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.
64
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/editorial-qa/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that thoroughly covers what the skill does (pre-publish QA framework with specific review dimensions) and when to use it (explicit trigger terms plus situational descriptions). The description is comprehensive without being vague, listing concrete QA activities and providing both keyword-based and scenario-based triggers. Minor weakness is that it's somewhat verbose and could be slightly more concise, but the detail serves the purpose of disambiguation.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 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. These are concrete, identifiable activities rather than vague abstractions. | 3 / 3 |
Completeness | Clearly answers both 'what' (pre-publish QA framework covering brief adherence, voice consistency, fact accuracy, etc.) and 'when' (explicit 'Triggers on...' clause with keyword triggers plus situational triggers like 'when a content team is shipping sloppy work'). The trigger guidance is explicit and comprehensive. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'editorial QA', 'content review', 'pre-publish review', 'content audit', 'hallucination check', 'content sampling', 'voice consistency check', 'brief adherence check'. Also includes situational triggers like 'shipping sloppy work' and 'AI-co-authored content reaching publish unaudited' that match how users naturally describe their problems. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche: pre-publish content QA specifically. The combination of editorial QA, AI-content auditing, voice consistency, and programmatic SEO sampling creates a distinct identity unlikely to conflict with general content creation, SEO, or editing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
54%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at workflow clarity with well-defined sequencing, halt conditions, and escalation patterns, and has excellent progressive disclosure with 10 clearly organized reference files. However, it is significantly over-verbose—repeating the 'catch-problems vs checkbox' framing multiple times, explaining concepts Claude already knows, and including philosophical framing that doesn't add actionable value. The actionability is moderate: checklists are specific but lack executable templates or automation scripts.
Suggestions
Cut the first 4 paragraphs (problem framing, production shapes, when-to-use) and the 'What this skill is for' section down to 2-3 sentences max—Claude doesn't need the editorial philosophy explained at length.
Remove the 'Catch-problems QA vs checkbox QA' section or reduce it to a single sentence principle; the concept is restated in the intro, the framework summary, and the closing.
Add a concrete, copy-paste-ready QA checklist template (e.g., a markdown table or structured format) that an editor could immediately use as a review document for a single piece.
Remove the closing section entirely—it restates the framework considerations that were just listed and adds no new actionable information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~2,500+ words. It extensively explains concepts Claude already understands (what QA is, why checkbox QA fails, what hallucinations are), repeats the 'catch-problems vs checkbox' framing multiple times, includes lengthy philosophical framing ('the immune system of the content program'), and the closing section restates what was already covered. The introductory paragraphs alone spend ~150 words explaining the problem before any actionable content appears. | 1 / 3 |
Actionability | The skill provides concrete checklists (brief-adherence checks, AI tells, SEO checks, sampling numbers like '50 to 200 pages') and specific sequencing guidance, which is genuinely useful. However, it lacks executable code/commands, automation scripts, or copy-paste-ready templates. The guidance is specific but descriptive rather than executable—it tells you what to check but doesn't provide a runnable QA template, scoring rubric, or automated validation approach. | 2 / 3 |
Workflow Clarity | The QA workflow section provides clear sequencing (brief-adherence → fact-accuracy → structure → AI-audit → voice → SEO/AEO → linking → schema), explicit halt vs flag vs auto-fix categorization, single-owner accountability, escalation patterns, and threshold gating for scale (5% failure rate halts generation). The feedback loops are well-defined with clear decision points. | 3 / 3 |
Progressive Disclosure | The skill has a clear overview structure with 10 well-organized reference files, each clearly signaled with descriptive labels and one-level-deep links. The main SKILL.md provides enough detail to act on each check while pointing to reference files for deeper detail. Navigation is straightforward and the content split between overview and references is appropriate. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- rampstackco/claude-skills
- Commit
8e70d03
- 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.