Gemini 3 Flash baseline showed the Unsplash bullet wasn't directive
enough — the model still dropped imagery entirely on italian-
restaurant and vintage-moto-forum niches when the brief clearly
implied photography.
Changes:
- Added a MUST-ship-imagery lead paragraph listing the niches that
require photography (restaurant, hotel, magazine, etc.).
- Gave a literal Unsplash URL shape (`images.unsplash.com/photo-{id}?
auto=format&fit=crop&w=1600&q=80`) with real photo-id examples, so
weaker models have a concrete pattern to copy rather than inferring
the URL format.
- Promoted "zero imagery on an imagery brief" into the Editorial bans
list so it lands as a hard rule, not a nudge.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three related extraction bugs surfaced in the EAC session all rooted
in the line-based state machine:
1. `<style ... />` (JSX self-closing) had no separate `</style>` for
the "skip until close" mode to exit on, so the state machine stuck
and every `data-impeccable-variant` marker after it got missed.
Accept reported `handled: false, error: "Variant N not found"`.
2. A variant whose entire `<div ...>...</div>` sits on one line had
its body silently discarded — the marker line was `continue`d past,
and the extractor started capturing from the next line, which
usually belonged to a different variant or the wrapper close.
3. `extractCss` kept scanning for `</style>` after a self-closing
opener, greedily swallowing every subsequent variant div as "CSS".
Result: a mangled carbonize block stuffed with HTML and a duplicate
variant rendered below.
## Fix
Replaced the line-based state machine with a string-based flow:
- `stripStyleAndJoin(lines, block)` returns the wrapper text with
`<style>` elements fully removed. Handles self-closing, same-line
open+close, and multi-line open/close. Markers inside CSS strings
(e.g. `@scope ([data-impeccable-variant="1"])`) are gone by the
time extraction runs — no false positives.
- `extractInnerByAttr(text, attrMatch)` is a balanced-tag matcher that
walks the joined text finding `<TAG ...attrMatch...>…</TAG>` with
proper depth tracking for nested same-tag elements. Handles
single-line, multi-line, and deeply nested variants.
- `extractOriginal` and `extractVariant` are thin wrappers over the
above.
- `extractCss` gets explicit same-line handling: returns null for
self-closing (nothing to carbonize), extracts inner content via
regex for same-line `<style>…</style>`, falls through to the
existing multi-line path otherwise.
## Tests
New tests/live-accept.test.mjs with four cases — all failing before,
all passing after:
- Self-closing `<style />` with dangerouslySetInnerHTML
- Single-line `<style>…</style>`
- Multi-line `<style>...</style>` (regression baseline)
- Discard restores the original element after self-closing style
Wired into `bun run test`. Full suite passes.
Credit: precise repro + root-cause trace from the other agent in the
EAC session.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Five related bugs that surfaced in a real Next.js App Router project
(EAC) all rooted in live-wrap.mjs treating source as line-anchored HTML:
1. findElement matched on raw substring anywhere, so it landed on a
className continuation line of a multi-line JSX tag whose class
happened to collide with a later target. The wrong tag got wrapped
(really, its attribute line got wrapped, producing broken JSX).
2. findClosingLine's opener regex required whitespace or `>` after the
tag name, so a bare `<section\n className="..."\n>` opener was
unrecognised; it returned `start` silently, capturing only one line.
3. buildSearchQueries only emitted `class="..."`, missing React's
`className="..."`. The full-combo query never fired in JSX, so
search silently degraded to single-class substring matching.
4. Wrapper output used `style="display: contents"` unconditionally,
which is invalid JSX (type error in strict setups, parser hazard
in production transforms).
5. --tag was ignored during the primary class search. Ambiguous class
hits inside the wrong element type weren't filtered out.
## Fixes
- New OPENER_RE `/<([A-Za-z][A-Za-z0-9]*)(?=[\s/>]|$)/` recognises
tag openers at end-of-line too.
- New findOpenerLine(lines, matchLine, tag): walks up to 10 lines
backward to the enclosing opener when the match lands on a
continuation line. Aborts the walk if it hits a different tag.
