skills/pbakaus_impeccable

Fork 0

mirror of https://github.com/pbakaus/impeccable.git synced 2026-09-11 21:57:14 +03:00

Files

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

3.3 KiB

Raw Blame History

Product

Register

brand

Users

Designers, product managers, and engineers who use AI coding tools (Cursor, Claude Code, Gemini CLI, Codex CLI, and others) and want better design output from their AI. They land on the site from GitHub, social media, or word of mouth, already aware that AI-generated UIs have quality problems. They're looking for a practical solution, not education about the problem.

Product Purpose

Impeccable gives builders a shared design vocabulary with their AI, delivered as a plug-and-play skill that works in every major AI coding harness. Success is measured in two ways: (1) the user can steer AI output with design precision instead of vague prose, and (2) the AI produces interfaces that pass professional design review, not "looks like an AI made it" output.

Brand Personality

Expert, opinionated, refined. Impeccable speaks with an authoritative design voice: confident taste, editorial quality, zero hedging. It's the design director in the room who knows exactly what's wrong and how to fix it. The tone is direct (no "maybe consider"), specific (no "improve the vibe"), and rooted in craft (no hype, no hedging).

Three-word personality: expert, decisive, editorial.

Anti-references

The site and brand must be the antithesis of everything Impeccable critiques. Specifically, avoid:

Generic AI tool marketing: dark mode with purple gradients, neon accents, glassmorphism, glowing particles, cyan-on-black.
SaaS landing-page clichés: hero-metric layouts, identical-card feature grids, sparkline decorations, "boost your productivity" copy.
Hedging language: "might", "could", "consider", "perhaps". Impeccable is opinionated — it picks a direction and commits.
Educational framing: this product is for people who already know they have a problem; we solve it, we don't teach it.
Over-decoration: every visual element must earn its place. No ornament for ornament's sake.

Design Principles

Practice what you preach. The site must pass its own anti-pattern tests with flying colors. If we ship anything we'd flag in an audit, we've lost.
Show, don't tell. Demonstrate design quality through execution, not through words about design quality. The site IS the demo.
Expert confidence. Direct, opinionated, decisive. No hedging. Every assertion should sound like it comes from someone who has seen a thousand interfaces and knows what works.
Editorial over marketing. Feels like a design publication (Eye Magazine, It's Nice That, A List Apart) rather than a SaaS landing page. Long-form reading, considered typography, breathing room.
Purposeful restraint. Every element earns its place. Nothing decorative without function. Nothing included because "landing pages usually have that".

Accessibility & Inclusion

Baseline: WCAG 2.1 AA on all pages. Key commitments:

Color contrast ratios verified with actual contrast checks, not eyeballing.
All interactive elements keyboard-navigable with visible focus states.
prefers-reduced-motion respected for every animation.
Semantic HTML first, ARIA as a supplement, never as a workaround.
Copy readable at an 8th-grade level; jargon only when precisely needed (design terms like "OKLCH", "chroma" are acceptable because they're the actual vocabulary users are here to learn).

3.3 KiB Raw Blame History