Files
pbakaus_impeccable/scripts/lib/utils.js
T
e7e923c4ef Skill + craft cleanup, detector hardening, native subagent pipeline (#152)
* skill: drop quality tiers, keep the real brand-craft guardrails

Codex's craft/brand pass introduced fast/ship/showpiece "quality bars"
plus brand-specific build gates, asset ledgers, sub-agent review, and
self-graded fallback labels. In practice those tiers became escape
hatches rather than craft pressure: the final output should always be
10/10, and the real decision points are splashiness and maximalism, not
quality.

Removed:
- All quality-bar / showpiece / fast / ship framing in shape.md and craft.md
- Standalone Brand Direction (#4) and Asset Requirements (#10) sections
  in shape's brief; renumbered back to 1-10
- The Brand hard rules section in brand.md (folded its real prohibitions
  into the existing Imagery and Brand bans sections)
- Brand-specific build-gate item, mock-fidelity bullet, production-bar
  bullet, present-step bullet in craft.md
- Asset ledger ceremony in craft Step 4
- Review-only sub-agents and "self-reviewed fallback, not independently
  validated" machinery in craft.md and polish.md
- The For brand surfaces, assess hard failures subsection in polish.md
  and the brand checklist row
- tests/brand-showpiece-reference.test.mjs (and its package.json wiring)

Kept (the real nuggets):
- Asset-substitution prohibition: image-led briefs ship real/generated
  assets or canvas/SVG/WebGL, not generic CSS panels, cards, bullets,
  or copy
- Repeated tiny uppercase tracked kicker labels as a brand ban
- Detector/QA output is defect evidence only, never proof of quality
- "What visual assets are real content here?" discovery question
- Inspect each major section individually for brand and long-form work
- repeated-section-kickers detection rule + fixture
- CLI improvements (JSON to stdout, -json/-fast aliases, severity field)
- critique.md: npx impeccable detect --json fix

Harness output dirs refreshed via bun run build. Full test suite (186)
passes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* skill: strip gate ceremony; require shape pause; allow compact briefs

The setup gate table and IMPECCABLE_PREFLIGHT banner pushed every
craft run through ritual restatement (PRODUCT.md → original prompt
→ round 1 → round 2 → 70-line "confirmed brief" → critique → summary,
all saying the same thing). Replaced with imperative prose that still
demands the same work but skips the user-facing telemetry.

Specifically:

SKILL.md
- Drop the Setup gate table and IMPECCABLE_PREFLIGHT banner.
- Keep the imperative steps explicitly: load context, identify register
  and load brand.md or product.md, AND load the matching command
  reference (craft.md / shape.md / etc.) when a sub-command is invoked.
  The command-reference step is non-negotiable; without craft.md loaded
  the agent skips the shape-and-confirm pause.

craft.md
- Drop the Build Gate / Craft Contract formal sections; replace with
  one paragraph stating prerequisites.
- Step 1 explicitly requires ending the response after presenting the
  shape output; the user must confirm before any code lands. Allows a
  compact 3-5 bullet brief when the prompt + PRODUCT.md already pin
  direction (full 10-section structure reserved for genuinely
  ambiguous tasks).
- Step 3 image gate skips silently when image generation isn't
  natively available; no user-facing announcement.
- Step 6 explicitly legitimizes "first pass clean, shipping" as a
  valid endpoint and bans inventing fake defects to demonstrate
  iteration.

shape.md
- Cap discovery at 1 round by default; second round only when first
  leaves material gaps.
- Adds an "assert-then-confirm, not menu-with-escape" rule: when
  PRODUCT.md and the prompt make one option obvious, name it and ask
  for confirm or override instead of enumerating "Restrained /
  Committed / Or something else?" as a real choice.
- Phase 2 brief has two forms now: compact (default for clear briefs)
  and full structured (genuinely ambiguous). Open Questions can't
  double as leading-with-Recommend; if you'd write "Recommend: X",
  decide X.
- Image gate same as craft.md.

Validated end-to-end with a Haiku skill-on observability run: agent
loads craft.md plus the brief's recommended implementation refs,
pauses for one productive question (accent color, trace fidelity,
CTA), and ships an artifact with zero side-tab violations vs. the
original v1 baseline. Cost trades up modestly for that quality.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* craft.md Step 6: Reading the screenshot is the inspection, not taking it

A v4 eval run took 4 targeted screenshots (hero, mobile, tablet,
query-section) and then never Read any of them back. The agent treated
browser_screenshot itself as "I inspected" and shipped without the
multimodal feedback loop ever closing. Detector caught the resulting
slop (5+ side-tab violations) on adjacent runs that did the same thing.

Step 6 now spells out the pattern explicitly: take the screenshot,
then Read the resulting PNG so its image content enters the
conversation as multimodal input, then critique what you actually see
in the image. With a check: "if your critique could have been written
without looking at the image, you didn't look at the image."

