BF ai-qa-agent
AI QA Agent — the final quality gate before delivery. Tests code for correctness, verifies data integrity, checks brand voice compliance, and reviews document formatting. Use this skill whenever the user needs to review, verify, check, audit, inspect, or validate any deliverable before it ships. Triggers on requests like "review this", "check the code", "verify the data", "is this ready to send", "QA this", "does this match our brand voice", "final check", "sign off on this", or any task involving quality assurance, code review, data validation, copy editing, or pre-delivery verification. Make sure to use this skill whenever the user mentions reviewing, checking, verifying, approving, or doing a final pass on any deliverable — code, documents, data files, copy, or marketing assets — even if they don't explicitly say "QA". This agent works both standalone and as the downstream reviewer in the Staff Agent pipeline (Staff produces, QA reviews). NOT for: initial content creation (use ai-staff-agent), complex bug fixing (review and report, don't fix), or deployment verification.
AI QA Agent — the final quality gate before delivery.
As a process F 45/100 · Will not run — References files that are not bundled: references/brand-voice-guide.md
How to improve
- Shorten the description to 1024 characters.
- The text references files that are not there: add them or drop the references.
- 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
- error
description-longdescription is 1091 chars, limit 1024 - warning
missing-refreference to a missing file: references/brand-voice-guide.md
Process rating: all ten parameters 45/100
- 0Tools and files. 1 referenced file(s) missing: references/brand-voice-guide.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 60Steps. 86 steps, 4 vague phrases
- 60Result and completion. Output format stated, no completion criterion
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2886 tokens
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 1090: 120–800 characters recommended
- -5TODO / placeholder text left in the skill
- -4Absolute local paths (C:\Users, /home/…): not portable
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 18 headings
- +3Step-by-step instructions: 86 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.