jbaruch/blog-writer
Write developer blog posts from video transcripts, meeting notes, or rough ideas. Extracts narrative from source material, structures content with hooks and technical sections, formats code examples with placeholders, and checks drafts against 22 AI anti-patterns with structural variant detection, two-pass scanning, and rewrite auditing. Auto-updates anti-pattern list from Wikipedia before each session. Includes interactive onboarding to learn the author's voice from writing samples. Use this skill whenever the user wants to write a blog post, draft a blog, turn a transcript into a blog, work on blog content, or mentions "blog" in the context of content creation. Also trigger when the user provides a video transcript and wants written content derived from it, or when continuing work on a blog series.
94
Quality
94%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 hits all the marks. It provides specific concrete actions, comprehensive trigger terms that users would naturally say, explicit 'Use when' guidance with multiple scenarios, and a clear distinctive niche around developer blog content creation from source materials.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Extracts narrative from source material, structures content with hooks and technical sections, formats code examples with placeholders, and checks drafts against 22 AI anti-patterns.' | 3 / 3 |
Completeness | Clearly answers both what (write blog posts, extract narrative, structure content, format code, check against anti-patterns) AND when with explicit 'Use this skill whenever...' clause listing multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'blog post', 'draft a blog', 'transcript into a blog', 'blog content', 'blog', 'video transcript', 'blog series' - these are all phrases users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on developer blog posts from transcripts/notes with distinct triggers like 'blog', 'transcript into a blog', and the specific '22 AI anti-patterns' check makes it highly distinctive from general writing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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 skill with excellent workflow clarity and progressive disclosure. The phased approach with explicit gates, the persona check upfront, and the clear file references demonstrate strong structure. The main weakness is some verbosity in explaining blog writing concepts that could be trimmed, though the actionable guidance and concrete examples largely compensate.
Suggestions
Tighten the 'Blog Anatomy' section by removing explanatory phrases like 'Sells the "so what" without spoiling the journey' - Claude understands what a TLDR does
Consider moving the detailed blog anatomy section to a reference file since it's more about writing craft than Claude-specific instructions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some verbose explanations (e.g., the detailed blog anatomy section explaining what a TLDR is, what an opening hook should be). Some sections could be tightened without losing clarity. | 2 / 3 |
Actionability | Provides concrete, executable guidance throughout: specific curl command for fetching Wikipedia, exact file paths to read, clear placeholder syntax with examples, and specific phase gates. The workflow is copy-paste ready. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with explicit phases, gates, and validation checkpoints. The persona check at the start, anti-pattern freshness check, and the phase table with gates provide clear sequencing and feedback loops. | 3 / 3 |
Progressive Disclosure | Well-structured with clear references to external files (persona/voice.md, references/tone-guide.md, etc.) that are one level deep. The main skill provides an overview while pointing to detailed materials appropriately. | 3 / 3 |
Total | 11 / 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.
Install with Tessl CLI
npx tessl i jbaruch/blog-writer@0.6.1Reviewed
Table of Contents