evaluate-plugin

Plugin evaluate-plugin from marketplace laurigates-claude-plugins in laurigates/claude-plugins. Commands read from the repo's manifest — today.

Skills (7)

• evaluate-context-engineering

  Context-engineering audit (C1-C6) of skills and always-loaded rules. Use when trimming context bloat, auditing a plugin, or after a new Claude model ships.

• evaluate-improve

  Suggest improvements to SKILL.md content, descriptions, or tool config from eval results. Use when raising pass rates, fixing triggering, or iterating on a skill after evaluation.

• evaluate-legibility

  Cold-read a SKILL.md with a zero-context agent reader to check its intent is legible. Use when validating whether a skill says clearly when to invoke it and how to start.

• evaluate-matrix

  Cross-model skill evals with real execution and grading — the executability gate. Use when checking whether a weak model can actually do a skill, not just comprehend it.

• evaluate-plugin-batch

  Batch evaluate every skill in a plugin and produce a plugin-level report. Use when auditing an entire plugin's quality or validating before a release.

• evaluate-report

  View evaluation results and benchmark reports for a skill or plugin. Use when reviewing past eval results, comparing benchmark runs, or tracking quality trends.

• evaluate-skill

  Evaluate a skill by running test cases and grading results. Use when testing whether a skill produces correct guidance, validating improvements, or benchmarking before release.

Subagents (3)

• eval-analyzer

  Analyze evaluation results to identify patterns, weaknesses, and improvement opportunities. Operates in comparison mode (with-skill vs baseline) or benchmark mode (trends across runs). Use after grading to generate suggestions.

• eval-comparator

  Blind comparison of two outputs without knowing their origin. Rates content quality and structure quality to objectively determine which output is better. Use to compare with-skill vs baseline runs without bias.

• eval-grader

  Grade evaluation runs against predefined assertions. Examines execution transcripts and outputs to determine pass/fail with cited evidence. Use as a subagent from evaluation orchestration skills.

Hooks (2)

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/evaluate-drift-probe.sh"

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/sync-evaluate-skill-workflow.sh"

Similar plugins