build
Skill2 starsChanged 3 months agoMITView on GitHub
Assembles landing page sections. GUARD against AI-slop and hardcodes. Refuses to work without DESIGN-LOCK. Uses only tokens from tokens.css. Bounded by the section list in DESIGN-LOCK §8. Runs /typography pass on every saved section. Verifies references/approved-manifest.md coverage per section.
169 other projects use a version of this.
Adopted by
Most recently taken up by
- IntelRealSense/librealsensetheir own version, first seen Nov 16, 2026
- realsenseai/librealsensetheir own version, first seen Nov 16, 2026
- mannobeats/hyper-tastetheir own version, first seen Nov 16, 2026
- jayden-dang/skillstheir own version, first seen Nov 16, 2026
- colinc86/glosstheir own version, first seen Nov 16, 2026
- wald21x6-ops/builder-kittheir own version, first seen Nov 16, 2026
Used with
Projects with it also use backprop, finances and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
JuliusBrusseeSkillbackprop
Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.
Also in 4 projects that use this
GerardoRdz96Skillfinances
Use when Gera talks about his money — logging an expense ("I spent X on Y"), checking where he stands this pay-period, closing a period, planning debt payoff, onboarding his financial picture, or asking for budgeting/finance opinions. Servy's financial brain. Triggers — "I spent", "log this expense", "where am I this period", "close the period", "how's my budget", "debt plan", "should I pay off", "finances onboard", "/finances".
Also in 3 projects that use this
cpiprintSkillfavicon
Generate favicons from a source image
Also in 3 projects that use this
madeehahassanSkillGo-Live
Pre-launch checklist. Use before making any app public, sharing a link externally, or announcing a product launch. Adapts to Claude Code, claude.ai, and Cowork.
Also in 3 projects that use this
TrevokeSkilldefine
Use when a new feature request, bug report, or work request needs requirements defined before implementation
Also in 3 projects that use this
HAR5HA-7663Skillshape
Plan the UX and UI for a feature before writing code. Runs a structured discovery interview, then produces a design brief that guides implementation. Use during the planning phase to establish design direction, constraints, and strategy before any code is written.
Also in 6 projects that use this
Other versions169 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 169
- FalkorDB/FalkorDB★ 11ksame name
- realsenseai/librealsense★ 9.1ksame name
- IntelRealSense/librealsense★ 9.1ksame name
- microsoft/microsoft-ui-xaml★ 8.6ksame name
- NexaAI/nexa-sdk★ 8.5ksame name
- hathach/tinyusb★ 7.3ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- pytorch/TensorRT★ 3ksame name
159 more not listed
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 repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- animationSkill
- auditSkill
- blocksSkill
- briefSkill
- copy-analyzeSkill
- deploySkill
- design-lockSkill
- iconsSkill
- inboxSkill
- mediaSkill
- mobileSkill
- refsSkill
- tokensSkill
- typographySkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
26 rules. 0 are common, 13 are distinctive, and 13 are very specific to this project.
0
Common
Most of the 155 edited versions we read keep these.
13
Distinctive
This author's own choices. Worth a look.
13
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
After /tokens (tokens.css exists and is filled).
- Very specific: line 13
After /copy-analyze (brief/copy-analysis.md with recommended structure exists).
- Very specific: line 14
After /blocks (brief/blocks/*.md filled).
- Very specific: line 15
After /animation (brief/animation.md exists — motion classes drive CSS).
- Very specific: line 16
After /media and /icons (assets in site/media/).
- Distinctive: line 46
Start with hero? With the contact form?
- Very specific: line 55
Use the existing skeleton (.sec.sec-<name> class).
- Very specific: line 64
Only variables from tokens.css: Verify after every write — grep #[0-9a-f]{3,8}, \d+px (except border 1px), \d+ms.
- Very specific: line 65
Use flex / grid / calc() for positioning, no magic numbers.
- Distinctive: line 66
No inline styles in HTML.
- Very specific: line 70
Only via window.track() wrapper for analytics (from main.js).
- Very specific: line 71
Read CSS variables via getComputedStyle(document.documentElement).getPropertyValue().
- Distinctive: line 72
Never hardcode ms / colors.
- Distinctive: line 95
If a manifest item that must appear in this section is missing:
- Distinctive: line 97
Ask user: implement it now, or explicitly remove the item from the manifest with a decision-log entry.
- Very specific: line 99
If the item is present — mark the checkbox [x] in the manifest.
- Distinctive: line 107
If any check fails — do not save, return an error citing the line.
- Distinctive: line 122
One section — one responsibility: Do not mix hero + proof in one file.
- Very specific: line 124
Do not "fix" the brief during build: If copy is weak — go back to /copy-analyze.
- Distinctive: line 125
Nothing decorative: Every element has a function.
- Distinctive: line 126
Never silently drop a manifest item: If it can't fit, ask the user to remove it explicitly.
- Distinctive: line 130
Do not edit DESIGN-LOCK.md (explicit user override only).
- Very specific: line 131
Do not edit tokens.css (only /tokens).
- Distinctive: line 132
Do not add dependencies (jquery, tailwind, react — no).
- Distinctive: line 133
Do not "improve" existing sections when the task is a new section.
- Distinctive: line 134
Do not create "utility" pages without a request.
“Common” is measured: kept by at least 6 in 10 of the 155 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.
