agentsclimarketplace

Frankx authority post

Skill frankxai/starlight-agent-skills/skills/brand/frankx-authority-post

Write a FrankX authority post — an AI-Architect-voiced LinkedIn/X post that leads with a result, teaches one concrete lesson, and stays humble. Use when drafting a thought-leadership post as FrankX, sharing a build/insight, or asked for an 'authority post'.From its SKILL.md

Install
npx -y skills add frankxai/starlight-agent-skills --skill frankx-authority-post

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.8 KB, 616 tokens by cl100k_base, as published. Nobody here has run it

FrankX Authority Post

An insight or shipped result → a FrankX-voiced authority post.

Purpose

FrankX's positioning is elite creator, AI architect, humble. This skill drafts authority content in that voice: lead with a demonstrated result, extract one concrete, teachable lesson, and let the work speak — no guru cadence, no grandiose claims. Output is ready to post on LinkedIn or X.

When it fires

  • Keyword triggers: authority post, frankx post, thought leadership, linkedin post, share this insight
  • File triggers: posts/**
  • Command triggers: /frankx-authority-post

Inputs

InputRequiredNotes
seedyesThe result/insight/build to post about.
platformnolinkedin (default) or x.
ctanoOptional soft call-to-action.

Voice rules

Lead with results and demonstrated expertise; precise/technical where useful; show don't tell; confident but understated. Avoid: spiritual/consciousness language, grandiose impact claims, over-explaining motivation, self-help cadence. Every claim must be earned and specific.

Workflow

  1. Find the result — the concrete, true thing that earns attention. ✅ Check: it's demonstrated, not asserted.
  2. Hook — first line states the result or the surprising lesson.
  3. Body — the one lesson, with enough specifics to be useful; humble about scope.
  4. Close — optional soft CTA or open question.
  5. Voice pass — strip guru/grandiose phrasing; verify every claim is earned.

Output contract

{
  "platform": "linkedin | x",
  "post": "string",
  "hook": "string — first line",
  "lesson": "string — the one teachable point",
  "claims_checked": ["string — each claim + why it's earned"]
}

Tools & MCP

  • Tools: Read. MCP: none required.

Quality bar

  • Leads with a demonstrated result, not a claim.
  • Exactly one clear, concrete lesson.
  • No spiritual/guru/grandiose language.
  • Humble in tone; specifics over superlatives.

Example

Input: "Shipped a 6-skill portable library that runs across 5 runtimes" → a LinkedIn post leading with that result, teaching one lesson about portable skill design, with a soft question close.


Built on SIP — Starlight Intelligence Protocol Substrate: starlightintelligence.org/protocol v1.1.0 Layers used: [file-contract, attestation, sovereignty] Vertical: starlight-agent-skills · portable capability layer

What ships with it: 3 files

3.1 KB alongside SKILL.md

examples/

tests/

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.