- findElement now iterates all matches (not just the first), takes
a tag parameter, and routes through findOpenerLine; wrapCli passes
--tag through.
- buildSearchQueries emits both `class="..."` and `className="..."`
for multi-class queries, and both `<tag class="..."` /
`<tag className="..."` for tag+class combos.
- Wrapper builder emits `style={{ display: "contents" }}` when
commentSyntax is JSX and `style="display: contents"` otherwise.
- findClosingLine uses the same OPENER_RE so its tag-name extraction
works on multi-line openers too.
## Tests
Five new regression tests in tests/live-wrap.test.mjs, all failing
before the fix, all passing after:
- wraps the correct <section> when a class collides with a multi-line
tag elsewhere
- emits JSX-safe style attribute ({{ }}) in .tsx files
- finds elements via className= (React) when the exact class combo is
unique there
- respects --tag to reject matches inside the wrong element type
- findClosingLine recognises an opener line where the tag sits at
end-of-line (multi-line JSX)
31/31 in tests/live-wrap.test.mjs and 54/54 in
tests/framework-fixtures.test.mjs pass.
Credit: precise bug report from the other agent in the EAC session
made diagnosis and test design straightforward.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The content heuristic for deciding whether a deprecated skill dir belongs
to us returned false for harden and optimize (their v2.x SKILL.md never
said "impeccable"), while lock-entry cleanup used the authoritative
source field. Result: lock entries purged, dirs orphaned.
Layer three signals now: lock source (authoritative), word heuristic,
then per-skill description fingerprints for the two stock v2.x skills
that predate the self-identification convention.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Shape names renamed to describe the patch mechanism (what the agent does)
rather than the origin (where the CSP lives). One template now covers
multiple frameworks.
## Shape rename
- shared-helper → append-arrays
- inline-headers → append-string
append-arrays applies wherever CSP is a structured directive array.
append-string applies wherever CSP is a literal value string.
## New detection coverage
- SvelteKit kit.csp.directives in svelte.config.js → append-arrays
- Nuxt routeRules / nitro.routeRules CSP header → append-string
- Nuxt-security module's contentSecurityPolicy → append-arrays
## New fixtures
- sveltekit-csp/: SvelteKit config with kit.csp.directives. Includes
expected-after-patch.js showing the array spread.
- nuxt-csp/: Nuxt 3 config with routeRules CSP. Includes
expected-after-patch.ts showing the string splice.
## Skill docs
Single append-arrays template covers Next monorepo, SvelteKit, and
Nuxt-security. Single append-string template covers inline Next
headers() and Nuxt routeRules. Per-framework specifics listed as
sub-bullets under each shape.
54 tests across 9 fixtures, all passing. Clean fixtures (plain vite,
nextjs-app, astro, sveltekit, multipage-with-generator) still classify
as shape: null.
Astro and Vue (non-Nuxt) left unhandled by design: Astro has no
first-party CSP mechanism; Vue without Nuxt is covered by the existing
Vite fixture. Plain Svelte has no framework CSP primitive and inherits
from its bundler (Vite/Rollup).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Real-world tests (EAC Next turborepo) confirmed that CSP is the common
blocker for live mode. Adds setup-time detection with a one-time user
consent flow — the patch becomes a permanent, dev-guarded entry in the
user's own config, not a transient add/remove.
## Changes
- New detect-csp.mjs helper: grep-based classifier returning
{ shape, signals }. Shape is one of:
- "shared-helper" (monorepo CSP helper with additional*Src arrays)
- "inline-headers" (literal CSP string in headers())
- "middleware" (response.headers.set in middleware.ts; detect-only v1)
- "meta-tag" (<meta http-equiv>; detect-only v1)
- null (no CSP)
Max depth 6, skips node_modules / build / cache dirs, 64KB per file.
- cspChecked boolean on config.json. First-run setup runs detection;
subsequent runs skip. Users re-trigger by deleting the flag.
Validator accepts it.
