SKILLEMALL.ai
GitHub ↗ RU Sign in

AB design-ai-benchmarking

Design and validity review for studies that benchmark one or more AI systems against a human-expert panel as the reference. Covers the evaluation question and arm definition, decoupled multi-dimensional rubrics with anchors, planted calibration probes, reviewer-panel construction, inter-rater reliability targets, LLM-as-judge versus human-as-judge adjudication, construct-independence guards, and a structured rating-export schema. Use before data collection on an AI-vs-expert evaluation.

Aperivue/medsci-skills Agent Skills author: Aperivue MIT 5 files body ≈ 2 811 tokens Open the sourcegithub.com↗ analyzed 27 h ago

Design and validity review for studies that benchmark one or more AI systems against a human-expert panel as the reference.

As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, running it twice

AnalyzerAI and agentstype 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
A
96/100
safety, quality, tests
Safety 60%
100
Quality 40%
89
Run on models
none yet
Process rating
B
65/100
Nearly there
Inputs and preconditions w 11
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    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: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "triggers"
    • note frontmatter-key unknown frontmatter key "tools"

    Process rating: all ten parameters 65/100

    • 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
    • 30Running it twice. 1 mutating operations with no state check
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 48 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2811 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)
    • +1No license
    • +2Single-language instructions
    • +3Description length 491: enough signal without eating the budget
    • +4Structure: 18 headings
    • +3Step-by-step instructions: 48 items
    • +3Output format is stated explicitly
    • +4Has examples (1 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.