agentleFS
namddpnamddp/social-media-agent-skills/skills/social-brand-voice/SKILL.md

social-brand-voice

Skill0 starsChanged 4 months agoMITView on GitHub

Build a practical social voice card from real writing samples, audience context, and explicit boundaries.

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

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Create a reusable voice card that helps every later draft sound recognizably human without imitating another creator.

    line 10
  2. Distinctive:

    Every voice claim is supported by an approved sample or labeled as a hypothesis.

    line 45
  3. Distinctive:

    Never infer sensitive personal traits from writing.

    line 52
  4. Distinctive:

    Never imitate a third party without authorization.

    line 53
  5. Distinctive:

    Never expose private samples in the final voice card.

    line 54
  6. Distinctive:

    Stop at a reviewed voice artifact.

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Social Brand Voice

Purpose

Create a reusable voice card that helps every later draft sound recognizably human without imitating another creator.

Inputs

  • Three to ten approved writing samples from the same person or brand
  • Audience, offer, and communication goal
  • Words, claims, jokes, and topics that are off-limits
  • Optional preferred language, dialect, and technical depth

Workflow

  1. Separate repeated habits from one-off phrases.
  2. Identify sentence rhythm, vocabulary, point of view, humor, evidence style, and call-to-action style.
  3. Extract short examples only from user-provided approved material.
  4. Define three voice anchors and three anti-patterns.
  5. Mark uncertain observations as hypotheses for human review.
  6. Produce a compact card that another skill can apply without the original samples.

Output

# Voice card
- Audience:
- Voice anchors:
- Sentence rhythm:
- Vocabulary to prefer:
- Patterns to avoid:
- Evidence style:
- Call-to-action style:
- Approved examples:
- Open questions:

Quality gate

  • Every voice claim is supported by an approved sample or labeled as a hypothesis.
  • The card describes patterns instead of copying signature lines.
  • Guidance is specific enough to reject an off-brand draft.
  • The card fits on one screen where practical.

Safety

  • Never infer sensitive personal traits from writing.
  • Never imitate a third party without authorization.
  • Never expose private samples in the final voice card.
  • Stop at a reviewed voice artifact; do not publish content.

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.