Loading...
Loading...
Found 20 Skills
Run isolated eval and grading calls using CC 2.1.81 --bare mode. Constructs claude -p --bare invocations for skill evaluation, trigger testing, and LLM grading without plugin/hook interference. Use when running eval pipelines, grading skill outputs, benchmarking prompt quality, or testing trigger accuracy in isolation.
Create and improve agent skills following the Agent Skills specification. Use when asked to create, write, or update skills.
Designs and writes high-quality Agent Skills (SKILL.md + optional reference files/scripts). Use when asked to create a new Skill, rewrite an existing Skill, improve Skill structure/metadata, or generate templates/evaluations for Skills.
Evaluate and improve skills through measured testing. Run trigger evaluations to test whether skill descriptions cause correct activation, optimize descriptions via automated train/test loops, benchmark skill output quality with A/B comparisons, and validate skill structure. Use when user says "improve skill", "test skill triggers", "optimize description", "benchmark skill", "eval skill", or "skill quality". Do NOT use for creating new skills (use skill-creator-engineer).
Find and evaluate Claude skills for specific use cases using semantic search, Anthropic best practices assessment, and fitness scoring. Use when the user asks to find skills for a particular task (e.g., "find me a skill for pitch decks"), not for generic "show all skills" requests.
Analyzes and compares existing skills from any source (skills.sh, GitHub, Claude marketplace, or local files) against a target skill or requirement. Fetches skill content, evaluates it across 10 dimensions, produces a structured comparison table, identifies gaps, and recommends whether to adopt, adapt, or build from scratch. Trigger when: analyze this skill, compare skills, is this skill good enough, what does this skill do, skill evaluation, should I use this skill, skill gap analysis, paste a skills.sh URL, GitHub skill URL, or upload a SKILL.md file for review.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch for Claude Code or Cursor, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
This skill should be used when the user wants to run baseline evaluations on existing agent skills, regenerate transcripts after a model upgrade, or check whether a skill still solves the gap it was authored for. Common triggers include "rerun the baselines", "re-eval skill X", "test all the skills", "check for skill drift", and "run the evals". Bakes in verbatim transcript capture (no paraphrasing), deterministic-only grading (regex / contains / file_exists — no LLM-as-judge), and the iteration-N workspace convention. Skip when authoring a new skill (use skill-creator) or modifying skill content directly.