Files
/build
Main assembler. Everything before this is preparation. Here HTML/CSS/JS sections come into existence.
When to use
- After
/tokens(tokens.css exists and is filled). - After
/copy-analyze(brief/copy-analysis.md with recommended structure exists). - After
/blocks(brief/blocks/*.md filled). - After
/animation(brief/animation.md exists — motion classes drive CSS). - After
/mediaand/icons(assets in site/media/).
Requirements — HARD BLOCKING
Refuse to work if:
DESIGN-LOCK.mdis not fully LOCKED (any TBD remains).site/css/tokens.csshas any value =0/ empty / TBD comment.brief/copy-analysis.mdis missing (we don't know the structure).- The section requested is not in DESIGN-LOCK §8 "Section vocabulary".
references/approved-manifest.mdis missing (created by/refs; must exist even if empty).brief/animation.mdis missing (created by/animation).
Process
Step 1. Read sources of truth
DESIGN-LOCK.md— what is allowed, what is not.site/css/tokens.css— which variables are available.brief/copy-analysis.md— section structure.inbox/texts/*— copy for this section.brief/blocks/<block>.md— if this is an interactive block.brief/animation.md— motion classes to apply per element.site/media/_srcset-snippets.md— ready<img>tags.site/media/icons/_snippets.html— ready inline<svg>snippets.references/approved-manifest.md— required elements for this section.
Step 2. Agree on scope
Ask the user:
- One section at a time? Or a list at once?
- Start with hero? With the contact form? Something else?
Recommendation: hero first (LCP-critical), then form (main CTA), then the rest.
Step 3. Section assembly
For each section:
A. HTML in site/index.html
- Use the existing skeleton (
.sec.sec-<name>class). - Semantic tags:
<section>,<h1>/<h2>,<button>,<form>,<label>. alton every<img>.- ARIA where needed.
B. CSS in site/css/<section>.css
One CSS file per section. Add <link> to index.html.
Rules:
- Only variables from tokens.css. Verify after every write — grep
#[0-9a-f]{3,8},\d+px(except border 1px),\d+ms. - Use
flex/grid/calc()for positioning, no magic numbers. - No inline styles in HTML.
- No
!important(if needed — the problem is elsewhere).
C. JS in site/js/<section>.js (if interactive)
- Only via
window.track()wrapper for analytics (from main.js). - Read CSS variables via
getComputedStyle(document.documentElement).getPropertyValue(). - Never hardcode ms / colors.
D. Animation classes from brief/animation.md
For each element in the section, apply the animation class dictated by brief/animation.md:
- Card elements →
card-hoverclass per §4. - Headings → text animation class per §3.
- Sections → scroll reveal class per §2.
- The
--stagger-base-ms,--motion-multiplier, computed durations already exist in tokens.css (written by/tokensafter/animationran).
Step 4. Checks before saving
Step 4a. Hardcode grep-checks (auto):
- Any hex color (
#[0-9a-f],rgb(,rgba() except--c-overlayalpha? → block. - Any hardcoded size (
\d+pxnot in comments, except1pxfor border)? → block. - Any hardcoded duration (
\d+ms)? → block. - Any emoji in HTML? → block.
- More than 2 different font-weights per section? → block.
- Section uses a radius other than
var(--radius)? → block.
Step 4b. Typography pass — call /typography on the saved HTML fragment. It walks text nodes, ties short words with , and prevents orphans/dashes at line end. This runs silently as part of /build — see typography SKILL.md for the rule set and the canonical short-word list.
Step 4c. Manifest coverage — read references/approved-manifest.md. For every item whose section-scope matches the current section (e.g. [ ] motif: horizontal thin rule between sections, [ ] icon:privacy → footer/trust, [ ] animation:card-hover:lift) — verify the item is present in the generated HTML/CSS.
If a manifest item that must appear in this section is missing:
- Do not save. Report which item is missing and where it is expected.
- Ask user: implement it now, or explicitly remove the item from the manifest with a decision-log entry.
If the item is present — mark the checkbox [x] in the manifest.
Step 4d. Anti-AI-slop checks:
- Section not in DESIGN-LOCK §8? → block.
- More than one gradient? → block.
- Center-align on a section if it's > 50% of the page? → warning.
- More than one icon style? → block.
If any check fails — do not save, return an error citing the line.
Step 5. Save + preview
Save HTML + CSS + (JS if any).
Suggest: python -m http.server 8000 — view in the browser.
Step 6. Iterate
- User views.
- Feedback → edits (without changing DESIGN-LOCK).
- Edits only within this section's scope — no "improve the neighbor".
Rules of behavior
- One section — one responsibility. Do not mix hero + proof in one file.
- Do not invent components. Button =
<button class="btn">. Not<div role="button">. - Do not "fix" the brief during build. If copy is weak — go back to
/copy-analyze. - Nothing decorative. Every element has a function.
- Never silently drop a manifest item. If it can't fit, ask the user to remove it explicitly.
What NOT to do
- Do not edit DESIGN-LOCK.md (explicit user override only).
- Do not edit tokens.css (only
/tokens). - Do not add dependencies (jquery, tailwind, react — no).
- Do not "improve" existing sections when the task is a new section.
- Do not create "utility" pages without a request.
Next
/mobile— mobile adaptation./audit— pre-ship check.
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
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.