- Skill live.md gains:
- CSP detection step in first-time setup (gated by cspChecked)
- Consent-prompt template (so every agent phrases it the same way)
- Shape 1 patch template: append `...__impeccableLiveDev` to
additionalScriptSrc/additionalConnectSrc in the app's config
- Shape 2 patch template: two-point edit — declare a dev-only
variable, interpolate into script-src and connect-src in the
CSP literal string
- Troubleshooting note for "said no but now live doesn't work"
## Fixtures
- nextjs-turborepo/: Turborepo shape (shared CSP helper with
additionalScriptSrc options). Sanitized from a real monorepo so the
patch mechanics get tested against realistic layering. Includes
expected-after-patch.ts for human/agent review.
- nextjs-inline-csp/: app-level next.config.js with a literal CSP
string. Includes expected-after-patch.js showing the Shape 2 edit.
## Tests
Framework-fixture harness extended with a detect-csp shape-classification
assertion per fixture. 42 tests across 7 fixtures pass. Clean fixtures
(vite-react, nextjs-app, astro, sveltekit, multipage-with-generator)
correctly return shape: null.
## Deliberately not doing
- No patches[] array, no marker-based rollback, no add/remove lifecycle.
The patch is a permanent dev-guarded config line — the same kind of
edit a user would make themselves.
- No base URL rewriting or proxy mechanism. Script tag still points at
localhost:8400; CSP permits it once patched. No browser-side changes.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Five representative project shapes under tests/framework-fixtures/ that
stage into fresh tmp git repos and drive the live scripts against each:
- vite-react: tracked index.html shell + src/App.jsx
- nextjs-app: app/layout.tsx as JSX inject target
- astro: src/layouts/Layout.astro
- sveltekit: src/app.html shell + src/routes/+page.svelte
- multipage-with-generator: src/ tracked, dist/ gitignored (our own
repo's shape); exercises the is-generated guard and
element_not_in_source fallback
Each fixture declares its config, expected source/generated paths, and
wrap cases in fixture.json. The harness copies into tmpdir, applies
gitignore, commits, then asserts:
- inject --port lands the script tag at the correct anchor across all
configured files
- inject --remove strips it cleanly
- is-generated classifies source vs generated paths correctly
- wrap routes to the expected source file or emits the expected
fallback error
Plumbing + bug caught while building out the matrix:
- IMPECCABLE_LIVE_CONFIG env var so tests can point live-inject at a
fixture-specific config.json without clobbering the harness copy.
Backwards-compatible.
- live-wrap.mjs no longer hardcodes dist/build in its directory skip
list. Only node_modules and .git remain universal skips; the
isGeneratedFile check is now the sole guard for generated paths. This
lets the includeGenerated second pass find elements in dist/ and
report generatedMatch, which is what the multipage-with-generator
fixture needs to exercise.
Wired into bun run test. 25 tests, 5 suites.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Addresses every issue surfaced during hands-on live-mode testing.
## Injection across multi-page sites
- Config schema: `file` → `files: string[]` so multi-page static sites can
opt into script-tag injection across every HTML entry the browser loads.
- `live-inject.mjs` loops the array, reports per-file results, and
refuses silently with `config_invalid` if the schema is stale.
- `insertBefore` switched from first-match to last-match (lastIndexOf)
so the anchor lands at the true close of `</body>`, not the first one
embedded inside a `<pre><code>` documentation sample.
## Source-vs-generated detection
- New `is-generated.mjs` helper: gitignore check + generated-header
markers. Edge-case `generatedFiles` config dropped — the two real
signals cover every project shape we tested.
- `live-wrap.mjs` excludes generated files from auto-search and returns
clear fallback errors: `file_is_generated`, `element_not_in_source`
(with `generatedMatch` path), and `element_not_found`.
- `live-accept.mjs` refuses to persist into generated files; returns
`mode: "fallback"` so the agent takes over via the Handle fallback
flow.
## Accept correctness
- `extractVariant` / `extractOriginal` now skip `<style>` regions when
matching markers. Previous regex substring match treated
`@scope ([data-impeccable-variant="N"])` in CSS as the target HTML
div, capturing garbage and producing orphan CSS that rendered as
prose on the page.
- On accept, the chosen variant's content is wrapped in
`<div data-impeccable-variant="N" style="display: contents">` so the
carbonize block's `@scope` selectors keep matching. Users see the
accepted design immediately; no pre-carbonize dead state.
