Agent Skills

SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.

Trust Score Usefulness Recommended Stars Latest

Filters

Verify

orchestkit

Run comprehensive verification: parallel agents for tests, security, coverage, grading and improvement suggestions; produces evidence-backed verification report

verificationtestingsecurity

208

6 triggers

Brain in the Fish — Document Evaluation

brain-in-the-fish

Evaluates documents against criteria using multi-agent, ontology-grounded scoring to produce evidence-backed, auditable evaluation reports.

document-evaluationevidence-verificationmulti-agent

7 triggers

Code Evaluation Harness

My CC Harness

Spawns an independent evaluator agent to score code outputs on functionality, code quality, originality, and usability/security, producing a structured EVAL_REP

evaluationtestingcode-quality

123

6 triggers