CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

72

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable QA playbook with excellent progressive disclosure and concrete checklists throughout. The body is efficient and clearly sequenced, with only minor verbosity in framing prose and slightly conceptual validation guidance inline before delegation to references.

Suggestions

Tighten the recurring '47-item checklist / process theater' framing so it is stated once rather than restated across the intro, the catch-problems section, and the failure modes section.

Promote at least one concrete validate-fix-retry loop into the main body (e.g. for fact-accuracy or schema validation) rather than delegating all feedback loops to reference files, since this is a publish-gate skill where validation is central.

Convert a few directive checks like 'read with these patterns top-of-mind. Flag any match' into a short enumerated procedure so the action is unambiguous without needing the reference.

DimensionReasoningScore

Conciseness

Mostly lean and efficient with bullet-driven, opinionated sections that earn their place, but the 'process theater / 47-item checklist' motif repeats across the intro and multiple sections and the framing/closing prose could be trimmed. Efficient with minor over-explanation rather than the leanest possible form.

4 / 5

Actionability

Concrete, specific checklists per QA gate with quantified thresholds ('5%', '40 to 60 word answer paragraph', '3 to 7 internal links'), though some guidance stays at directive level ('read with these patterns top-of-mind. Flag any match') rather than fully procedural steps.

4 / 5

Workflow Clarity

Clear sequencing ('Brief-adherence runs first... A final read closes the sequence'), explicit halt vs flag vs auto-fix, and escalation paths are present; the main body describes validation conceptually while delegating the explicit validate-fix-retry loops to references, leaving minor checkpoint gaps inline.

4 / 5

Progressive Disclosure

Clear overview body with 10 well-signaled one-level-deep references, all verified as real files, plus an organized reference file list with per-file descriptions — easy to navigate and content appropriately split.

5 / 5

Total

17

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, well-triggered description that cleanly answers what the skill does and when to invoke it, with explicit boundary guidance against a sibling skill. Every dimension lands at the top anchor.

DimensionReasoningScore

Specificity

Lists multiple specific concrete coverage areas — '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' — comprehensive across the QA surface.

5 / 5

Completeness

Explicitly answers both 'what' (the pre-publish QA framework and its coverage) and 'when' via 'Triggers on...' and 'Also triggers when...' clauses with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger terms including synonyms — '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' — plus situational phrasings users would actually say.

5 / 5

Distinctiveness Conflict Risk

Clear niche as the pre-publish QA gate, with explicit disambiguation ('use `brand-voice` when the voice system itself needs defining') and distinct positioning against the other content-suite skills.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
rampstackco/claude-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.