CB editorial-qa
Pre-publish QA framework for content. Brief adherence, voice consistency, fact accuracy, structure and clarity, AI-content audit, SEO and AEO compliance, internal linking and schema validation, QA at scale via sampling, the QA workflow, and the discipline that distinguishes catch-problems QA from checkbox QA. Triggers on editorial QA, content review, pre-publish review, content audit, content QA process, AI-content audit, hallucination check, content sampling, programmatic QA, voice consistency check, brief adherence check. Also triggers when a content team is shipping sloppy work, when AI-co-authored content is reaching publish unaudited, when a QA process burns reviewers out, or when a programmatic SEO set needs sampling discipline. On a voice consistency check, this skill owns checking a draft against an existing voice system at the publish gate; use `brand-voice` when the voice system itself needs defining or documenting.
Pre-publish QA framework for content.
As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5292 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "catalog_summary" - note
frontmatter-keyunknown frontmatter key "display_order" - note
edit-residuethe text marks something as outdated (lines 196): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 12 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70Execution cost. Instruction body is 5292 tokens
- 100Tools and files. No external tools needed
- 100Steps. 128 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low 15 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)
- +3Description length 939: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 16 headings
- +3Step-by-step instructions: 128 items
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (10 of 10)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.