Validated with v5b: agent took 6 screenshots, Read all 6 back, and
shipped with zero detector findings (vs the previous greenfield runs
that hit 1-12 findings each).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* craft + brand: framework foundation, build-pipeline respect, image verification

Three closely-linked additions surfaced by an eval-harness session
investigating why the agent always shipped flat single-file HTML and
zero imagery on greenfield brand briefs.

1. craft.md gains a new Step 0 "Project Foundation" before Shape.
   Detects existing framework / component library / icon set and
   uses what's there. Greenfield: ask the user via AskUserQuestion
   with sensible defaults framed by the brief (Astro for content/
   brand sites, SvelteKit/Next/Nuxt for app surfaces, single
   index.html only for one-shot demos). Skipping the framework
   decision and writing flat HTML "to satisfy the spec" produces
   work that reads as a 2018 prototype regardless of visual
   quality.

2. craft.md Step 5 production bar gains two bullets:
   - Respect the build pipeline. Edit source files and run the
     project's `npm run build`; do not write to build/ / dist/ /
     .next/ directly with cat/heredoc/Bash redirects. Bypassing
     the pipeline skips asset hashing, image optimization, code
     splitting, and CSS extraction.
   - Verify external image URLs before referencing them. Use an
     image-search MCP, web-fetch tool, or browser if available;
     guessed photo IDs ship as broken-image placeholders.

3. brand.md "Imagery" section:
   - Generalizes the Unsplash URL guidance to "verify URLs
     before referencing them" with a hierarchy: image-search MCP
     > web-fetch > confidence-restricted manual selection >
     fewer photos.
   - Tightens the tech/dev-tool exception. Old line "zero imagery
     can be correct" gave models a permission slip. New framing
     keeps the underlying truth (typography + code + diagrams
     primarily carry voice) but raises the floor: imagery still
     earns its place when it serves the brief, and skipping it
     requires naming the typographic/diagrammatic move that's
     carrying the visual weight instead. "Zero imagery is the
     failure mode of laziness, not restraint."

Eval-harness corpus that prompted this: 19/19 brand landing tasks
shipped 0 images each, including ones where Opus had taste enough
to break the dev-tool color default lane. The skill needs to teach
both halves of the decision; the harness shouldn't have to nudge.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* detector: body-text-viewport-edge rule + OKLCH/var-resolution + anchor-inherit FP fixes

New rule: body-text-viewport-edge flags body paragraphs that render flush
against the left/right viewport edges (no container padding). Tested via
the new tests/fixtures/antipatterns/body-text-viewport-edge.html fixture
(3 flag cases, 5 pass cases) and the test in detect-antipatterns-browser.

False-positive class fixes — all jsdom-mode only (real browsers resolve
the cascade correctly so these gates stay inert there). Five related
gaps that compounded into ~14× spurious contrast findings on Tailwind v4
pages with OKLCH color tokens:

  • OKLCH parser. jsdom returns the literal "oklch(...)" string from
    getComputedStyle; the detector now converts to sRGB via Björn
    Ottosson's matrices. Handles Tailwind v4's compact minified form
    "oklch(21.5%.02 50)" (no space after %).
  • var() resolution. resolveBackground + checkElementColors now
    accept the existing customPropMap and parse `var(--color-paper)`
    etc. as proper RGB via the new parseColorResolved helper.
  • bg-color before bg-image. The old order bailed on any gradient
    ancestor before checking for a solid background-color underneath,
    causing the body's decorative paper-grain gradient to be measured
    against instead of the page's actual `bg-paper` cream.
  • body/html-level gradient → white fallback. When the only opaque
    ancestor we can read is body/html with a gradient overlay (and
    jsdom can't decompose `background: var(--paper) gradient` to
    extract the solid color), return white instead of falling through
    to resolveGradientStops — which was picking up paper-grain noise
    colors and using them as the bg.
  • Anchor-inherit workaround for jsdom :link UA specificity.
    Tailwind v4's preflight declares `a { color: inherit }` (0,0,1).
    jsdom's UA stylesheet has `:link { color: blue }` at (0,1,1) and
    wins the cascade. Real Chrome wraps :link in :where() (0,0,0) so
    the page rule wins. When the page declares the inherit rule AND
    we see jsdom's default `rgb(0,0,238)` on an anchor, walk to the
    nearest non-anchor ancestor and use its color.
  • Alpha-fallback safety gate. When text has alpha<1 AND we couldn't
    find an opaque ancestor (effectiveBg null), skip the contrast
    finding. Covers any remaining FP class the deeper fixes miss.

Verified end-to-end against an Opus iter-1 artifact on Tailwind v4 with
14 cream/cream FPs + 2 blue-link UA FPs before; 0 findings after, while
the color.html fixture's 12 real low-contrast cases continue to flag
(verified via direct detectHtml calls).

cli/engine/detect-antipatterns-browser.js is the generated browser
distribution — regenerated from .mjs via scripts/build-browser-detector.js
(no manual edits to the generated file).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* craft.md: tighten verbose passages, de-codex Step 6, cut redundancies

Cumulative reduction: 218 → 155 lines (-29%).

