agentleFS
Rushik-GhuntalaRushik-Ghuntala/claude-code-skills/skills/post-creator/SKILL.md

post-creator

Skill0 starsChanged 7 months agoMITView on GitHub

Create complete, ready-to-publish single tweets from a topic or rough idea with multiple format variants

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create complete, ready-to-publish single tweets from any topic or rough idea.

    line 9
  2. Very specific:

    Use CTA patterns from references/cta-patterns.md

    line 20
  3. Distinctive:

    Every post must be COMPLETE — not a hook that trails off

    line 65
  4. Distinctive:

    Use specific numbers and details over vague claims

    line 67
  5. Distinctive:

    No external links in the tweet body (suggest self-reply for links)

    line 68

≈ “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

Post Creator

Create complete, ready-to-publish single tweets from any topic or rough idea. Generates 3 variants in different formats, scored for engagement.

Instructions

  1. Parse the topic/idea from $ARGUMENTS
  2. Generate viral hooks first — Before writing posts, generate 5 scroll-stopping hook options using the hook archetypes from ../viral-hook-generator/references/hook-patterns.md and voice archetypes from ../viral-hook-generator/references/dev-voice-archetypes.md. Score each hook on Curiosity (0-10), Specificity (0-10), and Algorithm-Friendliness (0-10). Select the top 3 hooks to use as openers for each post variant.
  3. Identify the best 3 post formats from references/post-formats.md that fit the topic
  4. Generate 3 complete post variants — each using one of the top-scored hooks as its opener, in a different format:
    • Each post must be complete and ready to publish (not just a hook)
    • Include hook + body + CTA in one tweet
    • Stay within 280 characters (or clearly mark if it's a long-form post)
    • Use CTA patterns from references/cta-patterns.md
  5. Score each post using engagement-prediction logic:
    • Hook Strength (0-20)
    • Reply Potential (0-20)
    • Share Potential (0-20)
    • Save Potential (0-15)
    • Algorithm Fit (0-15)
    • Audience Match (0-10)
    • Total: 0-100
  6. Rank by total score (highest first)

Output Format

🎣 Hook Generation for: [TOPIC]

Top hooks selected (scored by Curiosity + Specificity + Algorithm-Friendliness):
1. "[Hook text]" — Total: XX/30 (C: X | S: X | A: X)
2. "[Hook text]" — Total: XX/30 (C: X | S: X | A: X)
3. "[Hook text]" — Total: XX/30 (C: X | S: X | A: X)

---

📝 Posts for: [TOPIC]

1. (Score: XX/100 — [Format Type])
   "[Complete tweet text]"
   
   Breakdown: Hook X/20 | Reply X/20 | Share X/20 | Save X/15 | Algo X/15 | Audience X/10

2. (Score: XX/100 — [Format Type])
   "[Complete tweet text]"
   
   Breakdown: Hook X/20 | Reply X/20 | Share X/20 | Save X/15 | Algo X/15 | Audience X/10

3. (Score: XX/100 — [Format Type])
   "[Complete tweet text]"
   
   Breakdown: Hook X/20 | Reply X/20 | Share X/20 | Save X/15 | Algo X/15 | Audience X/10

🕐 Best time to post: [recommendation based on content type]
💡 Tip: [one specific improvement suggestion for the top-scoring post]

Key Rules

  • Every post must be COMPLETE — not a hook that trails off
  • Vary the formats across the 3 variants
  • Use specific numbers and details over vague claims
  • No external links in the tweet body (suggest self-reply for links)
  • Max 2 hashtags, placed naturally
  • End with engagement driver (question, CTA, or strong closer)

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.