mirror of
https://github.com/pbakaus/impeccable.git
synced 2026-09-12 22:26:38 +03:00
1a4b5c2fa2173d9e80a75e3cc29cae353d267228
15
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
   
|
9ffd3211d5 |
Neo Kinpaku design system + Live Mode v3 (#169)
* Add neo kinpaku design system page * skill: rip out baked-in category recipes and saturated-default motion tropes Programmatic bias mining (impeccable-evals) traced four major defects back to specific lines in this skill that contradicted SKILL.md's own first-order-reflex warning: - brand.md "Pairing and voice" prescribed four category→aesthetic recipes (editorial → serif+sans, tech/dev/fintech → tight tracking, consumer/food/travel → script/display serif, creative → rule-break). These directly drove OpenAI's 76% extreme-negative letter-spacing on tech briefs and Anthropic/Google's 28-34% italic-serif-display slop on editorial/food briefs. Replaced with one sentence: the shape depends on the brand, not on the brand's category. - brand.md "Brand permissions" had "Typographic risk. Enormous display type, unexpected italic cuts, mixed cases, hand-drawn headlines, a single oversize word as a hero." — a four-for-one slop driver behind 97% OpenAI comically-large H1, 42% bad-SVG illustration, and the editorial-italic slop. Deleted outright. - typeset.md and teach.md repeated the same category recipes; trimmed to the principle without the recipe. - SKILL.md Typography: added a hard hero-H1 ceiling (clamp() max ≤ 6rem ≈ 96px), with a <codex> block to make it explicit since OpenAI over-indexes here (97% ≥128px vs 24% for Anthropic). - animate.md, bolder.md, brand.md: removed "staggered reveals" and "scroll-triggered transitions" as the prescribed default ambitious motion. By 2026 that's the saturated AI tell, not a choreography. Reserved stagger for legitimate list-sibling rhythm. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: anti-cream + codex-specific defect bans + universal slop bans Second pass after measuring more biases against the eval corpus. - SKILL.md Color: explicit "cream/sand/beige body bg is the saturated AI default of 2026" rule. Tone down the "tint every neutral" line so it doesn't read as "default to warm-tinted near-white" (which OpenAI hits at 74% and Anthropic at 31%-47%). - SKILL.md Absolute bans: add universal bans for two slop patterns detected at 55-95% across providers — tiny uppercase tracked eyebrow above every section (the 2023-era kicker that's now AI grammar) and numbered section markers (01/02/03). Also explicit "text that overflows its container is the universal defect on tablet/mobile." - SKILL.md Absolute bans → <codex> block: ban the GPT-specific defects Paul annotated repeatedly — `border:1px solid` + soft-wide-shadow (≥16px blur) "ghost cards", `border-radius:32px+` over-rounding, hand-drawn/sketchy SVG illustrations (loose-sketch / *-sketch classes, feTurbulence paper-grain filters), repeating-linear-gradient stripes, "X theater" AI-slop copy phrases. - SKILL.md Motion → <gemini> block: the image :hover transform tell (38% Google skill-on rate). Hover effects on images add no info; the image isn't an action target. Animate card chrome, not the image. - SKILL.md Typography: hard display letter-spacing floor ≥-0.04em (OpenAI defaults to -0.075em → cramped). Existing hero ceiling <codex> block extended with the letter-spacing rule. - codex.md Step A example: stop seeding "warm-grounded (deep oxblood + cream)" as the warm-palette template, which primes the cream default. - colorize.md Tinted backgrounds: stop printing the literal cream recipe `oklch(97% 0.01 60)`; replace with brand-anchored guidance. - document.md examples: warm-ash-cream → cool-paper so the example doesn't seed cream as the canonical neutral example. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: universal anti-slop bans + contrast/font-count/all-caps-body rules Third pass after measuring the rest of the cross-provider matrix: - Color: explicit "Verify contrast" rule. Low-contrast text fires at 68% across all providers skill-on (90+% off). The most common failure is muted gray body on a tinted near-white; light-gray-for- elegance is named as the single biggest cause of unreadable AI pages. - Typography: max-3-font-families rule. Overused-fonts (>4 families) fires at 28% Anthropic / 36% Google / 0% OpenAI skill-on; >50% off. Also: universal "no all-caps body copy" (moved from brand-only ban to Shared design laws since product-register also overuses caps). - Copy: anti-aphoristic-cadence ban targets Anthropic's signature "X. No Y." / "X. Just Y." voice (63% skill-on copy-slop rate, 77% off — the worst rate in the matrix). Once-is-voice / three-or-more- is-tell framing per the runner's copy-slop detector. - Copy: anti-SaaS-buzzword-string ban with the literal phrase list the detector watches for (streamline/empower/supercharge, trusted- by-leading, best-in-class/enterprise-grade/cutting-edge, etc). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: strengthen anti-cream rule across full warm-neutral band Smoke validation showed the cream fix worked for Google + OpenAI but Anthropic Sonnet italian-restaurant still shipped `--paper: oklch(90% .018 88)` — cream just outside the L≥95% band the rule cited. Broaden the rule: - Band: OKLCH L 0.84-0.97, C < 0.06, hue 40-100 (was 95-97% / 60-95). - Name the token-name tells explicitly (paper / cream / sand / bone / flour / linen / parchment / wheat / biscuit / ivory) — the model defaults to one of these regardless of what hex it lands on. - Call out the specific brief patterns ("warm, traditional, family- coastal-Italian" / "editorial-restraint") that the model translates into cream by reflex. Then provide three explicit non-cream options: saturated brand color, true off-white at C=0, or darker mid-tone. Warmth in the brand is carried by accent + typography + imagery, not by body bg. