agentleFS
namddpnamddp/social-media-agent-skills/skills/social-platform-adapter/SKILL.md

social-platform-adapter

Skill0 starsChanged 3 months agoMITView on GitHub

Convert an approved angle into a platform-native draft for eight major social channels.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Read references/platform-playbook.md and select the target platform guidance.

    line 21
  2. Distinctive:

    Write three hooks using different mechanisms: tension, specificity, and useful surprise.

    line 22
  3. Distinctive:

    Add only hashtags, links, and emojis that improve comprehension or discovery.

    line 25
  4. Very specific:

    Run social-skills lint and revise material findings.

    line 26
  5. Distinctive:

    Never manufacture urgency, scarcity, authority, or social proof.

    line 51
  6. Distinctive:

    Never include private account, customer, or analytics data without approval.

    line 52
  7. Distinctive:

    Never publish, schedule, reply, or message from this workflow.

    line 53

≈ “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 Platform Adapter

Purpose

Draft content that respects platform behavior while preserving the same verified facts and brand voice.

Inputs

  • One approved row from a repurposing map
  • Voice card and source brief
  • Target platform
  • Desired reader action

Workflow

  1. Read references/platform-playbook.md and select the target platform guidance.
  2. Write three hooks using different mechanisms: tension, specificity, and useful surprise.
  3. Choose the hook that best matches the evidence, not the most dramatic claim.
  4. Draft with platform-native pacing and formatting.
  5. Add only hashtags, links, and emojis that improve comprehension or discovery.
  6. Run social-skills lint and revise material findings.
  7. Label the result as a draft awaiting human approval.

Output

# Platform draft
- Platform:
- Objective:
- Selected hook:
- Draft:
- Source claims used:
- Lint notes:
- Approval status: DRAFT

Quality gate

  • The opening communicates a real reason to continue.
  • The draft contains at least one concrete fact, example, or useful instruction.
  • Platform choices affect structure, not just character count.
  • The call to action asks for one proportionate next step.

Safety

  • Never manufacture urgency, scarcity, authority, or social proof.
  • Never include private account, customer, or analytics data without approval.
  • Never publish, schedule, reply, or message from this workflow.

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.