skill-creator
Create, edit, and optimize Agent Skills, with evals and skill-description triggering optimization.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for skill-creator, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
Anthropic's official meta-skill for authoring and improving skills. Walks the draft-test-evaluate-iterate loop, drafts quantitative evals, runs test prompts, and uses bundled scripts (eval-viewer/generate_review.py and a skill-description improver) to benchmark performance and optimize triggering accuracy. Generates SKILL.md files and runs eval tooling.
Key features and capabilities
- Guided skill drafting and iteration loop
- Eval-viewer benchmark and variance analysis
- Skill-description triggering optimizer script
Use cases
- Create a new Agent Skill from scratch
- Optimize an existing skill's trigger accuracy