tdg-personal/article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
87
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
92%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 clearly articulates specific content types, includes natural trigger terms, and explicitly addresses both what the skill does and when to use it. The voice-matching capability adds a distinctive angle, though there is some risk of overlap with other writing-related skills. The description uses proper third-person voice and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete content types: articles, guides, blog posts, tutorials, newsletter issues, and long-form content. Also specifies the distinctive capability of deriving voice from supplied examples or brand guidance. | 3 / 3 |
Completeness | Clearly answers both what ('Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance') and when ('Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'articles', 'guides', 'blog posts', 'tutorials', 'newsletter', 'long-form content', 'voice consistency', 'brand guidance'. These are terms users naturally use when requesting written content. | 3 / 3 |
Distinctiveness Conflict Risk | While it specifies long-form content with voice consistency, it could overlap with general writing or copywriting skills. The voice-matching aspect and 'longer than a paragraph' qualifier help differentiate it, but 'articles' and 'blog posts' are broad enough to potentially conflict with other content-creation skills. | 2 / 3 |
Total | 11 / 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.
A well-crafted, opinionated writing skill that is concise, well-structured, and avoids common LLM verbosity traps. Its main weakness is the lack of concrete before/after examples showing the principles in action, which would significantly boost actionability. The progressive disclosure is adequate but could benefit from linking to supplementary files for the genre-specific structure guidance.
Suggestions
Add 1-2 concrete before/after examples showing a generic AI paragraph rewritten according to the core rules, to make the guidance fully actionable.
Consider splitting the genre-specific structure guidance (Technical Guides, Essays, Newsletters) into a separate GENRES.md reference file to keep the main skill leaner and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line earns its place. No explanations of what articles are or how writing works. The banned patterns list and core rules are terse and specific. The skill assumes Claude's intelligence throughout. | 3 / 3 |
Actionability | The guidance is specific and opinionated (banned patterns, core rules, structure templates), but it's entirely instruction-based with no concrete examples of input/output. A before/after example of a rewritten paragraph or a sample outline would make it fully actionable. | 2 / 3 |
Workflow Clarity | The writing process is clearly sequenced (clarify → outline → proof-first sections → expand → cut). The quality gate serves as an explicit validation checkpoint before delivery. For a non-destructive creative task, this level of workflow structure is appropriate and complete. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and the voice handling correctly delegates to `brand-voice`. However, the structure guidance for three content types is inline when it could be split into separate reference files, and there's no navigation to any supplementary materials beyond the brand-voice reference. | 2 / 3 |
Total | 10 / 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 | |
Reviewed
Table of Contents