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * v3.2.0: skill bias-fix release Bumps version from 3.1.1 to mark the four-commit skill cleanup that rips out baked-in category recipes (brand.md), saturated-default motion tropes (staggered reveals everywhere), the cream/sand body-bg AI tell, codex-specific defects (1px+wide-shadow, over-rounding, hand-drawn SVGs, stripes, X-theater copy), the extreme-letter-spacing default, and universal slop bans (all-caps eyebrow on every section, numbered-section markers, all-caps body, font-family-count > 3, aphoristic copy cadence, SaaS buzzword strings). Plus a hard hero-H1 ceiling (clamp() ≤6rem) and a Gemini-specific image:hover transform block. Validated against ~190 post-fix samples — see impeccable-evals biases tab for per-provider deltas. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * drop "no pure black/white" rule entirely The rule was contested in the design world and causing more damage than good — pushing every page into the tinted-near-white default which is the cream/sand AI tell we already explicitly ban elsewhere. Vercel, SVKMS, Brutalist sites, et al. use pure black/white successfully; the skill shouldn't second-guess that. Skill markdown deletions: - SKILL.md Color: drop the "Never use #000 or #fff" bullet. - color-and-contrast.md: drop the "Never Use Pure Gray or Pure Black" subsection, the "Never pure black" table-row prescription, and the "Avoid: Using pure black for large areas" bullet. - colorize.md: drop the "NEVER use pure black or pure white for large areas" bullet. - polish.md: drop the "Tinted neutrals: No pure gray or pure black" half of the bullet (the gray-on-color bullet survives). Detector code (cli/engine): - registry/antipatterns.mjs: remove the `pure-black-white` entry. - rules/checks.mjs: remove the three `findings.push({ id: 'pure-black-white', ... })` emit points (inline #000 bg, Tailwind bg-black class, plain-HTML scan path). - engines/regex/detect-text.mjs: remove the two pure-black-white regex rules (CSS `background: #000…` + Tailwind `bg-black`). - detect-antipatterns-browser.js: regenerated via scripts/build-browser-detector.js. Tests: - detect-antipatterns-fixtures.test.mjs: invert the assertion that pure-black-white fires; expect it to NOT fire post-v3.2. Drop the Tailwind bg-black-opacity edge-case test (no longer relevant). - detect-antipatterns.test.js: drop the standalone "detects pure- black-white in styled-components" test and remove pure-black-white from the multi-detector assertions in PricingCard, globals.css, and GlobalStyle.tsx tests. 166 bun tests pass; 24 node fixture tests pass. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: strip example patterns from copy rules, strengthen gemini block v3.2 rerun validation surfaced two issues: 1. Copy-slop detector fires more on Gemini under v3.2 (48% → 84%) than under no-skill baseline. Root cause: the anti-aphoristic-cadence rule printed the literal "X. No Y." / "X. Just Y." patterns as examples, and Gemini imitated them as the recommended voice. Same recipe-becomes- bias trap we hit with brand.md:116's "Enormous display type, unexpected italic cuts, mixed cases, hand-drawn headlines" enumeration. Fix: describe the cadence as a rhythm ("serious statement, then punchy short negation") without printing literal patterns. Buzzword list trimmed to a single inline phrase family rather than quoted strings. 2. Gemini image:hover transform Gemini-tell hadn't dropped (31% off → 32% v3.2). Strengthen the <gemini> block: explicit "Never animate <img> elements on hover", call out the Tailwind group-hover:scale / group-hover:rotate / group-hover:translate parent-hover patterns by name (Gemini was reaching for these via Tailwind even though the prior text talked about :hover on the image directly). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: simplify context loading and inline register directive Replaces load-context.mjs's JSON output with a tight markdown block from the renamed context.mjs. The script now extracts PRODUCT.md's `## Register` field and appends a `NEXT STEP:` directive naming the matching reference (brand.md / product.md), which moved Gemini from skipping the register load entirely to honoring it. Drops the `.impeccable.md` auto-migration; makes IMPECCABLE_CONTEXT_DIR a lazy escape hatch consulted only when the default paths come up empty. Setup is now four bullets in one list. The DESIGN.md nudge is gone; in its place, a "familiarize with the existing design system" step that calls out CSS / tokens / running app as authoritative sources alongside DESIGN.md. The standalone `### Register` H3 stays for the cascade rules (task cue → surface → register field). New LLM-backed test suite at tests/skill-behavior/ runs five scenarios against claude-haiku-4-5, gpt-5.4-mini, and gemini-3.1-flash-lite via Vercel AI SDK. Captures real tool traces, asserts on context.mjs calls, brand.md loads, and teach.md fallback. Skips cleanly when API keys are unset. 13-14/15 pass; only stable failure is the v3.2.0-era gpt-mini S4 "don't re-run" regression. Adds @ai-sdk/google as devDep and the test:skill-behavior npm script. Touches em-dashes in skill/SKILL.md and four reference files so `bun run build:skills` passes its skill-prose validator. teach.md and document.md drop their "re-run the loader to refresh session cache" steps since the agent's own write is now the freshest source. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: merge orphan reference files into command sub-skills + inline S-tier invariants Two related restructurings: 1. SKILL.md now carries the cross-domain invariants that catch defects in any project (contrast/placeholder/gray-on-color, similar-font pairing, text-wrap, tabular-nums, centered-stack default, Flex/Grid choice, auto-fit grids, semantic z-index, reduced motion, stagger vs section-fade, premium motion materials, focus-visible, placeholders-aren't-labels, dropdown overflow trap, button/link copy). Greenfield-only rules (theme picking, color strategy, tinted neutrals) live under "New projects only". 