SKILLEMALL.ai
GitHub ↗ RU Sign in

CD eval-genius

Decide whether an AI/LLM/agent/retrieval system needs an eval, where it fits in the dev process, which one to run, and how to read the result; then design, gate, judge, and defend it. Not ordinary unit tests.

davila7/claude-code-templates Agent Skills author: davila7 MIT 1 file body ≈ 2 118 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Decide whether an AI/LLM/agent/retrieval system needs an eval, where it fits in the dev process, which one to run, and how to read the result; then design…

As a process D 38/100 · Unfinished process — References files that are not bundled: references/00-start-here.md, references/01-foundation.md, references/02-grading-and-metrics.md

ProcedureAI and agentsSoftware developmentData and analyticstype 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
C
82/100
safety, quality, tests
Safety 60%
100
Quality 40%
56
Run on models
none yet
Process rating
D
38/100
Unfinished process
References files that are not bundled: references/00-start-here.md, references/01-foundation.md, references/02-grading-and-metrics.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. 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 · 0

✓ No critical or high findings

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: references/00-start-here.md
  • warning missing-ref reference to a missing file: references/01-foundation.md
  • warning missing-ref reference to a missing file: references/02-grading-and-metrics.md
  • warning missing-ref reference to a missing file: references/03-judge-calibration.md
  • warning missing-ref reference to a missing file: references/04-search-vs-build.md
  • warning missing-ref reference to a missing file: references/05-dataset-construction.md
  • warning missing-ref reference to a missing file: references/06-harness-design.md
  • warning missing-ref reference to a missing file: references/07-gates-and-ci.md
  • warning missing-ref reference to a missing file: references/08-statistics.md
  • warning missing-ref reference to a missing file: references/09-reporting.md
  • warning missing-ref reference to a missing file: references/10-agentic-evals.md
  • warning missing-ref reference to a missing file: references/11-reading-results.md
  • warning missing-ref reference to a missing file: templates/preregistration.md
  • warning missing-ref reference to a missing file: templates/benchmark-assessment-scorecard.md
  • warning missing-ref reference to a missing file: templates/eval-report.md
  • warning missing-ref reference to a missing file: templates/quality-checklist.md

Process rating: all ten parameters 38/100

Will not run. References files that are not bundled: references/00-start-here.md, references/01-foundation.md, references/02-grading-and-metrics.md
  • 0Tools and files. 16 referenced file(s) missing: references/00-start-here.md, references/01-foundation.md, references/02-grading-and-metrics.md
  • 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. 2 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 100Steps. 29 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2118 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +3Description length 208: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 29 items

Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.