SKILLEMALL.ai
GitHub ↗ RU Sign in

BF skill-reviewer

Reviews skill quality with evidence-based design rubrics and read-only batch inventories. Use for self-review, external skill or repository audits, and authorized auto-PR improvements. Separates design quality from measured task benefit and host compatibility.

daymade/claude-code-skills Agent Skills author: daymade MIT 10 files · 4 scripts body ≈ 2 028 tokens Open the sourcegithub.com↗ analyzed 11 d ago

Reviews skill quality with evidence-based design rubrics and read-only batch inventories.

As a process F 33/100 · No process to follow — References files that are not bundled: ../skill-governance/references/skill-surface-governance.md

AnalyzerSoftware developmentCommercetype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
93/100
safety, quality, tests
Safety 60%
98
Quality 40%
85
Run on models
none yet
Process rating
F
33/100
No process to follow
References files that are not bundled: ../skill-governance/references/skill-surface-governance.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 2

✓ No critical or high findings

Medium and low: 2
  • low Obfuscation obf-base64-blob references/quality_method_sources.md:17
    Long base64-looking blob (documentation of a security skill)
    | [ACES runtime metrics](https://github.com/NVIDIA/SkillEvaluator/blob/a045…6ce/src/skillevaluator/tier3/harbor/metrics.py#L18) | Separate process evidence from answer
    security skill
  • low Obfuscation obf-base64-blob references/quality_rubric.json:79
    Long base64-looking blob (quoted — discussed, not commanded)
    "https://github.com/NVIDIA/SkillEvaluator/blob/a045…6ce/src/skillevaluator/tier3/harbor/metrics.py#L18",
    quoted

Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: ../skill-governance/references/skill-surface-governance.md

Process rating: all ten parameters 33/100

Will not run. References files that are not bundled: ../skill-governance/references/skill-surface-governance.md
  • 0Tools and files. 1 referenced file(s) missing: ../skill-governance/references/skill-surface-governance.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 100Steps. 22 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2028 tokens

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 260: enough signal without eating the budget
  • +4Structure: 19 headings
  • +3Step-by-step instructions: 22 items
  • +4Has examples (12 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)
  • +3All 2 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.