Last commit on September 2, 2026·Created on May 22, 2026
openclaw/agent-skills
“A suite of utilities for validating behavior and securing agent transcripts in development workflows”
Combined rank
#274
across all skills
Stars
1.1k
7d change unavailable
Forks
97
Watchers
3
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of real attention, adoption, and active maintenance.
TL;DR
This collection provides specialized tools for managing the intersection of AI agents and software engineering. It enables developers to redact and publish session transcripts, perform structured code reviews across multiple LLM providers, and validate user behavior against prewritten contracts for APIs and CLIs.
The toolkit emphasizes safety and isolation, offering capabilities for source-blind validation and remote proofing within untrusted environments across multiple operating systems.
WHO IT'S FOR
AI agent / automation builders
implementing structured handoffs and session sharing
QA / test automation engineers
validating user behavior against prewritten contracts
Platform / DevEx teams
standardizing READMEs and session redaction workflows
Backend / infrastructure engineers
managing remote proof and untrusted isolation
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Want to install it?
Clone to Claude · Clone to Codex · Manual Copy · Symlink to AgentRepository instructions