AB openreview-review-analyzer
Fetch and analyze peer reviews from OpenReview for any academic paper. Use this skill when the user mentions OpenReview, asks about reviews for a paper, wants a review summary or synthesis, provides an openreview.net URL, mentions a paper forum ID, asks about reviewer opinions or scores for a conference submission (ICLR, NeurIPS, ICML, AAAI, etc.), or wants to understand what reviewers think about a specific paper. Also trigger when the user says things like 'what did reviewers say about this paper', 'summarize the reviews', 'get reviews for this submission', or 'analyze reviewer feedback'. Even if the user just pastes an OpenReview link, this skill should trigger.
As a process B 71/100 · Nearly there — weak spots: inputs and preconditions, 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 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 23 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 906 tokens
- 100Running it twice. No mutating operations
- low The response is described with custom markup (3 tags): a typed call is more reliable
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 673: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 23 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.