## Browser-side UI
- `positionBar` gains a third case: when the selected element is taller
than the viewport, pin the bar to a stable viewport anchor instead of
teleporting between top and bottom as the user scrolls.
- No-HMR source-fetch path (`injectVariantsFromSource`) now calls
`hideShaderOverlay()` on state transition to CYCLING. Previously the
shader kept running after variants arrived via the fetch fallback.
- `pickVariantContent` helper replaces fragile `> :first-child`
selection for outline positioning. Skips non-visual tags (style,
script, link, meta, template) and falls back to the variant div
itself when a variant contains multiple visual children.
- `resumeSession` re-captures and restarts the shader overlay when
the page reloads mid-generation (Bun HTML HMR does a full reload
and destroys the canvas).
- MutationObserver re-anchors `selectedElement` when the original
element is detached by HMR, preventing zero-rect highlight drift.
## Skill docs
- `live.md` reframes `config.files` as "the HTML files the browser
actually loads" and documents the regen-wipes-inject caveat for
multi-page generator projects.
- New Handle fallback section covers the three wrap error shapes and
how the agent should manually wrap for preview and commit to real
source on accept.
- Handle accept documents the new `data-impeccable-variant` wrapper
and the carbonize agent's duty to strip it.
## Prefetch feature (landed but disabled)
A `prefetch` event fires from the browser on first CONFIGURING per
route so the agent can pre-Read the source file before Go. Real latency
win in the linger-before-Go case but costs a harness round trip when
Go fires quickly. Disabled via a `PREFETCH_ENABLED = false` flag in
`live-browser.js`; server validator and skill dispatch stay so re-
enabling (with a browser-side debounce) is a one-line change.
## Harness guidance
Earlier skill rewrite compressed two load-bearing instructions:
- Restored prescriptive wording for "open the tab via Chrome MCP
before the first poll" and the Claude Code background-poll policy.
- Flag-mapping for `live-wrap` rewritten as explicit bullets so models
don't collapse `--element-id`/`--classes`/`--tag` into a single
`--query` argument.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Bun's HTML HMR does a full page reload when the live-wrap.mjs edit
lands, so the shader canvas is destroyed and in-memory capture blob is
lost. resumeSession rehydrated state from localStorage but never
restarted the overlay, so the wait went dead.
resumeSession now re-captures the original's content (still in the DOM
inside the variant wrapper) and restarts showShaderOverlay when we
reload mid-generation. Also swaps the two remaining :first-child
selectors in resumeSession for pickVariantContent so the earlier
loose-children robustness fix carries across reloads.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two regressions surfaced in smoke testing, both traceable to state
drift when live-wrap.mjs rewrites the source file and HMR swaps the
DOM.
1. Variant outline on the wrong element. The skill rewrite lost the
explicit "each variant must be a complete element replacement"
rule and dropped the "full element replacement" comments from
variants 2 and 3. Models started producing variants with loose
sibling children, so live-browser's :first-child selector framed
only the first sibling. Restored the rule, made all three comments
consistent, and replaced :first-child with pickVariantContent —
which skips non-visual tags (style/script/link/meta/template) and
falls back to the variant div itself when a model still ships
multiple visual children.
2. Loading shader freezes after wrap. The MutationObserver only woke
up when new non-original variants arrived, so when the wrapper
first appeared via HMR with just the original inside, selectedElement
was left dangling on the now-detached pre-wrap node. Scroll-tracking
read a zero rect on every frame and collapsed the shader canvas to
0x0. The observer now re-anchors selectedElement to the original's
content the moment the wrapper shows up, keeping overlays positioned
until real variants land.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The skill rewrite compressed two load-bearing instructions into ambient
context:
- "Navigate the browser to the URL" lost the signal that models with
Chrome MCP should proactively open the tab before the first poll.
Restored the forcing phrasing and the "before the first poll" anchor.
- "Claude Code can background the poll" read as permission rather than
prescription. Models fell back to foreground blocking by default.