Step 0: drop the "Why this matters" paragraph at the end. The body of
Step 0 already makes the framework-pick point; the paragraph just
re-explains it with extra rhetoric.

Step 1: replace the 4-sentence "you must end your response" block with a
single line. The original said the same thing three different ways.

Step 3: trim the conditional / defensive scaffolding (Purpose subsection,
"do not skip because the eventual UI is semantic..." paragraph,
duplicated approval-loop guidance). Mock fidelity inventory preserved.

Step 4: drop the "keep UI text semantic" sentence; it duplicates Step 5's
"Semantic first" rule. The rasterized-vs-semantic decision rule stays.

Step 5: tighten each production-bar bullet to bold-lead + specifics
format. All 15 rules preserved (real content, mock ingredients, semantic
first, spacing/alignment, typography, state coverage, interaction quality,
icon set, build pipeline, image URL verification, optimized imagery,
premium motion, maintainability, technical cleanliness, ask-when-uncertain).

Step 6: rewrite around "look at what you built like a designer would —
your eyes are whatever the harness gives you." Drops Codex-specific
"In Codex, use browser-use" bias. Drops the verbose 3-step Read pattern
(condensed to one sentence). Drops the 1-8 numbered checklist (replaced
by a tight paragraph). Keeps the load-bearing rules: read the PNG,
don't fabricate iteration, mock fidelity reference, exit bar = studio
defensibility.

Step 7: drop the closing "Iterate based on feedback. Good design is
rarely right on the first pass" preachy filler.

All em-dashes converted to semicolons / colons / periods to satisfy
the skill prose validator.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* build: native subagent pipeline + Codex-only asset producer

Adds an agent cross-compile pipeline alongside the existing skill
pipeline. Sources live at skill/agents/*.md; providers that declare
agentFormat (codex-toml, claude-md) emit native subagent files. An
optional providers: <list> field on an agent gates which harnesses
get a copy; default (no field) ships everywhere.

The impeccable-asset-producer agent is opt-in to Codex only. It's
useful for Codex's native image generation path and is untested
elsewhere; Claude has no native image gen anyway.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* brand: inverse-test + cultural-symbol palette guardrail

Two additions to the brand register reference:

- Inverse slop test: describe the page the way a competitor would
  describe theirs. If that sentence fits the modal landing page in
  the category, restart.
- Palette guardrail: when a cultural-symbol palette is the obvious
  pull, reach past it. Let cultural reading come from typography,
  imagery, and copy.

Harness mirrors regenerated; some also catch up to the image-
verification paragraph from e3ad2ef that hadn't been re-synced.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* PRODUCT.md: widen audience beyond developers

Designers, product managers, and engineers all use AI coding tools
and want better design output. Keeping the audience narrow to
"frontend and full-stack developers" understates who the skill is
actually for. Also retitles "developer" to "user/builder" in the
purpose statement.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* site + build: bump rule count to 29, strip changelog from detector check

Two changes:
- site/pages/index.astro: three live mentions of "28 rules / checks"
  bumped to 29 after the body-text-viewport-edge rule landed in
  b9bf496.
- scripts/build.js: the detection-count validator was reading the
  unstripped content, so historical counts inside changelog entries
  (e.g. "28 rules" from an older release note) were flagging against
  the current detector total. The command-count check already strips
  the changelog ul; the detection check now does the same.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test: align hero-eyebrow-chip fixture with relaxed rule gates

b9bf496 intentionally relaxed two gates in checkHeroEyebrow:
- removed the heading-size ≥ 48px anchor (modern hero h1s use
  clamp/vw/var that jsdom can't resolve)
- raised the eyebrow text ceiling from 30 to 60 chars

Two fixture cases that satisfied the negative side of the old gates
now match the rule:

- "Body-Sized Heading Below Eyebrow" — 24px h1 with tracked-caps
  label above. Per the rule's stated intent ("a tiny tan label
  directly above any h1 is the antipattern regardless of how big
  the h1 ends up"), this is a flag.
- "Long Uppercase Sentence Above Hero" — 46-char tracked-caps label
  is under the new 60-char ceiling, so still eyebrow-shaped.

