AF prisma-2020-review-assistant
Review, audit, coach, and extract PRISMA 2020 reporting compliance for systematic reviews, meta-analyses, protocols, reviewer comments, and draft manuscript sections. Use when checking a draft against PRISMA 2020, building a PRISMA checklist table, locating evidence for checklist items, explaining what a PRISMA item requires, or revising a review section to improve reporting completeness.
As a process F 55/100 · Will not run — References files that are not bundled: assets/source-docs/PRISMA_2020_checklist.docx, assets/source-docs/PRISMA_2020_expanded_checklist.pdf
How to improve
- The text references files that are not there: add them or drop the references.
- 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
- warning
missing-refreference to a missing file: assets/source-docs/PRISMA_2020_checklist.docx - warning
missing-refreference to a missing file: assets/source-docs/PRISMA_2020_expanded_checklist.pdf
Process rating: all ten parameters 55/100
- 0Tools and files. 2 referenced file(s) missing: assets/source-docs/PRISMA_2020_checklist.docx, assets/source-docs/PRISMA_2020_expanded_checklist.pdf
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 7 branches
- 85Steps. 98 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1658 tokens
- 100Running it twice. No mutating operations
- low 11 top-level sections: this looks like several domains in one skill
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)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 391: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 98 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.