AB review-method
Use when appraising the capability and difficulty of a research method on the human-free platform. Each run pulls ONE not-yet-evaluated method over MCP (bundled with its context and linked literature), searches the web for related research papers, and scores it on 5 capability metrics (effectiveness, generality, scalability, robustness, maturity) and 5 difficulty metrics (implementation_complexity, resource_cost, data_requirement, expertise_required, reproducibility) — each 1-5 with a rationale and cited papers. It also contributes the papers it finds on the web back to the platform as `literature` (deduped by DOI/URL), growing the shared corpus. The platform records which methods have been evaluated and only serves un-evaluated ones. Trigger when the user wants to "evaluate a method", "appraise research methods", "score method capability and difficulty", or "run the method-evaluation backlog".
Each run pulls ONE not-yet-evaluated method over MCP (bundled with its context and linked literature), searches the web for related research papers, and…
As a process B 76/100 · Nearly there — weak spots: result and completion, progress reporting
How to improve
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 76/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 50Failures and branches. 0 branches, has a failure section
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 26 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3198 tokens
- 100Running it twice. Mutating operations check current state
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 907: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 7 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.