Both cases moved from the should-pass column to should-flag, with
case descriptions rewritten to explain the gate they exercise.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Paul Bakaus <paulbakaus@pauls-mbp-3.lan>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-12 23:11:18 -07:00

714 lines
24 KiB
JavaScript
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
import fs from 'fs';
import path from 'path';
// Per-project artifacts live inside `scripts/` of an installed skill but
// belong to the consuming project, not the distributable skill. The build
// excludes them from dist, and the harness-sync step preserves them across
// the rm+recopy so local state isn't destroyed on every rebuild.
// - config.json: legacy live-mode inject target list for existing projects.
// New installs write project config at .impeccable/live/config.json instead.
export const PER_PROJECT_SCRIPT_ARTIFACTS = new Set(['config.json']);
// Walk the harness-dir skill tree and return any per-project script
// artifacts found, ready for restoration after a full sync rm+recopy.
// Returns [{ relPath, content: Buffer }], where relPath is relative to
// the passed-in rootDir (typically `<configDir>/skills`).
export function stashPerProjectArtifacts(rootDir) {
if (!fs.existsSync(rootDir)) return [];
const out = [];
const walk = (dir) => {
for (const entry of fs.readdirSync(dir, { withFileTypes: true })) {
const p = path.join(dir, entry.name);
if (entry.isDirectory()) { walk(p); continue; }
// Only preserve files inside a skill's scripts/ directory.
if (path.basename(path.dirname(p)) !== 'scripts') continue;
if (PER_PROJECT_SCRIPT_ARTIFACTS.has(entry.name)) {
out.push({ relPath: path.relative(rootDir, p), content: fs.readFileSync(p) });
}
}
};
walk(rootDir);
return out;
}
export function restorePerProjectArtifacts(rootDir, stashed) {
for (const { relPath, content } of stashed) {
const target = path.join(rootDir, relPath);
fs.mkdirSync(path.dirname(target), { recursive: true });
fs.writeFileSync(target, content);
}
}
/**
* Parse frontmatter from markdown content
* Returns { frontmatter: object, body: string }
*/
export function parseFrontmatter(content) {
const frontmatterRegex = /^---\r?\n([\s\S]*?)\r?\n---\r?\n([\s\S]*)$/;
const match = content.match(frontmatterRegex);
if (!match) {
return { frontmatter: {}, body: content };
}
const [, frontmatterText, body] = match;
const frontmatter = {};
// Simple YAML parser (handles basic key-value and arrays)
const lines = frontmatterText.split(/\r?\n/);
let currentKey = null;
let currentArray = null;
for (const line of lines) {
if (!line.trim()) continue;
// Calculate indent level
const leadingSpaces = line.length - line.trimStart().length;
const trimmed = line.trim();
// Array item at level 2 (nested under a key)
if (trimmed.startsWith('- ') && leadingSpaces >= 2) {
if (currentArray) {
if (trimmed.startsWith('- name:')) {
// New object in array
const obj = {};
obj.name = trimmed.slice(7).trim();
currentArray.push(obj);
} else {
// Simple string item in array
currentArray.push(trimmed.slice(2));
}
}
continue;
}
// Property of array object (indented further)
if (leadingSpaces >= 4 && currentArray && currentArray.length > 0) {
const colonIndex = trimmed.indexOf(':');
if (colonIndex > 0) {
const key = trimmed.slice(0, colonIndex).trim();
const value = trimmed.slice(colonIndex + 1).trim();
const lastObj = currentArray[currentArray.length - 1];
lastObj[key] = value === 'true' ? true : value === 'false' ? false : value;
}
continue;
}
// Top-level key-value pair
if (leadingSpaces === 0) {
const colonIndex = trimmed.indexOf(':');
if (colonIndex > 0) {
const key = trimmed.slice(0, colonIndex).trim();
const value = trimmed.slice(colonIndex + 1).trim();
const isQuoted = /^(".*"|'.*')$/.test(value);
const unquotedValue = isQuoted ? value.slice(1, -1) : value;
const shouldCoerceBoolean =
key === 'user-invocable' || key === 'user-invokable' || !isQuoted;
if (value) {
frontmatter[key] = shouldCoerceBoolean
? unquotedValue === 'true'
? true
: unquotedValue === 'false'
? false
: unquotedValue
: unquotedValue;
currentKey = key;
currentArray = null;
} else {
// Start of array
currentKey = key;
currentArray = [];
frontmatter[key] = currentArray;
}
}
}
}
return { frontmatter, body: body.trim() };
}
/**
* Recursively read all .md files from a directory
*/
export function readFilesRecursive(dir, fileList = []) {
if (!fs.existsSync(dir)) {
return fileList;
}
const files = fs.readdirSync(dir);
for (const file of files) {
