Skip to content
Agentmart
Submit a tool

starlight-web-production

Direct, build, redesign, or audit high-value websites, landing pages, product UI, design systems, and web releases for FrankX, Starlight, Arcanea, GenCreator…

Skill by frankxai

IndexedMIT★ 11
Write a review

Chalk Labs

Need help deploying starlight-web-production?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/frankxai-starlight-web-production

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Direct, build, redesign, or audit high-value websites, landing pages, product UI, design systems, and web releases for FrankX, Starlight, Arcanea, GenCreator, Agentic Income, Reality Architect, or the related portfolio. Use for web work where reference research, original art direction, component and motion selection, responsive implementation, and production proof matter; do not use for backend-only changes.

Use cases: design, frontend, backend, security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/starlight-web-production

What's inside

Skill name
starlight-web-production
Description
Direct, build, redesign, or audit high-value websites, landing pages, product UI, design systems, and web releases for FrankX, Starlight, Arcanea, GenCreator, Agentic Income, Reality Architect, or the related portfolio. Use for web work where reference research, original art direction, component and motion selection, responsive implementation, and production proof matter; do not use for backend-only changes.
License
MIT
Instructions
59 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • openai.yaml · agents/
  • technology-lanes.md · references/

SKILL.md (first lines)

# Starlight Web Production

Treat distinctive quality as a release property. A framework, component library, screenshot, or animation technique is evidence or material—not the design direction.

## Authority

Read the owning repository's constitution, `AGENTS.md`, `taste.md`, `design.md` or `DESIGN.md`, tokens, components, analytics, and prior decision receipts. The order of authority is:

1. product truth and brand constitution;
2. repository-local design contract;
3. approved taste/reference records;
4. a locked primary reference and bounded secondary references;
5. live research;
6. model defaults.

Never let Aceternity, GSAP, Refero, shadcn, a template, or a trend become the brand.

## Operating sequence

1. Capture the current desktop and mobile truth. For greenfield work, capture the host context and gather real product states, proof, media, and copy.
2. State one recipient, one job, one promise, one action, one signature proof, and the intended feeling/understanding.
3. Research before composition. Prefer Refero styles/screens/flows when available; otherwise use current public, attributable sources. Record URL, owner, date, rights, observed principle, bounded use, and anti-reference.
4. For consequential visual work, produce exactly three materially different directions using the same real content. Resolve composition, type, imagery, interaction, motion posture, feasibility, and mobile behavior.
5. Record the selected direction. When the user explicitly delegates direction, select the highest-scoring option and record why; otherwise obtain the decision before implementation.
6. Establish static hierarchy, copy, proof, tokens, responsive behavior, and conversion path before motion.
7. Choose the smallest technology lane that expresses the selected direction. Read [technology-lanes.md](references/technology-lanes.md) before adding UI or motion dependencies.
8. Implement against the existing framework and design system. Do not rewrite a stack merely to reach a preferred library.
9. Render and inspect desktop, mobile, interactive, loading/error, and reduced-motion states. Test keyboard order, focus, contrast, reflow, links, claims, privacy, analytics, performance, and failures proportional to the surface.
10. Record commit, checks, preview, production URL, post-deploy inspection, rollback, and the preference receipt.

## Reference lock

Before substantial implementation, record:

```text
Primary foundation:
Preserve:
Secondary reference -> one bounded job:
Media strategy and rights:
Component lane:
Motion lane and named job:
Reject:
Token commitments:
Decision owner:
```

One source owns the foundation. Secondary sources never get averaged into generic premium minimalism.

## Release gates

Block promotion when the surface lacks a current visual capture, real product proof, an explicit reference lock, mobile composition, reduced-motion behavior, accessible interaction, or a production rollback. Copy-paste components must be restyled into owned tokens and inspected for dependencies, semantics, responsiveness, performance, and license boundaries.

Motion must orient, explain, confirm, reveal causality, or create one brand memory. A marketing surface normally earns at most one signature sequence. Do not animate multiple libraries against the same DOM property.

## Output

For builds, return the experience thesis, selected direction, preview, changed artifacts, visual and engineering evidence, verifier verdict, production proof, and rollback. For audits, return current captures, the first three release blockers, the governing rule, the smallest corrective release, and evidence limits.

From frankxai/Starlight-Intelligence-System, MIT.

More from frankxai/Starlight-Intelligence-System

Signals

Stars
11
Forks
3
Open issues
61
Last commit (this folder)
Aug 30, 2026 (2 months ago)
Last release
Jun 10, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from frankxai

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get starlight-web-production running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying starlight-web-production?

CallGet help
Cite this page

starlight-web-production skill. Agent Mart. https://agentmart.dev/skills/frankxai-starlight-web-production (last updated 2026-10-24)