2. Reference files merged into their command counterparts: - spatial-design.md -> layout.md - motion-design.md -> animate.md - color-and-contrast.md -> colorize.md - responsive-design.md -> adapt.md - ux-writing.md -> clarify.md - typography.md -> typeset.md (bolder.md redirected) - cognitive-load.md + heuristics-scoring.md + personas.md -> critique.md craft.md and shape.md "load references" lists updated to new file homes. interaction-design.md stays standalone (no 1:1 command verb). Net: 36 -> 27 reference files. Same content, fewer files, no orphaned reference loaded only from craft.md. Also extends the routing rules: if the user's first word doesn't match a command but the intent clearly maps to one, load that command's reference and proceed as if invoked. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: add sub-command + existing-project scenarios; move sub-command load to step 2 Adds three new LLM-backed scenarios to tests/skill-behavior: - S6: `/impeccable polish` → loads polish.md - S7: `/impeccable audit` → loads audit.md - S8: existing SvelteKit project (PRODUCT.md + DESIGN.md + src/app.css + src/lib/components/*.svelte + src/routes/+page.svelte) → agent reads at least one project code file to understand the existing design system S6/S7 surface a real model-floor: gpt-5.4-mini reads brand.md, reads the target index.html, and just does the polish/audit without ever loading the sub-command reference. Stronger SKILL.md wording didn't move it. Captured in the README baseline as a known weakness. Claude and Gemini honor the load reliably. To fix Gemini on S6/S7, sub-command reference loading is now Setup step 2 (right after context.mjs), not step 4 — placing it before the model gets focused on "doing the work". Step 3 (design-system familiarization) is tightened to require at least one project code read even when a sub-command reference loads in step 2, so Claude doesn't laser-focus on the sub-command flow and skip the broader exploration. Two new fixtures: MINIMAL_LANDING_HTML (a tiny static landing page for S6/S7) and SVELTE_PROJECT_FILES (a minimal SvelteKit scaffold with tokens, components, and a routes/+page.svelte for S8). Both designed to look real enough that agents treat them as production code. Suite is now 24 tests across three providers; baseline is 21-22/24, with the stable failures being gpt-5.4-mini scenarios 6 and 7. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: add reveal-animation safety rule (must enhance, not gate visibility) Class-triggered visibility transitions pause on hidden tabs and headless renderers. The italian-restaurant smoke produced a build where 2 sections shipped opacity:0 because the CSS transition never advanced past currentTime=0 (timeline paused). Added one-liner under Motion to prevent the antipattern: reveals must enhance an already-visible default, never gate content visibility on a class-triggered transition. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: restore prescriptive cream/sand/beige paragraph Bisection across 5 historical skill commits on Gemini 3.5 flash fast lane n=3 found that |
||
|
Paul BakausandGitHub
|
e1d3ea0b6f |
Detector architecture v2: static engine, benchmarks, lab, and visual contrast (#156)
* Add detector benchmark lab and visual contrast fallback * Expand visual contrast fixture coverage * Add browser visual contrast fallback * Show visual contrast overlays in detector lab * Fix detector lab short viewport layout * Fix detector lab visual overlays * Add visual contrast to browser scan overlays * Avoid browser scroll jumps during visual contrast scans * Resolve visual contrast lazily on scroll * Refresh detector lab visual counts lazily * Update pnpm lockfile for static parser deps * Address Bugbot detector API comments * Report extension visual contrast errors * Refactor detector into engine modules * Address Bugbot detector comments * Fix latest Bugbot detector notes * Fix visual contrast fixture labels * Refine detector lab fixtures * Fix stale detector overlay references * Fix detector lab fixture URLs * Fix typography lab fixture highlights * Fix typography lab page-level signal * Fix visual overlay lifecycle cleanup * Remove dead spotlight timer cleanup * Make browser async APIs reject consistently |
||
|
e587004ee4 |
Refactor: cleaner top-level directory structure (#138)
* refactor(content): merge content/site/ into site/content/ Phase 1 step 1 of the directory restructure. The dual content tree was called out in CLAUDE.md as cleanup; both trees were already in sync except for anti-patterns-catalog.js, which moves to site/data/. - Delete content/site/skills/ and content/site/tutorials/ (duplicates of site/content/, which is what Astro's content collection actually reads). - Move content/site/anti-patterns-catalog.js -> site/data/. - Update scripts/lib/sub-pages-data.js and scripts/build.js to read from site/content/ and site/data/. - Drop content/site/ from validateProse target list (site/content was already there). - Rewrite the "Two content trees" section in CLAUDE.md as a single-tree pointer; update stale dev-server text mentioning the deleted server/index.js. Tests: 186/186 pass. Skills build: clean. