← ClaudeAtlas

proselisted

Drafts, revises, and humanizes prose in two modes. DRAFT MODE writes new content in the correct voice and structure for the medium. REVIEW MODE scans existing text for AI writing patterns, scores it, and rewrites it in an authentic human voice. Detects the channel (blog, social media, email, IM, documentation, creative) and applies channel-specific rules, calibrating to a supplied writing sample. Use when writing blog posts, articles, documentation, runbooks, specs, emails, social media posts, IM, marketing copy, or UI text, and for fiction, poetry, scripts, and memoir. Also for reviewing a draft for AI texture, humanizing AI-generated writing, checking if text sounds like AI, rewriting in a stated voice, or removing AI patterns. Triggers are humanize, sounds like AI, voice check, blog review, rewrite in the user's voice, email review, draft this, remove AI patterns, write an email, write a social media post, review this doc, edit this scene. Don't use for code comments, commit messages, or private notes.
robcsaszar/prose · ★ 0 · AI & Automation · score 72
Install: claude install-skill robcsaszar/prose
# Prose Two modes. Detect the correct one before doing anything else. ## Mode Detection **Draft mode** — user has a topic, brief, or outline and wants new content written. **Review mode** — user has existing text and wants it improved, humanized, or scored. If ambiguous: ask — "Do you want me to write new content, or review/rewrite something you already have?" If the user does not respond, default to Draft Mode. --- ## Voice Calibration Before drafting or rewriting, ask for a voice sample if the user hasn't provided one. For short-form targets (IM, emails under 200 words): skip voice calibration unless the user has already provided a sample. > "Share 1–3 paragraphs of your own writing that feel most like you. I'll match your > sentence rhythm, word choice, and structural habits." Analyze the sample for: - Sentence length tendency (punchy / analytical / mixed) - How they open (claim-first, story-first, data-first, context-first) - Punctuation habits (parentheticals, colons, semicolons) - Recurring phrases or verbal tics - How they end (principle, challenge, open question, action) - Words they never use **Persisting the profile.** After analyzing a sample, offer to save the result so future sessions skip recalibration: fill in `references/voice-profile-template.md` and write it to `references/voice-profile.md` inside the skill folder (if the folder is read-only, output the completed profile for the user to save). If `references/voice-profile.md` already exists, read i