agentleFS
Arnie016Arnie016/fable-mythos/skills/voice-capsule/SKILL.md

voice-capsule

Skill0 starsChanged 4 months agoMITView on GitHub

Builds a reusable personal style guide (voice capsule) from the user's real writing samples so any model can write closer to their voice. Use when the user wants output to sound like them, asks to capture their voice or style, or complains that AI writing sounds generic.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Two registers = two modes: If the samples split into distinct voices (technical vs.

    line 19
  2. Distinctive:

    Validate: write one 100-word test paragraph with the capsule, compare against the samples, patch the capsule where it drifted.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Voice Capsule

Mission

Compress how a person actually writes into a capsule — rules plus annotated examples — that a cheaper model can follow later. Voice transfers through examples far better than through adjectives; the rules only fence off the failure modes.

Required input

At least 5 writing samples the user is proud of. Fewer than 5: ask for more, or proceed with an explicit LOW CONFIDENCE label — never fake a full capsule from two posts.

Workflow

  1. Find the patterns: sentence rhythm, how they open, how they close, signature moves, how they handle claims and hype, what they never do.
  2. Rules only where the pattern holds in 3+ samples. A one-off flourish is not a rule.
  3. Ban horoscope rules. "Writes with clarity and passion" describes everyone and grades nothing. Every rule must be checkable: "opens with the problem, never the announcement" passes; "authentic tone" fails.
  4. The bulk goes to annotated excerpts: 4–6 short passages from the samples, each with one line on the move being made.
  5. Two registers = two modes. If the samples split into distinct voices (technical vs. casual), build two labeled modes — never average them into mush.
  6. Validate: write one 100-word test paragraph with the capsule, compare against the samples, patch the capsule where it drifted.

Boundaries

This builds the user's voice from the user's writing. If asked to clone a named writer instead, say the capsule is built from their own samples — influences can be noted as references, not copied as identity.

Output format

Capsule file

Rules (each traceable to samples) · never-do list · annotated excerpts · modes if applicable.

Validation

The test paragraph + what was patched.

How to use it

One line: paste the capsule before any writing task, or attach it to a skill's examples file.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.