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor(skill): rename source/skills/impeccable/ -> skill/ Phase 1 step 2 of the directory restructure. The path was redundantly nested ("source/" wrapper plus "skills/impeccable/" — singular content hidden behind the plural). Collapses to flat skill/SKILL.md + skill/reference/ + skill/scripts/. - Move source/skills/impeccable/ -> skill/. - Rewrite scripts/lib/utils.js readSourceFiles(): drop the multi-skill iteration (CLAUDE.md commits to a single user-invocable skill); read skill/SKILL.md directly. - Update scripts/build.js, scripts/generate-og-image.js, and the sub-pages data layer to point at skill/. - Update tests/lib/utils.test.js: drop the "multi-skill" and "dir-name fallback" cases, update single-skill paths to skill/. - Update tests/build.test.js similarly: drop "multiple skills" integration test, update paths. - Update non-glob path joins in tests/framework-fixtures.test.mjs, tests/live-e2e/session.mjs, tests/live-e2e/agents/llm-agent.mjs, tools/live-loop.mjs. - Update prose/text references in CLAUDE.md, AGENTS.md, DEVELOP.md, README.md, scripts/lib/sub-pages-data.js, bin/commands/skills.mjs, site/data/anti-patterns-catalog.js, site/pages/docs/[...slug].astro, docs/adr-live-variant-mode.md, docs/plans/. Eval framework note: the separate impeccable-evals repo reads ../impeccable/source/skills/impeccable/ and needs a coordinated rename to ../impeccable/skill/. Tests: 186/186 pass. Skills build: clean. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor: rename docs/ -> notes/ Phase 1 step 3 of the directory restructure. The internal docs/ dir (ADRs and plans) clashed with the site's /docs route. Renaming it "notes/" makes the difference unambiguous: notes/ is project-internal process, /docs is the user-facing route under site/pages/docs/. No code references the dir; the rename is a clean git mv. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor(site): move public/ under site/public/ Phase 2 step 4 of the directory restructure. Public assets and the Astro publicDir now live alongside the rest of the site, so site/ is fully self-contained for static content. - git mv public site/public. - astro.config.mjs: add publicDir: './site/public'. Astro defaults to ./public at the project root, so the override is required. - scripts/build.js: write generated _data, _headers, _redirects, _routes.json, and js/detect-antipatterns-browser.js into site/public/. Also delete the dead _REMOVED() Bun static-site builder (replaced by Astro at #130; the placeholder no longer earns its keep). - scripts/build.js validateProse: replace the stale public/index.html reference (deleted at the Astro migration) with site/pages/index.astro in the count-validation file list, restoring homepage drift detection. - scripts/generate-og-image.js: write OG image into site/public/. - scripts/screenshot-antipatterns.js: read examples from + write screenshots to site/public/antipattern-{examples,images}/. - scripts/lib/sub-pages-data.js: load command demos from site/public/js/demos/commands. - .gitignore: rename the public/* generator-output entries to site/public/*. - CLAUDE.md: refresh CSS/data-file paths (still pointing at the old pre-Astro public/css/ + public/js/ tree), point the changelog and command-add checklists at site/pages/index.astro and site/scripts/data.js + site/scripts/components/framework-viz.js. Cloudflare Pages note: functions/ stays at the repo root because CF Pages auto-discovers it there with no configuration knob to relocate. Moving it under site/ would either break deployment or require a build-time copy step that adds more complexity than the cleanup is worth. Tests: 186/186 pass. Skills + site build clean. _headers, _redirects, _routes.json, _data/ all land in build/ correctly. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor(cli): consolidate bin/ + src/ + lib/ under cli/ Phase 2 step 5 of the directory restructure. The CLI surface was split across three top-level dirs whose names were easy to mistake for each other (especially src/ vs source/ pre-step-2). Consolidates under cli/. - git mv bin -> cli/bin (CLI entry + skills sub-command) - git mv src -> cli/engine (detect-antipatterns engine + browser variant) - git mv lib -> cli/lib (download-providers helper) Update package.json: - bin.impeccable: cli/bin/cli.js - main + exports: cli/engine/detect-antipatterns.mjs and the ./browser variant - files: ["cli/", "LICENSE"] Update internal references: - cli/bin/cli.js: dynamic import points at ../engine/, package.json read goes one level deeper (../../package.json). - functions/api/download/[type]/[provider]/[id].js + bundle/[provider].js: cli/lib/download-providers.js path. - scripts/build.js, scripts/build-browser-detector.js, scripts/build-extension.js: cli/engine path constants. - scripts/lib/sub-pages-data.js, scripts/lib/utils.js, skill/scripts/ live-server.mjs: comment refs. - tests/detect-antipatterns{,-browser,-fixtures}.test.{js,mjs}, tests/windows-path-fix.test.js: import + read paths. - AGENTS.md, CLAUDE.md: doc paths. Verified: - npx node cli/bin/cli.js --version, --help, detect --help all work. - bun run build, bun run build:browser, bun run build:extension all clean. Browser detector lands at cli/engine/detect-antipatterns-browser.js; extension/detector/detect.js still emits to the same location. - bun run test: 186/186 pass. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: update browser-detector paths missed in cli/ rename Bugbot caught two runtime path leaks where the comment got renamed to cli/engine/ but the actual code still used the old src/ segment. - skill/scripts/live-server.mjs: detectPaths array now joins cli, engine, detect-antipatterns-browser.js for both the repo-relative lookup (4 dirs up from .claude/skills/impeccable/scripts/ to repo root) and the npm node_modules fallback. Without this fix, the detection overlay would silently not load during live-server sessions. - scripts/build.js: the post-build copy of the browser detector into site/public/js/ was reading from src/. The if (fs.existsSync(...)) guard meant the copy was silently skipping, so antipattern-examples pages would 404 on /js/detect-antipatterns-browser.js once the site was deployed. Tests: 186/186 pass. Build clean. site/public/js/detect-antipatterns-browser.js re-emits as expected. