agentleFS
moronireismoronireis/agent-system-partners/.claude/skills/pipeline-luxo/SKILL.md

pipeline-luxo

Skill0 starsChanged 2 months agoMITView on GitHub

Luxury/premium overlay for design pipelines — inserts dsg-typography between direction and specs, loads luxury grammar and DNA references, and raises the dsg-critic bar with luxury calibration (restraint, codes, confidence). Activate for luxury-tier projects; not a standalone pipeline on its own.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Not a separate chain — an overlay that modifies pipeline-brand (or a direct dsg-director → dsg-ui/dsg-motion → dsg-critic flow) when the …

    line 8
  2. Distinctive:

    Default premium-but-not-luxury work (most SaaS, most B2B) — the base pipeline's principles already cover restrained, high-quality design.

    line 17
  3. Very specific:

    If brain/design-library/luxury/ has no DNA report for the project's vertical yet, dsg-director or dsg-typography should flag the gap rather …

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Pipeline: Luxo (Luxury Overlay)

Not a separate chain — an overlay that modifies pipeline-brand (or a direct dsg-director → dsg-ui/dsg-motion → dsg-critic flow) when the project pack is luxury/premium-tier. Activate by naming it alongside the base pipeline in intent, or by the director flagging the pack as luxury-tier before delegating.

When to use

  • The project pack's positioning is explicitly luxury/premium (fashion, hospitality, jewelry, high-ticket professional services) — check brand.md's positioning section.
  • The user asks for work to be judged against luxury standards, not general premium-web standards.

When NOT to use

  • Default premium-but-not-luxury work (most SaaS, most B2B) — the base pipeline's principles already cover restrained, high-quality design. Adding luxury calibration here produces pretentious output that disconnects from the audience.

What it changes

  1. Insert dsg-typography between dsg-director and dsg-ui in the chain. The director's type intent gets a full deep-typography pass (High-Low pairing, OpenType audit, variable axes, kinetic brief) before dsg-ui ever touches a token.
  2. Load extra references for every agent in the chain: brain/design-library/principles/luxury-grammar.md and brain/design-library/luxury/ (brand DNA reports). dsg-director's brief and dsg-critic's verdict both cite these explicitly, not just the general principles set.
  3. Raise the dsg-critic bar with three luxury-calibration lenses, scored in addition to the standard eight dimensions:
    • Restraint — zero tolerance for SaaS tells (border-radius on interactive elements, gradient CTAs, bounce/spring easing, pricing-tier cards, badge UI). Their presence is an automatic REVISE regardless of how polished everything else is.
    • Codes — presence of the luxury tells: serif in the type hierarchy, uppercase tracked micro-navigation, photography/imagery dominant over UI chrome, editorial (non-grid-uniform) asymmetry, negative space treated as precious rather than default.
    • Confidence — the work doesn't oversell: no urgency hacks, no exclamation-driven copy framing, no "explaining" the luxury — it just is. Quiet confidence reads as more expensive than loud reassurance.

Notes

  • This overlay does not change file paths or ownership — outputs still land where the base pipeline puts them (brief-design-<slug>.md, spec-ui-<slug>.md, design-<slug>.md), just with the extra step and extra scoring lenses applied.
  • If brain/design-library/luxury/ has no DNA report for the project's vertical yet, dsg-director or dsg-typography should flag the gap rather than proceeding on assumption — luxury judgment without a reference set is just opinion.

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.