agentleFS
uplikauplika/uplika-plugin/skills/voice-profile/SKILL.md

voice-profile

Skill3 starsChanged 35 days agoMITView on GitHub

Create or update the voice file the writing skills read: tone, ending style, words to avoid, signature, examples from recent posts.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every writing skill in this plugin reads one file before it writes: ~/.uplika/<workspace-slug>/voice.md.

    line 8
  2. Very specific:

    If the file exists, read it and ask what to change.

    line 18
  3. Distinctive:

    Ask three questions first, in the person's language: the tone (two or three words), how posts usually end, and words they never use.

    line 19
  4. Distinctive:

    Keep the profile in the conversation for this session only and say so.

    line 25

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “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 profile

Every writing skill in this plugin reads one file before it writes: ~/.uplika/<workspace-slug>/voice.md. One file per workspace, because a workspace is one brand. Claude Code, Codex and the other agents all read the same path, so the voice stays the same whichever agent writes.

When to use

  • The person asks to set up or change how their posts should sound.
  • A writing skill found no voice file and the person agreed to make one.

Procedure

  1. Find the workspace slug: list_accounts shows the workspace; if the account has several and the answer is workspace_required, ask which one and pass that workspaceId on every later call in this session.
  2. If the file exists, read it and ask what to change. Otherwise start from references/voice-template.md.
  3. Ask three questions first, in the person's language: the tone (two or three words), how posts usually end, and words they never use. Then the optional ones: who they talk to, what they will not claim, their signature (hashtags, sign-off, links).
  4. Pull examples from what they actually wrote: call list_channel_posts for their main channel and take three to five recent posts (their best ones if they say which). Paste them as they are; do not rewrite them.
  5. Show the whole file and save it only after they approve. Create the folder if needed.

Agents that cannot write files

Keep the profile in the conversation for this session only and say so. Offer the text so the person can save it themselves.

Tools

  • list_accounts: which workspace (slug) the file belongs to
  • list_channel_posts: the person's own recent posts as examples

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.