agent-skills
Shared AI agent skills for code review, validation, and session sharing
All Skills in This Repository (6)
Pure Emerald Level Indicators
openclawagent-transcript
Generate sanitized transcripts from local agent logs for GitHub PR/issue bodies.
openclawhandoff
Generates handoff prompts with task context and instructions for receiving agents.
openclawcrabbox
Automate remote OpenClaw validation on AWS and Blacksmith Testbox platforms.
openclawsession-viewer
Convert JSONL session transcripts from Codex, Claude Code, OpenClaw, or Pi into interactive HTML files.
openclawbehavior-validator
Validate application and API behavior against prewritten contracts without source code access.
openclawreadme-standard
Standardizes README structure, badges, tone, and verification gates for openclaw repositories.
Frequently Asked Questions
FAQPage SchemaHow to install agent-skills?▼
Run `npx skills add openclaw/agent-skills --all -g -y` in your terminal to install all skills in this suite globally.
What does the autoreview skill do?▼
It runs a structured second-model code review on your local changes, branch, or commit, reporting only verified blocking issues by default.
Can AI validate my app without reading the source code?▼
Yes. The behavior-validator skill tests your app, CLI, or API purely through user-visible behavior against a written contract.
Does agent-skills work with Claude Code and Codex?▼
Yes. Every skill follows the standard SKILL.md format and works in Claude Code, Codex, and other compatible agents.
How do I share an AI coding session safely?▼
The beam and agent-transcript skills redact secrets and private data, then publish or attach a sanitized session transcript for reviewers.
Related Repositories in Software Engineering
View All in Software Engineering→
openclawopenclaw
Run a personal AI assistant across your devices and chat apps
obrasuperpowers
Gives coding agents a disciplined workflow from idea to merged code
facebookreact
AI agent skills for building, testing, and porting React core