AB review-pr
Review a GitHub pull request from a PR number, repo-qualified reference, or URL; reconcile the current content against all earlier review comments so fixes do not regress; post one consolidated PR comment; and watch for the PR author's "addressed" responses until a clean review, at no/low token cost while nothing changes. Use when the user asks to review, babysit, re-check, or continuously monitor a PR until no blocking issues remain, with bounded convergence across follow-up cycles.
Review a GitHub pull request from a PR number, repo-qualified reference, or URL; reconcile the current content against all earlier review comments so fixes do…
As a process B 79/100 · Nearly there — weak spots: result and completion
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: 3. 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 79/100
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4899 tokens
- 100Steps. 74 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 488: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 74 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.