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: cleanup-deprecated import path missed an extra .. in cli/ rename Bugbot caught three call sites in cli/bin/commands/skills.mjs that import '../../skill/scripts/cleanup-deprecated.mjs'. Pre-rename, that was correct from bin/commands/ (one parent to bin/, one to repo root). After moving the file from bin/commands/ to cli/bin/commands/, the path is one directory deeper, so it needs three .. segments to reach the repo root. Without the fix, every cleanup invocation throws on import and gets swallowed by the surrounding try/catch — silent skip. cli/bin/cli.js's package.json read already uses '../../package.json' (the same depth pattern), confirming three levels is correct. Verified: dynamic import resolves and exports the expected functions. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: sweep stale path/file references missed in the restructure Same root cause as the two bugbot finds: some references in moved or related files weren't tracked because they didn't match a simple sed pattern. Caught the rest by walking each moved dir's depth and each Astro-migration deletion. Stale path references (post-Astro migration, missed earlier): - CLAUDE.md: legacy URL redirects "live in server/index.js" -> point at the actual sources (scripts/build.js generateCFConfig + site/public/_redirects). - AGENTS.md: counts.js path (public/ -> site/public/), changelog file (public/index.html -> site/pages/index.astro), screenshots note (public/ -> site/), source-of-truth dirs (source/, src/ -> skill/, cli/). - tests/detect-antipatterns-browser.test.mjs: comment about routes "in server/index.js". - skill/reference/live.md: workflow.css example for "this repo" was pre-Astro (public/css/) -> site/styles/. (User-project Vite/Next example unchanged.) Stale path that pointed at moved files: - tests/skills-cli.test.js: CLI path was '..', 'bin', 'cli.js'; now '..', 'cli', 'bin', 'cli.js'. Test isn't wired into bun run test but it would have failed if invoked. Dead files (orphaned by Astro migration, never cleaned up): - tests/server/download-validation.test.js: imported from ../../server/lib/{validation,api-handlers}.js which were deleted in |
||
|
Paul BakausandClaude Opus 4.6
|
af2d6e1194 |
Support PRODUCT.md + DESIGN.md as canonical context files
Pioneers a two-file convention for project context:
- PRODUCT.md (strategic): users, brand, principles — answers who/what/why
- DESIGN.md (visual): follows Google's Stitch DESIGN.md spec — answers how-it-looks
Both files live at the repo root. Filename matching is case-insensitive.
DESIGN.md wins on visual conflicts, PRODUCT.md wins on strategic/voice.
Legacy .impeccable.md is auto-migrated to PRODUCT.md on first read by the
new shared loader. This is silent and one-shot — the rename is permanent.
What changed:
- New scripts/load-context.mjs: shared context loader used by every command
that needs project context. Reads both files, handles legacy migration.
- New reference/document.md: /impeccable document command that generates
DESIGN.md by auto-extracting tokens (colors, typography, spacing, radii,
shadows, components) from CSS/Tailwind/theme files, then asking the user
to confirm descriptive language for atmosphere and color character.
Follows Google's Stitch DESIGN.md format for tool compatibility.
- SKILL.md Context Gathering Protocol updated to load both files and
nudge the user to run /impeccable document when DESIGN.md is missing.
- reference/teach.md rewritten to split discovery cleanly: strategic
questions go to PRODUCT.md, visual/design-system work is delegated to
/impeccable document (skipped on empty projects).
- reference/live.md consumes {product, design, productPath, designPath,
migrated} from the loader instead of a single context blob.
- scripts/live.mjs uses the shared loader instead of inline file reading.
- Command count updated 22 → 23 (new: document). Metadata, router table,
command menu, periodic table viz, and homepage data all updated.
- .gitignore adds PRODUCT.md + DESIGN.md (repo-local, not shared).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
||
|
Paul BakausandClaude Opus 4.6
|
e4d1d96926 |
Auto-generate argument hint with all commands grouped by category
The static "[command] [target]" hint didn't help users discover available commands. The build now reads command-metadata.json and groups commands by category (from SKILL_CATEGORIES) with middle-dot separators for natural line-breaking in the prompt bar. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
Paul BakausandClaude Opus 4.6
|
bb94dadda0 |
Add live variant mode: element picker, action panel, poll/reply bridge (22 commands)
New feature: /impeccable live starts an interactive visual iteration server. Users select elements in the browser, pick a design action (bolder, quieter, etc.), and the agent generates HTML+CSS variants written directly to source. The dev server's HMR hot-swaps them in, and MutationObserver progressively reveals each variant in a cycler UI as it arrives. Architecture: - src/live/server.mjs: HTTP + WebSocket server with session token auth, long-poll /poll endpoint for the agent, WebSocket for the browser - src/live/poll.mjs: CLI client (npx impeccable poll / poll --reply) - src/live/browser.js: element picker with keyboard nav (arrows=siblings, shift+arrows=parent/child), action panel (12 commands, freeform input, variant count), variant cycler with progressive reveal via MutationObserver - src/live/protocol.mjs: shared message types and event validation - source/skills/impeccable/reference/live.md: agent loop instructions (inject script, poll loop, generate variants, accept/discard, cleanup) CLI changes: - bin/cli.js: added "poll" top-level command - src/detect-antipatterns.mjs: liveCli() now delegates to src/live/server.mjs - package.json: added ws dependency Registered /impeccable live as command #22 across all standard locations. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
Paul BakausandClaude Opus 4.6
|
e58cbc432f |
Split /onboard back out as its own command (21 commands total)
Pre-3.0, onboard was folded into /harden when we were trying to reduce
namespace pollution. In the single-skill model that tradeoff is gone,
so the weakest of the old merges is the first to undo.
