AF research-review-skill-factory
Build custom peer-review skills for specific research areas, problem families, and method combinations using OpenReview evidence. Use when Codex needs a compact meta-review skill factory that takes a research field or topic cluster, retrieves and synthesizes recent ICLR/OpenReview reviewer concerns and accepted-paper author response patterns, then generates a ClawHub-ready reviewer skill tailored to that field/problem rather than to one specific manuscript.
As a process F 43/100 · Will not run — References files that are not bundled: references/research_area_profile.md, references/openreview_review_response_bank.md, references/review_output_contract.md
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: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/research_area_profile.md - warning
missing-refreference to a missing file: references/openreview_review_response_bank.md - warning
missing-refreference to a missing file: references/review_output_contract.md
Process rating: all ten parameters 43/100
- 0Tools and files. 3 referenced file(s) missing: references/research_area_profile.md, references/openreview_review_response_bank.md, references/review_output_contract.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 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
- 100Steps. 40 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 984 tokens
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
- +2Single-language instructions
- +3Description length 461: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 40 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.