improve-skill-quality
Diagnoses and fixes skills in the dotnet/skills repository that lose to their own baseline, fail to activate, time out, or return "no credible improvement". Use when an evaluation verdict is a regression or underpowered, when a skill regressed after a change, when /evaluate reports no results, or when deciding whether a weak skill should be strengthened or retired. Do not use for scaffolding a brand-new skill (use create-skill) or a brand-new eval (use create-skill-test).
npx skills add dotnet/skills --skill improve-skill-quality --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Improve Skill Quality Turn a failing or unconvincing evaluation into a targeted fix. The single most common mistake in this repo is rewriting skill prose in response to a verdict whose real cause was the eval, the fixtures, or the harness. Classify first, then fix. ## When to Use - An evaluation verdict is a regression, underpowered, or "no credible improvement". - A skill wins in the isolated arm but not in the plugin arm, or is reported "not activated". - `/evaluate` reports "Evaluation ran but produced no results". - A skill scores well but costs too much (tokens, turns, wall time, plugin menu budget). - Deciding whether to strengthen or retire a persistently weak skill. ## When Not to Use - Creating a new skill from scratch — use `create-skill`. - Creating a new `eval.yaml` from scratch — use `create-skill-test`. - Changing the harness itself (`eng/skill-validator`, `eng/vally-adapter`, `evaluation*.yml`). ## Inputs | Input | Required | Description | |-------|----------|-------------| | Verdict evidence | Yes | The `/evaluate` PR comment, or `results.json` from the run artifacts | | Losing trial transcripts | Yes for content fixes | Baseline vs. skilled output plus the judge'
- When to Use
- When Not to Use
- Inputs
- Workflow
- Step 1: Get the evidence before forming a hypothesis
- Step 2: Classify the failure
- Step 3: Rule out harness and reliability causes
- Step 4: Verify the fixtures before touching the skill
- Step 5: Check whether the eval could ever have passed
- Step 6: Check whether the two arms differ at all
- Step 7: Fix skill content against the losing trial
- Step 8: Fix activation
- Step 9: Re-validate
- Validation
dotnet run --project eng/skill-validator/src/SkillValidator.csproj -- check --plugin ./plugins/<plugin> python eng/eval-quality/check_eval_quality.py
What does the improve-skill-quality skill do?
Diagnoses and fixes skills in the dotnet/skills repository that lose to their own baseline, fail to activate, time out, or return "no credible improvement". Use when an evaluation verdict is a regression or underpowered, when a skill regressed after a change, when /evaluate reports no results, or when deciding whether a weak skill should be strengthened or retired. Do not use for scaffolding a brand-new skill (use create-skill) or a brand-new eval (use create-skill-test).
How do I install it?
Run `npx skills add dotnet/skills --skill improve-skill-quality --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From dotnet/skills, a repository with 4,927 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.