const filePath = path.join(dir, file);
const stat = fs.statSync(filePath);
if (stat.isDirectory()) {
readFilesRecursive(filePath, fileList);
} else if (file.endsWith('.md')) {
fileList.push(filePath);
}
}
return fileList;
}
/**
* Read and parse the impeccable skill source.
* After v3.0 the repo holds exactly one user-invocable skill, flat at skill/.
* Returns { skills: [oneEntry] } so downstream array-shaped consumers stay happy.
*/
export function readSourceFiles(rootDir) {
const skillDir = path.join(rootDir, 'skill');
const skills = [];
const skillMdPath = path.join(skillDir, 'SKILL.md');
if (!fs.existsSync(skillMdPath)) {
return { skills };
}
const content = fs.readFileSync(skillMdPath, 'utf-8');
const { frontmatter, body } = parseFrontmatter(content);
const references = [];
const referenceDir = path.join(skillDir, 'reference');
if (fs.existsSync(referenceDir)) {
const refFiles = fs.readdirSync(referenceDir).filter(f => f.endsWith('.md'));
for (const refFile of refFiles) {
const refPath = path.join(referenceDir, refFile);
references.push({
name: path.basename(refFile, '.md'),
content: fs.readFileSync(refPath, 'utf-8'),
filePath: refPath
});
}
}
// PER_PROJECT_SCRIPT_ARTIFACTS (defined at module top) are excluded from
// the distributable skill so the build never bundles one project's state
// into another's.
const scripts = [];
const scriptsDir = path.join(skillDir, 'scripts');
if (fs.existsSync(scriptsDir)) {
const scriptFiles = fs.readdirSync(scriptsDir).filter(f => {
if (PER_PROJECT_SCRIPT_ARTIFACTS.has(f)) return false;
return fs.statSync(path.join(scriptsDir, f)).isFile();
});
for (const scriptFile of scriptFiles) {
const scriptPath = path.join(scriptsDir, scriptFile);
scripts.push({
name: scriptFile,
content: fs.readFileSync(scriptPath, 'utf-8'),
filePath: scriptPath
});
}
}
const agents = [];
const agentsDir = path.join(skillDir, 'agents');
if (fs.existsSync(agentsDir)) {
const agentFiles = fs.readdirSync(agentsDir).filter(f => f.endsWith('.md'));
for (const agentFile of agentFiles) {
const agentPath = path.join(agentsDir, agentFile);
const agentContent = fs.readFileSync(agentPath, 'utf-8');
const { frontmatter: agentFrontmatter, body: agentBody } = parseFrontmatter(agentContent);
const name = agentFrontmatter.name || path.basename(agentFile, '.md');
const providersRaw = agentFrontmatter.providers;
let providers = null;
if (Array.isArray(providersRaw)) {
providers = providersRaw.map(p => String(p).trim()).filter(Boolean);
} else if (typeof providersRaw === 'string' && providersRaw.trim()) {
providers = providersRaw.split(',').map(p => p.trim()).filter(Boolean);
}
agents.push({
name,
codexName: agentFrontmatter['codex-name'] || name.replace(/-/g, '_'),
claudeName: agentFrontmatter['claude-name'] || name,
description: agentFrontmatter.description || '',
tools: agentFrontmatter.tools || '',
model: agentFrontmatter.model || '',
effort: agentFrontmatter.effort || '',
maxTurns: agentFrontmatter['max-turns'] ? Number(agentFrontmatter['max-turns']) : '',
nicknameCandidates: agentFrontmatter['nickname-candidates'] || [],
providers,
body: agentBody,
filePath: agentPath,
});
}
}
skills.push({
name: frontmatter.name || 'impeccable',
description: frontmatter.description || '',
license: frontmatter.license || '',
compatibility: frontmatter.compatibility || '',
metadata: frontmatter.metadata || null,
allowedTools: frontmatter['allowed-tools'] || '',
userInvocable: frontmatter['user-invocable'] === true || frontmatter['user-invocable'] === 'true',
argumentHint: frontmatter['argument-hint'] || '',
context: frontmatter.context || null,
body,
filePath: skillMdPath,
references,
scripts,
agents
});
return { skills };
}
/**
* Ensure directory exists, create if needed
*/
export function ensureDir(dirPath) {
if (!fs.existsSync(dirPath)) {
fs.mkdirSync(dirPath, { recursive: true });
}
}
/**
* Clean directory (remove all contents)
*/
export function cleanDir(dirPath) {
if (fs.existsSync(dirPath)) {
fs.rmSync(dirPath, { recursive: true, force: true });
}
}
/**
* Write file with automatic directory creation
*/
export function writeFile(filePath, content) {
const dir = path.dirname(filePath);
ensureDir(dir);
fs.writeFileSync(filePath, content, 'utf-8');
}
/**
* Extract DO/DON'T patterns from a skill markdown file, grouped by section
* (h3 `### ` headings). Recognizes both formats:
* - Markdown bullet form: `**DO**: …` / `**DON'T**: …`
* - Prose form: `DO …` / `DO NOT …`
*
* Defaults to the main impeccable SKILL.md but accepts any relative path so
