~ / leaderboard / skill / skill-eval
Skill · #1847 
skill-eval
Validates a skill by running scenarios in isolated clean-room environments, then reports where the skill's instructions failed to produce expected agent behavior. Use when asked to 'evaluate a skill',
5rigs use it
0%of all rigs
9.7kavg rig context tax
Get it
$ npx degit boshu2/agentops/skills/skill-eval .claude/skills/skill-eval From the most-starred rig that ships it: boshu2/agentops. Same-named skills in different rigs may differ — review before use.
Often used together with
plan · 3review · 3refactor · 2retro · 2incident · 2implement · 2security · 2skill-creator · 1grill-me · 1handoff · 1
Rigs using skill-eval (5)
boshu2/agentops
DevOps discipline for AI coding agents: shape the work, track it as a graph, and get each change judged by a context that didn't write it.
Skill Collector 5.7k tok ·
sunitghub/canon-skills
The agent workflow harness: plans, decisions and acceptance criteria live in your repo, and a second agent grades the work before a sprint closes.
Skill Collector 5.8k tok ·
greglas75/zuvo
Auto-activating, multi-agent skill ecosystem for Claude Code, Codex, and Cursor. 51 skills, 26 agents, quality gates, knowledge store, adversarial review, content writing & optimization.
Skill Collector 8.7k tok ·
lamngockhuong/aiteamkit
Multi-harness AI plugin for Claude Code, Cursor and Codex CLI: skills that run the delivery lifecycle of a project team - intake, estimate, design, spec, breakdown, plan, implement, fix, review, QA, verify, release, incident, retro, onboard
Skill Collector 26.8k tok ·
AbdouMoumen/claude-skills-plugin
Claude Code plugin with personal skills: skill-creator, plugin-creator, forge, mcp-toggle, fresh-start, dotfiles-sync
Skill Collector 1.7k tok ·