Harden and onboard live in different mental modes. Harden is defensive
(edge cases, i18n, overflow, errors). Onboard is activation (first-run
flows, empty states as CTAs, progressive disclosure). A user thinking
"design the onboarding flow" was never going to type /impeccable harden.
Changes:
- New reference file at source/skills/impeccable/reference/onboard.md,
restored from the pre-merge version in git history rather than the
condensed 33-line summary that was in harden.md.
- Removed the "Onboarding & First-Run Experience" section from
source/skills/impeccable/reference/harden.md.
- Updated harden description/editorial/process-steps to drop onboarding
keywords; split commandProcessSteps so harden stays focused on
production resilience and onboard gets its own phases.
- Registered onboard in: SKILL.md description + command menu + router
table, command-metadata.json, IMPECCABLE_SUB_COMMANDS, pin.mjs
VALID_COMMANDS, SKILL_CATEGORIES, COMMAND_RELATIONSHIPS, data.js
commandCategories + commandProcessSteps + commandRelationships,
framework-viz commandSymbols + commandNumbers.
- Reused the existing content/site/skills/onboard.md editorial wrapper
(it was orphaned by the merge but never deleted), updating it to use
/impeccable onboard.
- Bumped all user-facing count references 20 -> 21: public/index.html,
CLAUDE.md, README.md, NOTICE.md, plugin.json, marketplace.json,
sitemap.xml, build-sub-pages.js.
- Harness dir audit.md and critique.md changes are the
{{available_commands}} placeholder expanding to include onboard.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
||
|
Paul BakausandClaude Opus 4.6
|
b0f44f83c6 |
Consolidate 18 skills into 1 /impeccable skill with 20 commands
Biggest change in a while. Users previously had 18 standalone skill
entries cluttering their /menu; now they have one entry (/impeccable)
that routes to 20 specialized commands via argument dispatch. The pin
mechanism (/impeccable pin audit) restores standalone shortcuts on
demand for commands users hit all the time.
## Architecture
- Single /impeccable skill with command router section in SKILL.md
- 20 commands served via reference files under source/skills/impeccable/reference/
- /impeccable pin <command> creates a lightweight redirect shim so users
who prefer /audit, /polish, etc. can still have them
- Context gathering (teach) auto-runs on first use
- command-metadata.json is the single source of truth for command
descriptions, argument hints, and relationships
## Site rewrite
- Docs URL: /skills renamed to /docs (with /skills permanent redirects)
- Homepage hero frames Impeccable as "one skill with 20 commands"
- "Get Started" split into 50/50 install + how-to-use with editorial
numbered steps, /impeccable shown as the home command with three modes
- New /docs overview: home command hero card + dense category rows
matching the old cheatsheet density, with leads-to/pairs-with/
combines-with relationship metadata served from a shared source
- Cheatsheet merged into /docs, /cheatsheet redirects
- Magazine spread and mobile cards show /impeccable as a stacked
namespace label above the command name at full display size
- Periodic table updated with craft/teach/extract as first-class cells
- Skill detail pages generate from reference files, with an editorial
wrapper per command for tagline + body
- Tutorials and anti-patterns pages updated to use /impeccable <cmd>
## Build system
- Dead code removed (scripts/lib/transformers/shared.js)
- Build log wording fixed ("1 skill" not "1 skills (1 user-invocable)")
- generateApiData fallback branch removed (throws loudly if metadata
missing instead of silently degrading)
- Commands API includes editorial tagline alongside the long description;
UI surfaces prefer tagline for human display, description for auto-
trigger keyword matching
## Gitignore
- Added .claude/scheduled_tasks.lock, .claude/settings.local.json to
ignore list (local Claude Code state that should not be tracked).
- Harness skill directories (.claude/skills/, .agents/skills/, etc.)
remain tracked by design: npx skills reads them from this repo at
install time and they enable clean submodule use.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
||
|
Paul BakausandClaude Opus 4.6
|
faa7453db7 |
Consolidate skills from 21 to 18: rename, merge, and fold
- Rename /arrange to /layout for clarity - Merge /normalize into /polish (design system discovery + cleanup phases) - Merge /onboard into /harden (onboarding, empty states, progressive disclosure) - Fold /extract into /impeccable extract sub-mode (reference file, sidebar link) - Update all counts, cross-references, data files, demos, and metadata - Remove System category (now empty) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
Paul Bakaus
|
ebe07cbae5 |
Merge gallery into /anti-patterns, hide rule ids
Two fixes from the review.
1. Rule id chip hidden. The internal slugs (e.g. 'border-accent-on-rounded')
are not useful to readers, only to detector code. Drop the
.rule-card-id element from the card head entirely. The DOM id on
the article stays so rules can still be anchor-linked.
2. Merge /gallery into /anti-patterns and drop 'Gallery' from the nav.
'Gallery' in the top nav reads as 'things built with impeccable'
when it is actually a curated collection of AI-generated UI in the
wild — the complement to the rule catalog above.
- Add GALLERY_ITEMS to content/site/anti-patterns-catalog.js
(11 entries, same ids and copy as the old gallery.html)
- Render a new 'In the wild' section at the bottom of
/anti-patterns with a card grid of the 11 specimens, each linking
to its standalone live example under /antipattern-examples/{id}.html
- New .gallery-card CSS: square thumbnail, italic display title,
charcoal body, hover lifts the card and tints the title accent
- Add an 'In the wild' entry to the anti-patterns TOC sidebar so
readers can jump to it
- Drop the 'Gallery' link from the top-level nav in the shared
header partial and the 4 hand-authored HTML pages. The old
/gallery route still serves its page directly (for bookmarked
links), but the nav no longer advertises it and the gallery page
itself now marks Anti-Patterns as the active nav item.
|
||
|
Paul Bakaus
|
0d87b5afb5 |
Overhaul /anti-patterns with visuals, detection layers, and LLM rules
Three additions to the anti-patterns catalog page, all sourced from a
new content/site/anti-patterns-catalog.js file so the user's parallel
edits to src/detect-antipatterns.mjs don't conflict with display metadata.
