bapfernandez/article-reviewer
Editorial reviewer for tessl.io blog articles — scores drafts across SEO, alignment, technical depth, structure, and originality, then generates actionable feedback.
90
90%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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 an excellent skill description that is highly specific, comprehensive, and distinctive. It clearly articulates multiple concrete actions (scoring, style enforcement, SEO package generation, review comment production), provides explicit trigger guidance via a 'Use when...' clause with natural user terms, and is scoped to a specific brand context that minimizes conflict risk. The description uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: scores drafts across five named categories, enforces specific house style rules (em dashes, suggestive tone, heading hierarchy, internal links), generates SEO package with named components, and produces a copy-pasteable Google Docs review comment. | 3 / 3 |
Completeness | Clearly answers both 'what' (reviews, scores, enforces style, generates SEO package, produces review comment) and 'when' with an explicit 'Use when...' clause listing specific trigger scenarios like reviewing, editing, improving, or scoring a Tessl blog article or draft. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'review', 'edit', 'improve', 'structure', 'score', 'feedback', 'blog article', 'draft', plus the brand-specific 'Tessl' which is essential for routing. These cover the common ways someone would phrase such a request. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the brand-specific scope (Tessl blog at tessl.io/blog), the specific five-category scoring system, named house style rules, and the Google Docs review comment output format. Very unlikely to conflict with generic writing or editing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted editorial review skill with excellent actionability and workflow clarity — the output template, scoring rubrics, and step-by-step process leave little room for ambiguity. Its main weaknesses are moderate verbosity (the Tessl context section and some explanatory text could be leaner) and a monolithic structure that would benefit from splitting reference material into separate files. The house style checklist and type-mismatch guidance are particularly strong additions.
Suggestions
Move the SEO Priority Keywords table and the detailed Tessl context block into separate reference files (e.g., SEO_KEYWORDS.md, TESSL_CONTEXT.md) and link to them from the main skill to reduce token load.
Tighten the Tessl context section — Claude doesn't need the marketing-style framing ('the next unit of software', 'you can't optimize what you can't measure'); a lean bullet list of product facts and positioning would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is thorough and mostly earns its length given the complexity of the editorial review process, but there's notable verbosity in sections like the Tessl context block (explaining concepts Claude could be told more concisely) and the article type classification table with examples that pad the token count. The SEO keyword reference table and scoring rubrics are efficient, but the overall document could be tightened by ~20-30%. | 2 / 3 |
Actionability | Highly actionable — provides an exact output template with specific formatting, a concrete scoring rubric with clear anchors for each score level, a step-by-step review process, specific house style rules to check, and a committed SEO keyword decision process. The Google Docs comment template is copy-paste ready and leaves no ambiguity about what to produce. | 3 / 3 |
Workflow Clarity | The review process is clearly sequenced in 6 explicit steps (classify → note voice → score → generate SEO → produce comment → tone guidance). The scoring thresholds table provides clear decision points for recommendations. The house style quick-check serves as a validation checklist. For a non-destructive editorial review task, this level of workflow clarity is excellent. | 3 / 3 |
Progressive Disclosure | The content is entirely monolithic — everything lives in one long file with no references to external files for the detailed scoring rubrics, SEO keyword clusters, or the Tessl context block. The SEO keyword reference table and the detailed 5-category scoring rubrics could be split into separate reference files, with the main skill providing a concise overview and linking out. The document is well-structured with clear headings, but at this length (~300+ lines), it would benefit from splitting. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents