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
The following published posts define the canonical tone. When adding new examples, add them to this list with a one-line note about what they demonstrate.
URL: https://tessl.io/blog/my-coding-agent-lied-to-me-and-i-have-the-screenshots/ Series: Agent Johnson, Episode 1 Key patterns: Opening with collaborator banter, escalating failure narrative, "But wait it gets better" transitions, AirPointsHelper3000 naming joke, the wink-CTA ending.
URL: https://tessl.io/blog/my-coding-agent-invented-an-api-that-doesnt-exist-and-blamed-cors-when-it-failed/ Series: Agent Johnson, Episode 2 Key patterns: Callback to previous post, Head First Java extended analogy, constitution/ Continental Congress running joke, Viktor-as-foil dynamic, "tried pure vibecoding before" continuity, "Which one do you want running in production?" rhetorical closer.
URL: https://tessl.io/blog/my-coding-agent-needed-a-package-manager-for-its-own-brain-and-i-gave-it-one-using-a-skills-registry/ Series: Agent Johnson, Episode 3 Key patterns: "Three months is a long time in AI tooling" opening, skills-as-package-manager analogy, the monkey problem (agent skipping failing e2e tests), "vibecoding is fast food / SDD is a chef's meal" closer from Viktor, intent integrity chain teaser. Quality note: This post was written with a smaller context window and has sections where the voice drifts toward industry analyst tone ("The architectural convergence signaled a winning approach") and events are summarized rather than shown as specific moments. Use it as a reference for structure and series continuity, but calibrate voice quality against Episodes 1 and 2.
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
example-persona