* rules in `cli/engine/detect-antipatterns.mjs` can anchor to register-specific
* reference files (e.g. `reference/editorial.md`) via an optional `skillFile`
* field. Callers that don't pass `relativePath` get the legacy behavior.
*
* Returns { patterns: [...], antipatterns: [...] }
*/
// Curated short-list for the homepage Antidote section. Intentionally
// hand-written (not auto-extracted) so the copy stays tight and
// editorial. The long-form catalog lives on /slop — this is the teaser.
const CURATED_CATEGORIES = [
{
name: 'Typography',
do: [
'Pair a distinctive display face with a restrained body face; vary across projects.',
'Use a ≥1.25 scale ratio between hierarchy steps. Flat scales read as bland.',
'Cap body line length at 6575ch. Wider is fatiguing.',
],
dont: [
'Inter, Roboto, Plex, Fraunces, or any other reflex default. Look further.',
'Monospace as lazy shorthand for "technical."',
'Long passages in uppercase. Reserve all-caps for short labels.',
],
},
{
name: 'Color & Contrast',
do: [
'Use OKLCH. Reduce chroma near lightness extremes.',
'Tint neutrals toward the brand hue. Chroma 0.0050.01 is enough.',
'Pick a color strategy before picking colors (Restrained, Committed, Full, Drenched).',
],
dont: [
'Pure #000 or #fff. Always tint.',
'Dark mode + purple-to-cyan gradients. The AI tell.',
'Gradient text via background-clip. Use weight or size for emphasis.',
],
},
{
name: 'Layout & Space',
do: [
'Vary spacing for rhythm. Tight groupings, generous separations.',
'Use the simplest tool: Flexbox for 1D, Grid for 2D, plain flow often enough.',
'Let whitespace carry hierarchy before reaching for color or scale.',
],
dont: [
'Wrap everything in cards. Nested cards are always wrong.',
'Identical card grids of icon + heading + text, repeated endlessly.',
'The hero-metric template: big number, small label, supporting stats, gradient accent.',
],
},
{
name: 'Visual Details',
do: [
'Commit to an aesthetic direction and execute it with precision.',
'Use ornament only where it earns its place.',
],
dont: [
'Side-stripe borders (border-left/-right > 1px). The dashboard tell.',
'Glassmorphism everywhere. Rare and purposeful or nothing.',
'Rounded rectangles with generic drop shadows. "Could be any AI output."',
],
},
{
name: 'Motion',
do: [
'Use transform and opacity. Animate the composited properties only.',
'Ease out with exponential curves (quart / quint / expo).',
'Respect prefers-reduced-motion on every transition.',
],
dont: [
'Animate layout (width, height, padding, margin).',
'Bounce or elastic easing. Feels dated and tacky.',
'Decorative motion for its own sake. Motion should signal state.',
],
},
{
name: 'Interaction',
do: [
'Use optimistic UI: update immediately, sync later.',
'Design empty states that teach the interface, not just say "nothing here."',
'Progressive disclosure: start simple, reveal sophistication on demand.',
],
dont: [
'Make every button primary. Hierarchy matters.',
'Default to a modal. Exhaust inline alternatives first.',
'Repeat information the user can already see.',
],
},
];
export function readPatterns(_rootDir, _relativePath) {
// Hand-curated list — see CURATED_CATEGORIES above. The homepage
// Antidote teaser uses this; the full catalog lives on /slop.
return {
patterns: CURATED_CATEGORIES.map((c) => ({ name: c.name, items: c.do })),
antipatterns: CURATED_CATEGORIES.map((c) => ({ name: c.name, items: c.dont })),
};
}
// Previous SKILL.md parser retained below but disabled; kept as a
// reference for how prefix-style extraction used to work.
function _legacyReadPatterns(rootDir, relativePath = 'skill/SKILL.md') {
const skillPath = path.join(rootDir, relativePath);
if (!fs.existsSync(skillPath)) {
return { patterns: [], antipatterns: [] };
}
const content = fs.readFileSync(skillPath, 'utf-8');
const lines = content.split('\n');
const patternsMap = {}; // category -> items[]
const antipatternsMap = {}; // category -> items[]
let currentSection = null;
const pushPattern = (item) => {
if (!currentSection) return;
if (!patternsMap[currentSection]) patternsMap[currentSection] = [];
patternsMap[currentSection].push(item);
};
const pushAntipattern = (item) => {
if (!currentSection) return;
if (!antipatternsMap[currentSection]) antipatternsMap[currentSection] = [];
antipatternsMap[currentSection].push(item);
};
for (const line of lines) {
const trimmed = line.trim();
// Track section headings (### Typography, ### Color & Theme, etc.)
if (trimmed.startsWith('### ')) {
