~ / leaderboard / skill / skill-evaluation
Skill · #3789
skill-evaluation
Diagnose skill failures and evaluate whether a proposed method improves task outcomes. Use for behavioral skill assessment, not routine authoring or metadata edits.
5rigs use it
0%of all rigs
5.0kavg rig context tax
Get it
$ npx degit fabricioctelles/skills/skills/skill-evaluation .claude/skills/skill-evaluation From the most-starred rig that ships it: fabricioctelles/skills. Same-named skills in different rigs may differ — review before use.
Often used together with
receiving-code-review · 2subagent-driven-development · 2systematic-debugging · 2test-driven-development · 2using-git-worktrees · 2code-reviewer · 2verification-before-completion · 2technical-writing · 2test-engineer · 2web-research · 2
Rigs using skill-evaluation (5)
fabricioctelles/skills
A collection of skills for AI agents (Kiro, Cursor, Windsurf, Claude Code, and others). Each skill is a reusable module that teaches the agent to perform complex tasks with context, structure, and best practices.
Skill Collector 943 tok · · Q0
gonzalezpazmonica/savia
Sistema agéntico soberano para gobernar y ejecutar trabajo con IA, independiente de modelo, proveedor y frontend, con criterio humano por diseño.
Orchestrator 16.1k tok · · Q73
willfish/nix
Personal Nix flake for NixOS, Home Manager, Hyprland and headless nix-darwin
Skill Collector 2.2k tok · · Q5
voyager67/Agent-Workbench
Turn AI agents into reliable engineering partners. Agent Workbench is a curated skill library for Claude Code, Codex, and beyond—featuring 50+ practical workflows for coding, research, testing, debugging, reviews, and shipping, plus special
Orchestrator 2.7k tok · · Q0
Muratovnik/assay
Evidence-grounded methods for coding agents: skills and agent profiles for Claude Code, Codex, Cursor and Gemini CLI
Skill Collector 3.1k tok · · Q3