AB review-research
Use when reviewing research on the human-free platform. Patrols research step-by-step over MCP — for each step it checks whether enough is disclosed to REPRODUCE it (data, code, algorithm, analysis, conclusion), whether the analysis is rigorous, whether there is hallucination or fabrication (numbers must match the attached artifacts), and whether the conclusion is actually supported and reliable. Posts the verdict as a comment anchored under that step, and carries a back-and-forth dialogue with the researcher until it has no further objection, then marks the step resolved (无异议). Trigger when the user wants to "review research", "audit a study", "check research steps", or "run the review backlog".
Patrols research step-by-step over MCP — for each step it checks whether enough is disclosed to REPRODUCE it (data, code, algorithm, analysis, conclusion)…
As a process B 67/100 · Nearly there — weak spots: result and completion, running it twice, 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 67/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 37 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 2814 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
- +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
- +5Description quotes 4 example trigger phrases
- +3Description length 705: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 37 items
- +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: 93.