bapfernandez/article-reviewer
Editorial reviewer for tessl.io blog articles. Scores drafts across six strategic dimensions (audience, AEO/GEO, SEO, Tessl alignment, technical depth, structure) with atom-level recommendations grouped under each dimension. Paste-ready output for Tessl's article review page.
65
82%
Does it follow best practices?
Impact
—
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, complete, and distinctive. It clearly articulates what the skill does (multi-dimensional blog review with scoring, house style enforcement, keyword commitment, and paste-ready output), when to use it (explicit trigger clause with natural user terms), and is scoped narrowly enough to the Tessl blog context to avoid conflicts. The description uses third person voice throughout and avoids vague language or buzzwords.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: scores across six named strategic dimensions totalling /30, enforces house style with specific rules (no em dashes, no hype, heading hierarchy, internal links), commits to a primary keyword from priority clusters, and outputs a paste-ready review. Highly detailed and concrete. | 3 / 3 |
Completeness | Clearly answers both 'what does this do' (reviews blog articles, scores across six dimensions, enforces house style, outputs paste-ready review) AND 'when should Claude use it' with an explicit 'Use when...' clause listing specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | The 'Use when...' clause includes natural terms users would say: 'review', 'edit', 'improve', 'structure', 'score', 'give feedback', 'blog article', 'draft', and 'Tessl'. These cover a wide range of natural phrasings a user might employ when requesting blog review help. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped specifically to Tessl blog articles with a named scoring framework, specific house style rules, and named priority keyword clusters. The combination of 'Tessl blog', the six named dimensions, and the specific output format makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is exceptionally actionable with a clear, well-sequenced workflow and concrete output format — Claude would know exactly what to do and produce. However, it is severely over-length, with extensive inline reference material (keyword clusters, scoring rubrics, persona matrices, house style checklists) that should be split into separate files. Redundancy across sections (em dash rules repeated three times, persona guidance in multiple places) further inflates token cost without adding clarity.
Suggestions
Extract the SEO Priority Keywords reference, Persona × Article Type Fit table, and House Style Quick-Check into separate bundle files (e.g., SEO_KEYWORDS.md, PERSONAS.md, HOUSE_STYLE.md) and reference them from the main SKILL.md with one-level-deep links.
Consolidate duplicate guidance: em dash rules, hype word lists, and persona defaults each appear in 2-3 places — define each once and reference that single location.
Compress the scoring rubric tables: the 0-5 anchor descriptions for each category could be reduced to 1-line anchors for scores 1, 3, and 5 only, cutting the scoring section roughly in half.
Remove explanatory framing that Claude doesn't need (e.g., 'A growing share of readers will ask ChatGPT, Claude, Perplexity, or Gemini rather than visit tessl.io') and replace with direct instructions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~400+ lines. It explains editorial concepts, persona definitions, and scoring rubrics at length that Claude could infer from much shorter instructions. The SEO keyword clusters, persona matrices, and scoring anchors could be dramatically compressed. Many sections repeat guidance (e.g., em dash rules appear in Step 1, the house style checklist, and the hard fails section). | 1 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: exact output templates with formatting, specific scoring rubrics with anchor examples, explicit decision processes for keyword selection, atom-level recommendation examples, and a paste-ready review format. Claude knows exactly what to produce and how to score each dimension. | 3 / 3 |
Workflow Clarity | The review process is clearly sequenced in 9 explicit steps (Step 0 through the Review Process section). The workflow includes validation checkpoints like hard fails that override scores, spectrum anchoring filters to run before scoring, and explicit thresholds for publish decisions. The sequence is logical: classify → filter → note voice → read → score → SEO → touchpoint → output. | 3 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of content with no bundle files or external references. The SEO keyword clusters, persona matrices, scoring rubrics, house style checklist, and output template are all inline. Much of this reference material (keyword clusters, persona fit tables, house style checklist) would be better split into separate reference files, with the SKILL.md serving as an overview pointing to them. | 1 / 3 |
Total | 8 / 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