currentSection = trimmed.slice(4).trim();
// Normalize "Color & Theme" to "Color & Contrast" for consistency
if (currentSection === 'Color & Theme') {
currentSection = 'Color & Contrast';
}
continue;
}
// Markdown bullet form (legacy): **DO**: ... and **DON'T**: ...
if (trimmed.startsWith('**DO**:')) {
pushPattern(trimmed.slice(7).trim());
continue;
}
if (trimmed.startsWith("**DON'T**:")) {
pushAntipattern(trimmed.slice(10).trim());
continue;
}
// XML-block prose form (current). Both space and colon variants:
// "DO NOT use ..." / "DO NOT: Use ..."
// "DO use ..." / "DO: Use ..."
// IMPORTANT: check `DO NOT` BEFORE `DO` so the prefix doesn't get
// gobbled by the wrong matcher.
if (trimmed.startsWith('DO NOT: ')) {
pushAntipattern(trimmed.slice('DO NOT: '.length).trim());
continue;
}
if (trimmed.startsWith('DO NOT ')) {
pushAntipattern(trimmed.slice('DO NOT '.length).trim());
continue;
}
if (trimmed.startsWith('DO: ')) {
pushPattern(trimmed.slice('DO: '.length).trim());
continue;
}
if (trimmed.startsWith('DO ')) {
pushPattern(trimmed.slice('DO '.length).trim());
continue;
}
}
// Convert maps to arrays in consistent order
const sectionOrder = ['Typography', 'Color & Contrast', 'Layout & Space', 'Visual Details', 'Motion', 'Interaction', 'Responsive', 'UX Writing'];
const patterns = [];
const antipatterns = [];
for (const section of sectionOrder) {
if (patternsMap[section] && patternsMap[section].length > 0) {
patterns.push({ name: section, items: patternsMap[section] });
}
if (antipatternsMap[section] && antipatternsMap[section].length > 0) {
antipatterns.push({ name: section, items: antipatternsMap[section] });
}
}
return { patterns, antipatterns };
}
/**
* Provider-specific placeholders
*/
export const PROVIDER_PLACEHOLDERS = {
'claude-code': {
model: 'Claude',
config_file: 'CLAUDE.md',
ask_instruction: 'STOP and call the AskUserQuestion tool to clarify.',
command_prefix: '/'
},
'cursor': {
model: 'the model',
config_file: '.cursorrules',
ask_instruction: 'ask the user directly to clarify what you cannot infer.',
command_prefix: '/'
},
'gemini': {
model: 'Gemini',
config_file: 'GEMINI.md',
ask_instruction: 'ask the user directly to clarify what you cannot infer.',
command_prefix: '/'
},
'codex': {
model: 'GPT',
config_file: 'AGENTS.md',
ask_instruction: "STOP and use Codex's structured user-input/question tool when available; if unavailable, ask directly in chat to clarify what you cannot infer.",
command_prefix: '$'
},
'agents': {
model: 'the model',
config_file: '.github/copilot-instructions.md',
ask_instruction: 'ask the user directly to clarify what you cannot infer.',
command_prefix: '/'
},
'kiro': {
model: 'Claude',
config_file: '.kiro/settings.json',
ask_instruction: 'ask the user directly to clarify what you cannot infer.',
command_prefix: '/'
},
opencode: {
model: 'Claude',
config_file: 'AGENTS.md',
ask_instruction: 'STOP and call the `question` tool to clarify.',
command_prefix: '/'
},
'pi': {
model: 'the model',
config_file: 'AGENTS.md',
ask_instruction: 'ask the user directly to clarify what you cannot infer.',
command_prefix: '/'
},
'qoder': {
model: 'the model',
config_file: 'AGENTS.md',
ask_instruction: 'ask the user directly to clarify what you cannot infer.',
command_prefix: '/'
},
'trae': {
model: 'the model',
config_file: 'RULES.md',
ask_instruction: 'ask the user directly to clarify what you cannot infer.',
command_prefix: '/'
},
'rovo-dev': {
model: 'Rovo Dev',
config_file: 'AGENTS.md',
ask_instruction: 'ask the user directly to clarify what you cannot infer.',
command_prefix: '/'
}
};
/**
* Replace all {{placeholder}} tokens with provider-specific values
*/
function escapeRegex(str) {
return str.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
}
const EXCLUDED_FROM_SUGGESTIONS = new Set([
'impeccable', // foundational skill, not a steering command
'teach-impeccable', // deprecated shim
'frontend-design', // deprecated shim
]);
// Sub-commands of /impeccable that should appear in {{available_commands}}.
// These are the commands that audit/critique/etc. reference when suggesting next steps.
const IMPECCABLE_SUB_COMMANDS = [
'adapt', 'animate', 'audit', 'bolder', 'clarify', 'colorize',
'critique', 'delight', 'distill', 'document', 'harden', 'layout',
'onboard', 'optimize', 'overdrive', 'polish', 'quieter', 'shape', 'typeset',
];
export function replacePlaceholders(content, provider, commandNames = [], allSkillNames = []) {
const placeholders = PROVIDER_PLACEHOLDERS[provider] || PROVIDER_PLACEHOLDERS['cursor'];
