agentleFS
Sign inStart free
alanvaa06alanvaa06/award-craft/skills/elevate/SKILL.md

elevate

Skill1 starsChanged 3 months agoMITView on GitHub

Elevate an existing landing page toward Awwwards level — read the project, gap-analysis against the anatomy checklist, prioritized plan gate, apply approved items, mandatory verify. Use when the user wants an existing page improved ("/award-craft:elevate [path]"). Not for building from scratch (use craft).

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. BenjaminG/ai-skills★ 4same name
    2. catcatcatstudio/cat-skills★ 3same name
    3. EvolutionUnleashed/elevate★ 3same name
    4. welshofer/elevate★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Never silently change slugs, nav labels, form field names, or legal copy.

    line 46
  2. Distinctive:

    If the approved items require new assets, the same credit ceiling rule applies — propose the ceiling with the elevation plan and stop …

    line 51

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

Elevate — orchestrator

0. Preflight — identical to craft (see ${CLAUDE_PLUGIN_ROOT}/skills/craft/SKILL.md §0).

1. Read the project

Stack (confirm Next.js — if not, report that v0.1 only supports the fixed stack and stop); sections; existing animations (GSAP? Lenis? CSS?); existing DESIGN.md/PRODUCT.md or brand source (same resolution as craft §1). Detect the mode: Preserve (modernize without breaking identity) or Overhaul (new visuals, preserve content). State it in the gap-analysis.

2. Gap-analysis

Score the current page against the Awwwards anatomy checklist (${CLAUDE_PLUGIN_ROOT}/skills/direction/references/awwwards-rubric.md) + run impeccable's audit + its detector once over the target: node <impeccable-base>/scripts/detect.mjs --json <target> (base dir resolved in preflight). Consume its findings instead of re-deriving them; anything it already reports is a fix item, not a new observation. Output: what it has / what is missing / what is wrong (with file:line refs). Also score the copy: hero tests, arc coherence, banned language, micro-copy (see ${CLAUDE_PLUGIN_ROOT}/skills/direction/references/copywriting.md). Copy rewrites are a modernization lever — place them with typography (highest lift, lowest risk).

3. Elevation plan → GATE

Prioritized items (impact vs effort), each: what changes, which recipe applies, expected checklist deltas. ═══ STOP: human picks items ═══ Overhaul mode only: offer the comp round with the plan — three rendered compositions of the new first viewport (~3 credits, priced with get_cost), so the human approves a composition instead of a description. Follow ${CLAUDE_PLUGIN_ROOT}/skills/direction/references/comps.md; elevate never invokes direction, so run it here. Preserve mode does not comp: the incumbent composition is the reference, and rendering alternatives invites a redesign nobody asked for.

4. Apply approved items using ${CLAUDE_PLUGIN_ROOT}/skills/build-recipes (same rules).

Apply modernization levers in this order (highest lift / lowest risk first): typography refresh + copy rewrites (headline/CTA/banned language — same tier: highest lift, lowest risk) → spacing & rhythm → color recalibration → motion layer → hero and key-section recomposition → full block replacement (last resort). Never silently change slugs, nav labels, form field names, or legal copy. Token changes land in DESIGN.md's YAML frontmatter (normative) and, when they touch motion/shadows/breakpoints, in .impeccable/design.json — see the "On approval" section of ${CLAUDE_PLUGIN_ROOT}/skills/direction/SKILL.md. Never silently overwrite a DESIGN.md written by impeccable. If the approved items require new assets, the same credit ceiling rule applies — propose the ceiling with the elevation plan and stop before exceeding it. If any of them is a VIDEO asset, price the tier menu with get_cost and present it with the elevation plan exactly as Pass-1 item 9 of ${CLAUDE_PLUGIN_ROOT}/skills/direction/SKILL.md prescribes; elevate never invokes direction, so the menu has to be run here or the tier gets picked by an agent instead of the human. (Lever order distilled from taste-skill, MIT.)

5. Verify — invoke skill verify. Mandatory.

6. Report: antes/después — checklist score before vs after, screenshots

side by side, remaining gaps for a future pass.

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