mirror of
https://github.com/pbakaus/impeccable.git
synced 2026-09-12 22:26:38 +03:00
de9aa13a53443c87265da964cceac589dbc4d6ef
11
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
   
|
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 |
||
|
Paul BakausandClaude Opus 4.7
|
1ba75a820e |
fix(skill): 3 review-bot findings from EAC PR
1. cleanup-deprecated: strip `i-` prefix before fingerprint lookup so
`i-harden` / `i-optimize` classify correctly (regression from the
prefixed-naming migration).
2. build: substitute `{{scripts_path}}` in reference/*.md the same way
it's substituted in SKILL.md. Previously the placeholder survived
unresolved in built reference files, so any reference that told the
agent to run a scripts path emitted a literal `{{scripts_path}}` to
the shell.
3. live-poll: drop the `undici` import. Node's built-in fetch enforces a
300s headers timeout that can't be lowered per-request, so we now cap
each poll slice at 270s and loop internally until a real event or the
caller's total timeout. Removes the hard `ERR_MODULE_NOT_FOUND`
failure when undici isn't transitively hoisted.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Paul BakausandClaude Opus 4.6
|
4092ee5f22 |
Move PID file to project root (.impeccable-live.json)
os.tmpdir() returns /var/folders/.../T/ on macOS, not /tmp/. The skill reference was telling the agent to cat /tmp/impeccable-live.json which didn't exist. Moving the PID file to the project root makes it predictable across platforms and project-scoped (multiple projects can run independent live sessions). Changed in: live-server.mjs, live-poll.mjs, live.md reference. Added .impeccable-live.json to .gitignore. 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
|
2233d82f3a |
Bump skills to 3.0, remove prefixed bundle, redesign install section
- Bump skills plugin version 2.1.1 -> 3.0.0 (plugin.json, marketplace.json, harness SKILL.md files). CLI and Chrome extension unchanged. - Remove prefixed universal zip bundle and all related code: factory.js prefix/outputSuffix options, zip.js variant pass, utils.js prefixSkillReferences, the "universal-prefixed" entry in download-providers.js, and the matching test suite in utils.test.js. - Redesign Get Started step 1 "Install the skill and CLI": two terminal rows (npx skills + npm i -g impeccable) with paired notes, drop the Recommended badge. - Collapse "Other install methods" back into a <details> element so the primary install path is the first thing users see. - Simplify step 3 to "Add the Chrome extension": remove the CLI tool block (now in step 1), use standard .btn .btn-primary for the CTA so it matches other primary buttons (square corners, accent slide-up hover), and lay out the preview screenshot next to the button instead of stacked so the screenshot no longer dominates vertical space. - CLAUDE.md: rewrite with v3.0 architecture, the "no em dash also means no --" rule, the harness-dirs-are-tracked gotcha, the named-export test-spy warning, and the evals inline-skill.ts sync note. - AGENTS.md, DEVELOP.md: drop prefixed variant references. 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
|
7670d1325a |
Show actual skills version, not CLI version; normalize version for hash
- Build system now injects skills version (from plugin.json) into every SKILL.md frontmatter as a version field - CLI reads the version from the local impeccable SKILL.md and displays it in check/update output - Hash comparison normalizes the version field (so a version bump alone doesn't trigger a full re-download) - Removed misleading CLI version display from skills commands CLI bumped to v2.1.5. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
Paul BakausandClaude Opus 4.6
|
c2b72b9d44 |
Fix: factory transformer was not copying skill scripts to dist
The refactored factory.js transformer dropped script file support that existed in the old shared.js version. Scripts were read from source but never written to dist/, so npx skills installed skills without the cleanup-deprecated.mjs script, causing errors on first load. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
Paul BakausandClaude Opus 4.6
|
112317fd05 |
Rebase Trae support onto new factory architecture
Merge main (factory refactor) and adapt Trae to use the config-driven transformer system instead of a standalone trae.js file. Two provider entries (trae-cn, trae) replace the custom dual-directory logic. Also adds placeholderProvider support to the factory for providers that share placeholder configs but need separate output directories. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
Paul BakausandClaude Opus 4.6
|
7c208cdfbb |
Merge main and integrate command_prefix support into factory
Resolve conflict from codex.js (deleted in our branch, modified on main for command_prefix). The command_prefix feature from main is preserved in factory.js via PROVIDER_PLACEHOLDERS lookup. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
Paul BakausandClaude Opus 4.6
|
6de73abf1b |
Fix invalid YAML frontmatter and consolidate build transformers
Fixes #67: argument-hint values starting with [ were parsed as YAML flow sequences. Replace structured args arrays in source files with pre-formatted argument-hint strings, and quote values starting with [ or { in generateYamlFrontmatter(). Also consolidates 8 nearly-identical transformer files into a single config-driven createTransformer() factory. Adding a new provider now requires only a config object in providers.js instead of a full file. - Replace args source frontmatter with argument-hint strings - Add YAML quoting for values starting with [ or { - Add quote stripping to parseFrontmatter() for round-trip support - Create factory.js + providers.js, delete 8 individual transformers - Replace 16 explicit build.js calls with a loop over PROVIDERS - Consolidate 8 test files into 2 (factory + providers) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |