Works
40% of the score90/100
- References 1 file that is not in the repo: artifacts/traces/trace_1.json.
Does it parse, does it declare a name and a description, does it reference files that are actually there. A failure here is what sets the will-not-load verdict.
Maintained
25% of the score92/100
- no commits in the last 12 weeks
Days since the last commit on the repository that publishes it, on a steep curve, and whether that repository has been archived.
Adopted
20% of the score86/100
- 195,495 installs on skills.sh.
- 5,920 stars on the source repo.
Install counts from the skills.sh registry where they exist; repository stars and 30-day star velocity where they do not.
Documented
15% of the score90/100
- 3,057 words with worked examples.
- Ships 6 bundled files.
Length of the instructions, worked examples, bundled scripts and references, which is how much a model actually has to go on.
What the check found
1 findingIt points at files that are not in the repository, so those steps will fail.
Files it references that are not in the repository
- artifacts/traces/trace_1.json
What it says it does
from its own frontmatterThis skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Agent Platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
100/100
- Loads cleanly: valid frontmatter, required fields present, no dangling references.
92/100
- no commits in the last 12 weeks
86/100
- 195,884 installs on skills.sh.
- 5,920 stars on the source repo.
75/100
- 424 words with worked examples.
- Ships 3 bundled files.
100 × 0.40 = 40.0+ 92 × 0.25 = 23.0+ 86 × 0.20 = 17.2+ 75 × 0.15 = 11.25= 91.45, which rounds to
Loads. Every structural check Claude Code needs to register this passed.
90/100
- References 1 file that is not in the repo: references/samples.md.
92/100
- no commits in the last 12 weeks
86/100
- 195,533 installs on skills.sh.
- 5,920 stars on the source repo.
90/100
- 2,968 words with worked examples.
- Ships 6 bundled files.
90 × 0.40 = 36.0+ 92 × 0.25 = 23.0+ 86 × 0.20 = 17.2+ 90 × 0.15 = 13.5= 89.7, which rounds to
Loads. Every structural check Claude Code needs to register this passed.
Files it references that are not in the repository: references/samples.md