BB api-design-review
Use this skill when a backend engineer, platform engineer, or API team needs a structured review of a REST/HTTP API design (OpenAPI spec, design doc, or endpoint sketch) before clients build against it. Reviews nine dimensions and produces severity-tagged findings, a Top-5 must-fix list, and a Ship/Fix-then-ship/Hold verdict.
Use this skill when a backend engineer, platform engineer, or API team needs a structured review of a REST/HTTP API design (OpenAPI spec, design doc, or…
As a process B 68/100 · Nearly there — weak spots: when it triggers, inputs and preconditions
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Concealment
en-hide-from-userSKILL.md:168Instruction to hide actions from the user (negated — the text forbids it)2. Hold the finding and document the disagreement — do not silently delete a real issue.
negated
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 34, 83, 123): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 68/100
- 20When it triggers. No condition that starts the skill
- 30Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 59 steps, 1 vague phrases
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3779 tokens
- 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 The response is described with custom markup (4 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 327: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 59 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.