agentleFS
gladosAagmangladosAagman/linkedin-agent-skill/skills/li-voice/SKILL.md

li-voice

Skill1 starsChanged 5 days agoMITView on GitHub

Measure the user's actual LinkedIn voice from their own past posts and write voice.md from evidence, then check any draft for drift before it goes out. Use when the user says "write my voice.md", "learn how I write", "does this sound like me", "this doesn't sound like me", sets up the pack for the first time, or pastes several of their own posts.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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 skill in this pack reads ~/.claude/linkedin/voice.md.

    line 13
  2. Very specific:

    Run voice.py on the samples and save the JSON profile.

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

li-voice

Every skill in this pack reads ~/.claude/linkedin/voice.md. Filled in by hand, it says how the user would like to sound. Measured from their posts, it says how they do sound, and that is the version their network recognises. LinkedIn now holds back posts that read as low-effort AI. The fix is not a detector trick. It is sounding like the person whose name is on the post.

One tool lives in this folder and it runs:

python3 voice.py samples.txt                                   # measure, print the profile
python3 voice.py samples.txt --save ~/.claude/linkedin/voice.json
python3 voice.py --profile ~/.claude/linkedin/voice.json --check draft.txt

Input

Five to fifteen of the user's own posts, pasted into one file with a line of --- between them. Their own posts, written before they used AI on them if possible. Ghostwritten posts measure the ghostwriter.

Fewer than five and the tool says so. Do not pad the sample with posts you wrote for them.

What it measures

Sentence length and how much it varies, contractions, I / we / you, how often they ask questions or exclaim, casing, emoji, em dashes, how many numbers they use, and the words and openers that recur across posts. Each one is a mean and a spread, so a draft is judged against the user's own range, not against a rule.

Then write voice.md

  1. Run voice.py on the samples and save the JSON profile.
  2. Fill in templates/voice.md from what the user tells you (who they write for, what they sell, what is off limits, the proof they can use).
  3. Paste the Measured voice block the tool printed under "What I sound like". Where the hand-written answers disagree with the measurement, say so: "You said short and punchy. Your posts average 19 words a sentence." The measurement wins unless the user says they are changing on purpose.
  4. Save it to ~/.claude/linkedin/voice.md.

Checking a draft

--check scores a draft 0-100 against the profile and names the metric furthest from the user. Hard flags (emoji when they never use one, an em dash when they never write one, sentence case when they write lower-case, no contractions when they always use them) cap the verdict at CLOSE.

/li-preflight runs this check automatically when the profile exists.

Say this honestly

This is stylometry on a small sample, not identity verification. It catches a draft that drifted into generic LinkedIn voice. It cannot tell you a post is good. A post can match the voice perfectly and still have nothing in it.

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.