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 31 AI anti-patterns with structural variant detection, three-pass scanning (surface, skeleton, soul check), 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. Persona files live at ~/.claude/blog-writer-persona/ by default, with symlink support for custom locations (e.g. Google Drive for backup). Optional global voice saves your voice profile to Claude Code user memory so it applies across all projects. 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.
97
94%
Does it follow best practices?
Impact
99%
1.43xAverage score across 7 eval scenarios
Advisory
Suggest reviewing before use
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 clearly communicates specific capabilities, provides comprehensive trigger guidance, and occupies a distinct niche. It covers the full workflow from source material to finished blog post, includes unique differentiators like the 24 AI anti-patterns check, and provides thorough 'Use when' guidance with multiple natural trigger scenarios.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: extracting narrative from source material, structuring content with hooks and technical sections, formatting code examples with placeholders, and checking drafts against 24 AI anti-patterns. These are detailed and actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (write developer blog posts from various sources, extract narrative, structure content, format code, check against anti-patterns) and 'when' (explicit 'Use this skill whenever...' clause with multiple trigger scenarios including blog drafting, transcript conversion, and blog series continuation). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'blog post', 'draft a blog', 'transcript into a blog', 'blog content', 'blog', 'content creation', 'video transcript', 'blog series'. These are terms users would naturally use when requesting this kind of work. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: developer blog posts specifically from transcripts/notes, with the unique differentiator of checking against 24 AI anti-patterns. The combination of 'blog' + 'developer' + 'transcript' + 'anti-patterns' makes this unlikely to conflict with general writing or transcription 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, strong progressive disclosure, and highly actionable guidance. The phase-gated workflow with explicit validation checkpoints, the bootstrap sequence with branching logic, and the concrete placeholder formatting examples demonstrate sophisticated skill design. The main weakness is moderate verbosity — some sections (particularly Anti-Pattern Check Adherence and Persona Adherence) could be tightened by ~30% without losing information, as they repeat emphasis patterns that Claude doesn't need.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~200 lines) and includes some redundant emphasis (e.g., repeating 'do not skip phases' style warnings multiple times, the anti-pattern adherence section restates rules already implied by the workflow). However, most content is genuinely instructive and specific to this skill's unique workflow, so it's not egregiously verbose — just could be tightened in places. | 2 / 3 |
Actionability | The skill provides concrete, executable guidance throughout: specific bash commands (curl for Wikipedia, ln -s for symlinks), exact file paths, a clear phase-gated workflow with defined gates, specific placeholder formatting with numbered examples showing right vs wrong, and precise procedures (three-pass anti-pattern check). The blog anatomy section gives concrete structural guidance with specific do/don't examples. | 3 / 3 |
Workflow Clarity | The workflow is exceptionally well-structured with a clear phase table including explicit gates for each phase, a defined bootstrap sequence with branching logic, validation checkpoints (anti-pattern three-pass check, persona re-read before every writing action, voice spot-checks at phase transitions), and explicit error recovery ('if fetch fails, proceed with current file'). The feedback loop of Phase 4 revision with re-running checks is clearly defined. | 3 / 3 |
Progressive Disclosure | The skill is an effective overview that delegates detailed content to well-signaled reference files: persona/voice.md, references/tone-guide.md, references/ai-anti-patterns.md, references/process.md, references/setup.md, and persona/product.md. References are one level deep, clearly described with their purpose, and the reading order is explicitly specified. The main file stays at the orchestration level without inlining content that belongs in reference files. | 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.
Reviewed
Table of Contents