const cmdPrefix = placeholders.command_prefix || '/';
// Build the available_commands list.
// After the v3.0 consolidation, commands are sub-commands of /impeccable.
// If there's only one user-invocable skill (impeccable), generate sub-command references.
// Otherwise fall back to listing skill names (backwards compat for forks).
const nonExcluded = commandNames.filter(n => !EXCLUDED_FROM_SUGGESTIONS.has(n));
let commandList;
if (nonExcluded.length === 0) {
// Single-skill architecture: list sub-commands as /impeccable <sub>
commandList = IMPECCABLE_SUB_COMMANDS
.map(n => `${cmdPrefix}impeccable ${n}`)
.join(', ');
} else {
// Multi-skill architecture (backwards compat)
commandList = nonExcluded.map(n => `${cmdPrefix}${n}`).join(', ');
}
let result = content
.replace(/\{\{model\}\}/g, placeholders.model)
.replace(/\{\{config_file\}\}/g, placeholders.config_file)
.replace(/\{\{ask_instruction\}\}/g, placeholders.ask_instruction)
.replace(/\{\{command_prefix\}\}/g, cmdPrefix)
.replace(/\{\{available_commands\}\}/g, commandList);
// Replace `/skillname` invocations with the correct command prefix for this provider
// (e.g., `/normalize` → `$normalize` for Codex)
if (cmdPrefix !== '/' && allSkillNames.length > 0) {
const sorted = [...allSkillNames].sort((a, b) => b.length - a.length);
for (const name of sorted) {
result = result.replace(
new RegExp(`\\/(?=${escapeRegex(name)}(?:[^a-zA-Z0-9_-]|$))`, 'g'),
cmdPrefix
);
}
}
return result;
}
/**
* Decide whether a YAML scalar string value must be quoted to survive parsing.
*
* Plain (unquoted) YAML scalars cannot contain `: ` or ` #`, cannot start with
* a YAML indicator character, cannot look like a boolean/null/number, and
* cannot carry leading/trailing whitespace. parseFrontmatter strips surrounding
* quotes on input, so we must re-detect the need to quote on output — otherwise
* descriptions like "Handles: critique/review..." round-trip into invalid YAML.
*/
function yamlNeedsQuoting(value) {
if (typeof value !== 'string') return false;
if (value === '') return true;
// Leading or trailing whitespace
if (/^\s|\s$/.test(value)) return true;
// Starts with a YAML flow/indicator character
if (/^[\[\]{},&*!|>'"%@`#]/.test(value)) return true;
// Starts with `?`, `:`, or `-` followed by space or end of string
if (/^[?:-](\s|$)/.test(value)) return true;
// Contains `: ` (ends plain scalar) or ` #` (starts comment), or ends with `:`
if (/: |\s#|:$/.test(value)) return true;
// Reserved keywords that YAML 1.1 parsers coerce to boolean/null
if (/^(true|false|null|yes|no|on|off|~)$/i.test(value)) return true;
// Looks like a number
if (/^-?\d+(\.\d+)?([eE][+-]?\d+)?$/.test(value)) return true;
return false;
}
function formatYamlScalar(value) {
if (typeof value !== 'string') return String(value);
if (yamlNeedsQuoting(value)) {
return `"${value.replace(/\\/g, '\\\\').replace(/"/g, '\\"')}"`;
}
return value;
}
function appendYamlObject(lines, data, indent = 0) {
const space = ' '.repeat(indent);
for (const [key, value] of Object.entries(data)) {
if (Array.isArray(value)) {
lines.push(`${space}${key}:`);
for (const item of value) {
if (item && typeof item === 'object' && !Array.isArray(item)) {
lines.push(`${space} -`);
appendYamlObject(lines, item, indent + 4);
} else {
lines.push(`${space} - ${formatYamlScalar(item)}`);
}
}
} else if (value && typeof value === 'object') {
lines.push(`${space}${key}:`);
appendYamlObject(lines, value, indent + 2);
} else if (typeof value === 'boolean') {
lines.push(`${space}${key}: ${value}`);
} else {
lines.push(`${space}${key}: ${formatYamlScalar(value)}`);
}
}
}
/**
* Generate YAML frontmatter string
*/
export function generateYamlFrontmatter(data) {
const lines = ['---'];
for (const [key, value] of Object.entries(data)) {
if (Array.isArray(value)) {
lines.push(`${key}:`);
for (const item of value) {
if (typeof item === 'object') {
lines.push(` - name: ${formatYamlScalar(item.name)}`);
if (item.description) lines.push(` description: ${formatYamlScalar(item.description)}`);
if (item.required !== undefined) lines.push(` required: ${item.required}`);
} else {
lines.push(` - ${formatYamlScalar(item)}`);
}
}
} else if (typeof value === 'boolean') {
lines.push(`${key}: ${value}`);
} else {
lines.push(`${key}: ${formatYamlScalar(value)}`);
}
}
lines.push('---');
return lines.join('\n');
}
/**
* Generate a plain YAML document string.
*/
export function generateYamlDocument(data) {
const lines = [];
appendYamlObject(lines, data);
return lines.join('\n');
}