch prime and mulch record in parallel; locks serialize writes per domain.
Skill Extraction
When a Mulch record is valuable as a reusable skill: Get content from mulch query <domain> or mulch search "...". Create skills/<skill-name>/SKILL.md (template in assets/SKILL-TEMPLATE.md). Optionally note in the record (e.g. via mulch edit) that it was promoted to a skill.
Best Practices
Record immediately β context is freshest after the issue. Pick the right type β failure (description+resolution), convention (short rule), decision (title+rationale), etc. Use domains consistently β e.g. same api domain for all API-related learnings. Link related records β --relates-to, --supersedes. Run mulch prime at session start β so the agent is grounded in existing expertise. Promote when proven β move broadly applicable rules to CLAUDE.md, AGENTS.md, SOUL.md, TOOLS.md.
No .learnings/
This skill does not use .learnings/ or markdown log files. All learnings live in .mulch/ and are recorded via the Mulch CLI. If you see references to .learnings/ in older docs, treat them as superseded by Mulch.
Category context
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
5 Docs1 Config
- SKILL.md
- assets/LEARNINGS.md
- BENCHMARK.md
- QUALIFICATION.md
- README.md
- _meta.json