Agent skill · software engineering · aradotso
skillclaw-skill-evolution
Framework for collective skill evolution in multi-user LLM agent ecosystems — automatically distills session experience into reusable SKILL.md files and shares them across agent clusters.
Why this skill is useful
Adds executable scripts for skill evolution and sharing that fundamentally extend the AI's capabilities in multi-user environments.
What it needs
Requires git, npm installed locally. About 5k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
SkillClaw: Collective Skill Evolution for LLM Agents Skill by ara.so — Daily 2026 Skills collection. SkillClaw is a framework that makes LLM agents progressively smarter by evolving reusable skills from real session data and sharing them across a group of agents. It intercepts OpenAI-compatible API calls via a local proxy, records session artifacts, and runs an evolve server that distills experience into SKILL.md files synced via cloud storage (OSS/S3/local). Architecture Three components share the same storage layer and skill format: 1. Client Proxy — Local API proxy intercepting /v1/chat/completions and /v1/messages, syncing skills 2. Workflow Evolve Server (evolveserver) — Fixed 3-stage pipeline: Summarize → Aggregate → Execute 3. Agent Evolve Server (agentevolveserver) — Autonomous OpenClaw agent that reads sessions and writes evolved skills Installation Client / Local Development Server Deployment Environment Configuration Copy and populate credentials — never hardcode secrets: Config file lives at ~/.skillclaw/config.yaml. Inspect and modify: CLI Reference Client Proxy Setup Skill Management Benchmarking Starting the Evolve Servers Workflow Evolve Server (Summarize → Aggregate → Execute) Agent Evolve Server (Autonomous OpenClaw agent) Use --no-fresh to continue from existing evolved skills rather than starting from scratch each run. Local Filesystem Backend (for development) Key Configuration Options Option Description Default --- --- --- --port Server port 8787 --interval Seconds between evolution cycles 300 --storage-backend oss, s3, or local local --group-id Identifier for your agent cluster required --no-fresh Resume from existing skills flag --oss-endpoint OSS endpoint URL env var --oss-bucket OSS bucket name env var Skill Format (SKILL.md) Skills are Markdown files with YAML frontmatter. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/skillclaw-skill-evolution