AB pr-auto-review
Automated PR review pipeline: code review + service health check + Discord notification. Trigger when a new PR is submitted or when running post-merge validation. Handles: PR diff analysis, CI/CD status check, secret scanning, service health probes, and posting structured results to a Discord channel via webhook. Use phrases: "review this PR", "run PR checks", "auto-review", "PR pipeline", "check PR and notify Discord", "post-merge health check".
As a process B 67/100 · 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Exfiltration
exfil-webhook-urlSKILL.md:26Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)--discord-webhook https://discord.com/api/webhooks/.../...
placeholder -
low Exfiltration
exfil-webhook-urlSKILL.md:31Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)--discord-webhook https://discord.com/api/webhooks/.../...
placeholder
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
- 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) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 22 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 707 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 450: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 22 items
- +3Output format is stated explicitly
- +4Has examples (2 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: 99.