1. Detection layer badge per rule. Three layers:
cli - static analysis or jsdom. Runs from `npx impeccable detect`
on files, no browser required. 23 of 25 current rules.
browser - needs real browser layout (getBoundingClientRect).
Runs via the browser extension or Puppeteer, not the
plain CLI. Only 2 rules: cramped-padding and line-length,
as documented in tests/detect-antipatterns-browser.test.mjs.
llm - no deterministic detector. Flagged by /critique's LLM
review pass. 13 rules live only in the skill's DON'T list.
Each card renders a mono pill with the layer label, color-coded per
layer (neutral mist for CLI, blue tint for browser, amber tint for LLM).
The How-to-read legend grows a dl explaining what each layer means.
2. Inline visual example per detected rule. All 25 detection rules get
a ~140px tall preview area at the top of the card showing the bad
pattern as live HTML (cream background, self-contained inline styles).
Visuals for side-tab, gradient-text, dark-glow, nested-cards, and the
rest let you see what the detector is actually flagging. LLM-only
rules ship without visuals for now; their card bodies take the full
card height.
3. LLM-only rules merged into the sections. Parsed out from
source/skills/impeccable/SKILL.md DON'T lines that the detector
doesn't cover: Syne, monospace-as-technical, dark-mode-default,
everything-in-cards, identical-card-grids, hero-metric-layout,
glassmorphism, sparkline-decoration, generic-drop-shadows,
modal-reflex, every-button-primary, redundant-headers,
mobile-amputation. Each renders like a detection rule card but
shows the 'LLM only' layer badge and has no rule id chip. They
slot into the same section groups as detected rules (Interaction
and Responsive sections added to the section order so these get
real headings).
- scripts/lib/sub-pages-data.js: imports the catalog, enriches
detected rules with { layer, visual }, appends LLM_ONLY_RULES with
layer: 'llm'. Re-exports LAYER_LABELS and LAYER_DESCRIPTIONS for
the generator.
- scripts/build-sub-pages.js: renderRuleCard adds the visual block
and the layer badge; LLM rules drop the rule id chip since their id
is just an internal slug. groupRulesBySection now extends the
primary order with whatever extra sections rules reference.
- public/css/sub-pages.css: .rule-card now has a .rule-card-visual
preview area on top with border-bottom, body section below. New
.rule-card-layer pill styling per layer. Layer legend dl using a
2-column grid for badge -> description.
Dev server serves 38 total cards (25 detected + 13 LLM) across 8
sections: Visual Details, Typography, Color & Contrast, Layout & Space,
Motion, Interaction, Responsive, General quality.
|
||
|
Paul Bakaus
|
7d7f77d2ba |
Before/after split demos on skill pages + sidebar reorder
Two changes bundled:
1. Before/after split demos on every skill detail page.
- loadCommandDemos() in sub-pages-data.js: dynamically imports each
module in public/js/demos/commands (the same files the homepage
uses), returning a { skillId: { id, caption, before, after } } map.
Falls back to a warn-and-continue if a demo file can't be loaded
so one bad demo doesn't break the whole generator.
- buildSubPageData becomes async; caller in build-sub-pages.js
awaits it.
- Each skill object gets a .demo field (may be null for /shape).
- renderSkillDemo() produces the .split-comparison markup matching
the homepage: .split-container with .split-before + .split-after
+ .split-divider, plus Before/After labels and the caption. The
block sits between the detail header and the editorial wrapper
so readers see the visual before reading any prose.
- sub-pages.css ports the core .split-* layout from main.css (the
.slop-* and .impeccable-* helpers are homepage-specific and not
copied). Height is 360px to match the docs column.
- render-page.js grows a lightweight inline split-compare init
script (60 lines of vanilla JS) that handles drag and the skewed
clip-path without depending on the homepage's full lerp/ResizeObserver
module. Runs only on pages that actually have .split-container.
2. Sidebar reorder: Tutorials first, then skills.
Walk-throughs are the on-ramp; they belong at the top of the sidebar
where a new visitor will find them. Add <hr class="skills-sidebar-divider">
between the Tutorials group and the first skill category so the two
sections read as distinct.
Verified: /skills/polish, /skills/bolder, /skills/critique all render
the demo block. /skills/shape correctly has none. Sidebar on any /skills
or /tutorials page shows Tutorials first, then a thin mist divider,
then Create / Evaluate / Refine / Simplify / Harden / System skill
categories.
|
||
|
Paul Bakaus
|
a89f7f5040 |
Polish pass on editorial wrappers and skill detail layout
Feedback round from first review of the skill pages. Six concrete fixes:
1. Contain the auto-rendered SKILL.md in a distinct card.
The "skill itself" section was flowing straight into the editorial
wrapper above, making the two blocks read as one long mixed
document. Wrap the canonical body in .skill-source-card: white
paper background, mist border, rounded, with a small "SKILL.md"
badge header and an italic subtitle. Drop the old full-width
divider treatment; the card does the visual separation work.
