Skill Optimizer

Generate eval scenarios from a Tessl plugin (a packaged skill bundle), run baseline + with-context evals, and present results. Use when setting up an evaluation pipeline, running benchmarks, generating test scenarios, measuring skill performance or accuracy, scoring how well a skill helps agents solve tasks, or evaluating skill effectiveness before publishing.

Run task evals, analyze results, diagnose failures, apply targeted fixes, and re-run to verify improvements. Use when debugging evaluation scores, fixing failing or regressed criteria, analyzing why eval criteria pass or fail, reviewing eval rubric quality and redundant criteria, tracking before/after score improvements, editing plugin content to fix specific failing behaviors, or improving agent performance based on eval evidence.

Review and improve your SKILL.md with actionable recommendations. Reads skill bundle, validates syntax and references, explains rubric, shows before/after scores. Use when reviewing skill quality, improving a SKILL.md file, checking scoring dimensions and quick wins, auditing progressive disclosure and orphaned bundle files, generating improvement recommendations, running a post-edit quality audit, creating approval-gated change proposals, or automating the skill review workflow. For the full optimization cycle (review + evals + improve), use `optimize-skill-performance-and-instructions`.

Run task evals across multiple Claude models, compare results side-by-side, and optimise. Use when you want to benchmark a skill across models, compare haiku vs sonnet vs opus performance, run multi-model comparison or benchmark reports, identify model-specific gaps versus universal plugin gaps, evaluate whether a skill works for all model tiers, or validate a skill before publishing it to the registry.

Run the full optimization cycle for a plugin — review best practices, generate eval scenarios, run BOTH activation evals (does the skill self-activate?) and content evals (does the plugin help solve tasks?), diagnose gaps, fix, and re-run until scores improve. Use when someone says "optimize my skill", "improve my plugin", "run evals", "benchmark my plugin", or wants to measure and improve how well a plugin helps agents solve tasks.