Results for “skill-evaluation”

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

Guides users through creating, editing, and optimizing agent skills, including drafting, testing, evaluating, and improving skill performance.

Guides users through creating, refining, and evaluating agent skills, including drafting, testing, and optimizing descriptions for better triggering.

Guides users through creating, editing, and optimizing agent skills, including drafting, testing, evaluating, and improving skill descriptions for better triggering.

Use when auditing Codex skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

Screens resumes with skill matching, experience evaluation, and bias-free candidate ranking

Validate skill outputs against assertion manifests to detect regressions, enforce quality gates, and bootstrap starter manifests from historical runs.

Coordinates quality assurance workflows by routing testing tasks to specialized sub-skills for API testing, performance benchmarking, test analysis, tool evaluation, and process optimization.

Automatically evaluates Claude Code sessions to extract reusable patterns and save them as learned skills.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, 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.

Skill Tester

Skill Tester

Test a pipeline stage's skill file by running the stage WITH and WITHOUT the skill on the same input, comparing outputs, and proposing skill edits. Ryan Law principle 3 — recursive self-improvement. Run after any board complaint about a stage, and monthly per core stage.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, 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.

Analyzes development cycle and quality metrics to identify recurring issues, then generates additive patches to skill instructions to prevent them.

スキル定義（SKILL.md）を静的点検・ドライランで検証するスキル。 `--all` で全スキル一括健全性監査モード（ランキング＋修正案ドラフト生成）。 「スキルを点検して」「スキルをテストして」「スキルのバグ確認」「スキル検証」 「全部のスキルを点検して」「一括点検」または /skill-test を呼び出した時にトリガー。

Use the skill-reviewer skill to run a full 11-category audit of the $ARGUMENTS skill.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, 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.

Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages. Provides multi-dimensional scoring and actionable improvement suggestions.

Validate SKILL.md files against a quality rubric, scoring schema and instruction structure out of 100 and reporting a pass/fail verdict with specific fixes.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, 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.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, 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.

Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Handles source capture, precision passes, authoring, registration, and validation.

Iteratively reviews and fixes Claude Code skill quality issues by running automated fix-review cycles using the skill-reviewer agent until they meet standards.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, 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.

Validates, tests, and scores the quality of skills within a claude-skills ecosystem using Python scripts that check structure, syntax, runtime, and multi-dimensional quality metrics.

Analyze the available skill set and recommend candidate groups that could be consolidated into sub-skill bundles. Read-only — proposes a plan, does not move files.

Audit an existing processkit skill against the 5 Skill Killers, the Agent Skills standard, and Anthropic's troubleshooting playbook, producing a categorized findings report and draft Gotchas.