2. Rewrite the /impeccable "do not fight the opinion" pitfall.
The old text said "fighting the opinion usually produces worse
output", which discouraged informed pushback. Replace with language
that explicitly encourages users with real reasons (brand guideline,
accessibility, user research) to push back; the skill raises the
floor, not overrules your judgment when you have evidence.
3. Move /onboard from create to refine.
Onboarding is refinement of empty states and first-run experiences,
not greenfield creation. Fixed in:
- scripts/lib/sub-pages-data.js SKILL_CATEGORIES
- public/js/data.js commandCategories
Both locations now list onboard under 'refine'.
4. De-dupe overdrive and animate.
- overdrive: "how it works" listed 7 techniques as bullets and then
"try it" listed 5 concrete examples using the same 7 techniques.
Collapse "how it works" into a tight paragraph and make "try it"
a specific scenario instead of a laundry list.
- animate: pitfalls repeated the "no layout properties" rule that
was already stated in "how it works". Drop the duplicate.
5. Remove outdated tutorial guidance.
getting-started.md said "Cursor needs Nightly channel plus Agent
Skills in Settings. Gemini CLI needs the preview version." Neither
is true anymore. Replace with a generic pointer to check the
harness's own skill docs.
6. Embed the live visual overlay in critique-with-overlay tutorial.
The tutorial now renders the same demo iframe the homepage uses
(/antipattern-examples/visual-mode-demo.html) inside step 2, with
a mac-window chrome frame that mirrors the homepage preview. New
.tutorial-embed CSS in sub-pages.css defines the header with
traffic-light dots + mono title, the iframe body (520px tall),
and an optional caption. The user now sees the overlay in action
before being asked to run it locally.
|
||
|
Paul Bakaus
|
80d7502737 |
Extend docs-browser shell to detail pages, tighten sidebar, ban em dashes
Builds on the /skills overview landing. Every skill detail page now lives
inside the same sticky-sidebar shell, with the active skill marked via
aria-current and pulled out of the list with a 2px accent border.
- scripts/build-sub-pages.js: detail pages now wrap the .skill-detail
body in wrapInDocsLayout() and pass currentSkillId into the sidebar
renderer so the active row is marked
- public/css/sub-pages.css sidebar pass:
- Narrow from 260px to 200px (was way too wide for the content)
- Drop the redundant "Skills" label at the top (it was visually
competing with the category titles); keep the node for a11y via
visually-hidden styling
- Group titles shrink to 0.625rem mono uppercase in --color-ash so
they read as quiet signposts, not headings
- Tighten item line-height to 1.5 and vertical padding to 3px
- Replace the box-shadow inset accent with a border-left accent on
the active item, leaving it visually pulled left
- Simplify .skill-detail sizing so it works inside .skills-main
without its own max-width / padding
- Ban em dashes in user-facing copy everywhere:
- Rewrite 9 copy lines in index.html, 2 title tags in gallery.html,
inline category descriptions, the /skills overview lede + how-to,
two skills-generator comments, one aria-label, and the page titles
for Skills and skill detail pages
- New validateNoEmDashes step in scripts/build.js scans content/site,
public/*.html, and the sub-page generator sources. Build fails on
any — or — in user-facing copy. Uses commas, colons, periods,
or parentheses instead
Build green: all 26 HTML entrypoints bundle cleanly, all four hand-authored
pages retain the shared site header, anti-pattern rules still match
SKILL.md, zero em dashes.
|
||
|
Paul Bakaus
|
7847daffff |
Generate /skills index + 21 auto-rendered skill detail pages
Ships the first new sub-page section. Every user-invocable skill now has
its own page at /skills/{id}, with the canonical SKILL.md body rendered
via marked. The index at /skills lists all 21 skills grouped by category.
Editorial wrappers are opt-in: if content/site/skills/{id}.md exists, it
renders above the canonical body (with a "The skill itself" divider).
All 21 pages currently ship with the auto-rendered body only; hand-written
wrappers land in the next few commits.
- scripts/lib/sub-pages-data.js: builds the data model. Reuses
readSourceFiles() from lib/utils.js for skill content; parses the
ANTIPATTERNS array out of src/detect-antipatterns.mjs; reads optional
editorial wrappers from content/site/skills/*.md; validates that every
user-invocable skill has a category entry (build fails loudly if not).
- scripts/build-sub-pages.js: orchestrator. Writes generated HTML into
public/skills/*.html (gitignored). Called from both scripts/build.js
(before buildStaticSite) and server/index.js (at module load) so dev
and prod share the same generation code path.
- scripts/lib/render-page.js: new assetDepth parameter so generated
pages one level deep under public/ use relative paths (../favicon.svg,
../css/sub-pages.css) that Bun's HTML loader can resolve on disk.
- scripts/build.js: pass generated files into Bun.build entrypoints;
post-process to flatten build/public/* → build/* (Bun preserves the
public/ prefix when entrypoints span multiple depths).
- server/index.js: generateSubPages() runs at module load; new routes
/skills, /skills/:id, /anti-patterns, /tutorials, /tutorials/:slug
serve the pre-generated files via Bun.file().
- public/css/sub-pages.css: adds sub-page layout shell, skills index
grouped-list styling, skill detail header/meta chips/divider, collapsed
<details> reference sections, and a .prose block for rendered markdown
with editorial typography, code blocks, and inline code.
Verified: bun run build produces 26 HTML files (4 hand-authored + 22
generated), all flat under build/. Dev server returns 200 on /skills,
/skills/polish, /skills/impeccable, /skills/critique. Tests pass.
|