CB devil
Reviews a product document (PRD, spec, design brief) BEFORE implementation to surface holes — undefined edge cases, missing states, policy gaps — by attacking what the document is SILENT about (things unwritten, and things written only for the happy path). Acts as a strict "sign-off manager," ruling Approve / Conditional / Reject and producing a polite, forwardable question list. Works for planners/PMs (self-review before sharing), engineers (blocking questions before coding), and designers (screen states with no mockup). Use whenever the user wants a spec/PRD/plan/brief checked for readiness or gaps, or says "review this spec", "find holes in this PRD", "poke holes in this", "is this plan good to build?", "can I start implementing this?", "what states/edge cases am I missing?", "what should I ask the PM before coding?", "run devil", or pastes/links a planning document and asks whether it's ready to act on. Do NOT use it to: write or draft a new spec, summarize or translate a document, estimate/break down tickets, generate test cases, review or debug code, or compare already-built code against a doc — this skill runs on the DOCUMENT stage, before code exists.
Reviews a product document (PRD, spec, design brief) BEFORE implementation to surface holes — undefined edge cases, missing states, policy gaps — by attacking…
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- Shorten the description to 1024 characters.
- 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
- error
description-longdescription is 1178 chars, limit 1024
Process rating: all ten parameters 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4361 tokens
- 100Steps. 22 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Description length 1177: 120–800 characters recommended
- -5TODO / placeholder text left in the skill
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 14 headings
- +3Step-by-step instructions: 22 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.