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
Evaluation results
98%
73%Prepare a New Contributor's Draft for Publication
TLDR and placeholder formatting
TLDR is bullet points
0%
100%
TLDR bullet count
0%
100%
TLDR bullets are provocative
0%
100%
TLDR recurring character last
0%
100%
TLDR compressed not miniaturized
0%
100%
Screenshot numbering independent
50%
100%
Code numbering independent
50%
100%
Link numbering independent
25%
100%
Zero-padded numbers
12%
100%
No shared counter
90%
100%
Hedging filler removed
37%
75%
100%
51%Write a Developer Blog Post from a Debugging Session Transcript
Blog draft from transcript
Research bank naming
100%
100%
Research bank structure
80%
100%
Draft file naming
100%
100%
TLDR is bullets
0%
100%
TLDR bullet count
0%
100%
TLDR placed before body
0%
100%
TLDR recurring character last
0%
100%
Opening is narrative
87%
100%
Placeholder independent numbering
0%
100%
Placeholder zero-padding
0%
100%
Code VERIFY comment
0%
100%
Bio post-specific kicker
100%
100%
Series callback present
100%
100%
Word count range
40%
100%
No preamble announcement
100%
100%
Voice in technical sections
80%
100%
Narrative density maintained
100%
100%
100%
18%Build a Writer's Voice Profile from Writing Samples
Voice persona onboarding
Voice one-paragraph section
50%
100%
Rhetorical devices with quotes
90%
100%
Cultural reference analysis
25%
100%
Recurring characters identified
100%
100%
Voice consistency notes
50%
100%
Humor analysis present
75%
100%
Bio schema present
100%
100%
Bio kicker notes
100%
100%
Examples file created
100%
100%
Examples have pattern annotations
100%
100%
Product context skipped
100%
100%
100%
27%Create an Editorial Plan for a Blog Post
Editorial planning workflow
Research bank file naming
100%
100%
Research bank sections
50%
100%
Main idea template format
50%
100%
CTA is practical and specific
75%
100%
Section outline with descriptions
100%
100%
Placeholder locations in outline
10%
100%
Questions are numbered
100%
100%
Questions include guesses
40%
100%
Questions grouped by type
100%
100%
Series callbacks referenced
100%
100%
No prose draft written
100%
100%
100%
6%Bring a Flat Blog Draft to Life
Soul check: fixing sterile but pattern-clean prose
Identifies soullessness
100%
100%
Opening hook improved
58%
100%
First-person opinion added
100%
100%
Rhythm variation added
100%
100%
Informal element added
100%
100%
No new anti-patterns introduced
100%
100%
Technical accuracy preserved
100%
100%
Humor or edge present
100%
100%
Varied paragraph energy
87%
100%
Structure preserved
100%
100%
97%
11%Clean Up a Blog Draft for Publication
AI anti-pattern remediation
Contrastive negation fixed
50%
100%
Parallel binary comparisons fixed
0%
100%
Asyndetic tricolon fixed
100%
100%
Choppy fragments fixed
100%
100%
Symmetrical LLM patterns fixed
100%
100%
Self-answering fragments fixed
100%
100%
Parenthetical em-dashes fixed
60%
100%
Excessive em-dashes reduced
100%
100%
Preamble removed
100%
100%
Hedging removed
100%
100%
Emojis removed
100%
100%
AI vocabulary cleaned
100%
100%
Copula avoidance fixed
100%
100%
Low burstiness improved
100%
100%
Fabricated experience removed
100%
100%
False ranges fixed
100%
100%
Synonym cycling fixed
100%
80%
Unicode giveaways fixed
100%
100%
Participle-phrase filler fixed
100%
100%
Significance inflation fixed
100%
100%
Challenge-optimism sandwich fixed
100%
100%
Inline-header lists fixed
0%
100%
Vague attributions fixed
100%
100%
Boldface overuse fixed
100%
100%
Title case headings fixed
40%
100%
Standalone positive conclusion fixed
100%
100%
Labeling the device fixed
100%
100%
Restating proven point fixed
75%
100%
Telegraphing transitions fixed
100%
100%
Incomplete assertions fixed
100%
100%
Stacked data points trimmed
100%
0%
Soul check evidence
50%
100%
100%
20%Tighten a Developer Blog Draft
Trust-the-reader pattern detection
Device labels removed
60%
100%
Key insight label removed
100%
100%
Proven point restatements removed
90%
100%
Telegraphed transitions removed
100%
100%
Incomplete assertions removed
100%
100%
Editorial superlative removed
100%
100%
Stacked data points trimmed
30%
100%
Redundant restatement of test suite time removed
0%
100%
Punchline isolation
100%
100%
No new anti-patterns introduced
100%
100%
Technical content preserved
100%
100%
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents