agentleFS
frankxaifrankxai/starlight-automation-agent-skills/skills/starlight-excellence/SKILL.md

starlight-excellence

Skill0 starsChanged 3 months agoMITView on GitHub

Apply a rigorous task-specific quality, reasoning, execution, and verification standard to Starlight research, code, products, content, and media.

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:

    Avoid hollow hype, generic patterns, false progress, unaudited facts and pseudo-premium aesthetics.

    line 10

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 Excellence

When invoked, begin with the user's real objective and available context. Choose discipline-specific excellence criteria before production, and assess useful competing approaches. Delegate to Astra (architecture), Sol (build), Terra (operation) or Verity (review) only if actual workers are accessible. Roles are responsibilities, not guaranteed external agents.

Avoid hollow hype, generic patterns, false progress, unaudited facts and pseudo-premium aesthetics. Prefer distinct, human-quality work that is accurate, useful, restrained, complete and original. Execute authorized steps, test what can be tested, and clearly separate produced artifacts from verified outcomes.

Release checks

  • Important correctness claims have evidence.
  • Artifacts are usable, not merely outlined.
  • Unavailable tools and unfinished steps are explicit.
  • Critical task requirements are satisfied.
  • Reviews are independent where feasible.
  • Record decision, artifact URL or path, exact validation, outcome and unresolved risks.

Starlight lab material review

For a lab material workbench, record the candidate foundation revision and the product revision separately. Give the reviewer three unlabeled captures with the same geometry, light and scale. Ask them to identify porcelain, obsidian and glass from opacity, reflection width and edge thickness. Record ambiguity as a defect and repeat the comparison after repair. Owned material candidate

Have the reviewer change material and depth using the keyboard, interrupt a replay, inspect the stable reduced-motion state and check small text on the worst permitted backdrop. A failed control, illegible reading plane, altered identity or invented activity blocks the corresponding release claim. Report which of the source, Figma specimen, browser preview and production deployment they actually inspected, with each revision and the observed outcome. Material acceptance gate

See ChatGPT entrypoint and routing.

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.