What do I need to use Style Fingerprint?

3-5 samples the user wrote and shipped; The target register.

Is Style Fingerprint free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Style Fingerprint

Q: How do I know the Style Fingerprint output is good?

The skill verifies itself against its own quality checks: Every dimension yields a followable rule, not an adjective ("uses 8-14 word sentences, one 3-word sentence per paragraph" — not "punchy"); Signature moves are quoted verbatim from the samples; The banned list has at least 4 entries — voice is defined by what's absent; The proof paragraph is verifiably different from model-default and consistent with the samples.

🔵 Stable🕐 updated 2026-07-02 🔷 SkillSpec L3 pm-essentials

Study 3-5 documents the user actually shipped and distil a compact style card — so every skill writes in their voice, not the model's. Use when asked to learn my writing style, make outputs sound like me, build a voice profile, or when a user complains AI drafts don't sound like them. Produces a style card (rhythm, register, structure habits, pet phrases, banned moves) saved to the Brain where every other skill reads it.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸3-5 samples the user wrote and shipped — real emails, updates, PRD sections, posts. More samples of the *same genre* beat variety. Politely reject samples the user merely approved but didn't write — an edited-by-committee doc fingerprints the committee.

▸The target register — if samples span several (exec formal vs team casual) — or fingerprint each as a named variant

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Every dimension yields a followable rule, not an adjective ("uses 8-14 word sentences, one 3-word sentence per paragraph" — not "punchy")

✓Signature moves are quoted verbatim from the samples

✓The banned list has at least 4 entries — voice is defined by what's absent

✓The proof paragraph is verifiably different from model-default and consistent with the samples

✓The card is ≤300 words — a style card that's an essay never gets applied

⚠️ What it refuses to do

Do not fingerprint from fewer than 3 samples — you'd be fingerprinting one mood

Do not describe voice with adjectives ("professional yet approachable") — extract mechanics

Do not merge conflicting registers into one mushy card — name variants ("exec", "team") instead

Do not include the user's confidential content in the card — rules and short quoted phrases only

Do not overwrite an existing style card silently — diff against it and show what changed

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Start with

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="style-fingerprint"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Style Fingerprint is one of 625 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog