agentleFS
Sign inStart free
Starlight-IntelligenceStarlight-Intelligence/starlight-agent-skills/skills/brand/starlight-voice/SKILL.md

starlight-voice

Skill1 starsChanged 4 months agoMITView on GitHub

Apply the Starlight voice to any text — cool, premium, high-intellect, direct, technical, warm, playful; pattern recognition as poetry. Use when writing or rewriting content in the Starlight register, enforcing brand voice, or asked to 'make this sound like Starlight'.

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

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Test (Frank DNA): every phrase should be *measurable, actionable, grounded, earned* — if someone asks "what does that mean specifically?", …

    line 40

≈ “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

Starlight Voice

Any draft → the same content in the Starlight register.

Purpose

Starlight is the substrate brand register: cool, premium, intellectually serious, and genuinely fun — direct and technical, but warm. This skill applies that voice consistently and strips the failure modes (spiritual/guru language, vague transformation talk, grandiose claims) so output reads as Starlight, not generic.

When it fires

  • Keyword triggers: starlight voice, brand voice, make this sound like starlight, on-brand, rewrite in voice
  • File triggers: content/**, *.mdx, *.md
  • Command triggers: /starlight-voice

Inputs

InputRequiredNotes
textyesDraft to voice.
modenorewrite (default) or review (annotate, don't change).

Voice rules

Do: lead with results; precise, technical language where it earns its keep; show don't tell; confident but understated; pattern recognition framed vividly. Don't: spiritual/consciousness language ("soul-aligned", "awakening", "transformation"); grandiose impact claims; over-explaining motivation; self-help-guru cadence.

Test (Frank DNA): every phrase should be measurable, actionable, grounded, earned — if someone asks "what does that mean specifically?", you can answer with an example.

Workflow

  1. Diagnose — flag off-register phrases (spiritual/vague/grandiose). ✅ Check: each flag cites the rule it breaks.
  2. Rewrite (or annotate, in review mode) into the Starlight register.
  3. Preserve meaning + facts — voice changes tone, not truth.
  4. Final pass — does it sound cool, premium, and earned?

Output contract

{
  "mode": "rewrite | review",
  "result": "string — rewritten text (rewrite mode)",
  "flags": [{ "span": "string", "rule": "string", "fix": "string" }]
}

Tools & MCP

  • Tools: Read. MCP: none required.

Quality bar

  • No spiritual/guru/vague-transformation language remains.
  • Claims are earned and specific.
  • Facts unchanged; tone is cool, premium, warm, direct.

Example

Input: "This soul-aligned system will transform your consciousness." → review flags both phrases; rewrite → "This system changes how you work: [specific, demonstrated outcome]."

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

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.

Check your setup, free