Restructured harness guidance as a bulleted policy, prescriptive per
harness, with the reason attached (harness notifies on completion so
the conversation stays free).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Splits the skill into two register references (editorial, product),
replaces category-based theme selection with a forced physical-scene
inference, and introduces a four-step color strategy axis (Restrained /
Committed / Full palette / Drenched) with editorial permission for the
bold three.
Adds a seed mode to /impeccable document for pre-implementation
projects, updates /impeccable teach Step 5 to offer the seed path, and
grows /impeccable shape with Design Direction + Scope intake
(fidelity, breadth, interactivity, time). Extends live-mode variant
distinctness to forbid three variants sharing theme and dominant hue.
Also drops the anti-pattern validator coupling, consolidates a11y into
audit.md, and updates CLAUDE.md with the register architecture.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds a full annotation pipeline to /impeccable live. On Go, the browser
captures the selected element as a PNG (with annotations composed in),
uploads it to the live helper, and sends the generate event with the
screenshot path so the agent reads user intent visually instead of from
HTML alone.
Annotation tools (while an element is picked):
- Click inside the outline to drop a magenta comment pin with a text input
- Drag to paint a magenta SVG stroke (5 px click-vs-drag threshold)
- Click a pin to edit; double-click to delete; drag a pin to reposition
- Click a stroke to delete it (wider invisible hit path)
- Clear chip top-right wipes everything; hidden when no annotations
Capture pipeline:
- modern-screenshot vendored as an IIFE (scripts/modern-screenshot.umd.js)
and lazy-loaded from the live helper
- Font fix: cross-origin @font-face rules are fetched and fonts are inlined
as base64 data URIs before being handed to modern-screenshot via
font.cssText, since SVGs rasterized via canvas can't fetch external
resources (fix for "Impeccable" rendering bold-serif and items wrapping
wrong in the capture)
- Annotations are temporarily attached to the live element (not only the
clone) so computed styles resolve during the embed pass
- Session screenshots live in .impeccable-live/annotations/session-*/ in
the project root (gitignored) so the agent's Read tool doesn't trip a
per-path permission prompt
Loading shader (activates during GENERATING):
- WebGL overlay rendering the captured PNG as a halftone — cells with
luma-driven dot radius, rendered on paper-cream underneath a magenta
roller that sweeps top-to-bottom with a 3.4s cycle and clean overshoot
- Fixed asymmetric bandAt() using one-sided smoothsteps (previous reversed
smoothstep was undefined on d>0, giving "trail=1 everywhere below")
- Graceful <img> fallback when WebGL is unavailable; prefers-reduced-motion
freezes the band at t=0
Server:
- POST /annotation endpoint (raw image/png body, token + eventId query),
session-scoped tmpdir cleaned up on shutdown
- GET /modern-screenshot.js serves the vendored UMD with aggressive caching
- Optional screenshotPath / comments / strokes fields on generate events
- Fixed pre-existing /source crash on ENOENT (writeHead called twice)
Agent side:
- reference/live.md step 0 tells the agent to Read the screenshot first,
with four rules for interpreting annotations: comments are position-
anchored and scoped to the sub-element under their {x,y}; strokes are
gestures (loop=focus, arrow=direction, cross=delete); comments and
strokes are independent unless adjacent; don't silently guess on
ambiguous strokes
Also:
- Generating bar no longer claims "Generating 1 of 3..." (variants arrive
atomically) — now says "Generating N variants..."
- tests/live-server.test.mjs fixed to read the PID file from project root,
matching the server; adds coverage for the new endpoints and validator
fields
- .impeccable-live/ added to .gitignore
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
live-server.mjs stop now runs live-inject.mjs --remove after the HTTP
server shuts down, so HTML entries do not keep loading a dead localhost
live.js URL. Add stop --keep-inject to stop only the helper.
Update reference/live.md cleanup steps and sync all provider skill copies.
Made-with: Cursor
Document that Cursor Composer should run live-poll blocking in the same turn
(with a link to Cursor subagent foreground vs background docs). Claude Code may
use a background poll when the harness surfaces completion. Sync reference to
all provider skill bundles.
Made-with: Cursor
typography.md had a parallel 4-step font-selection procedure and a smaller
banned-fonts list (5 fonts: Inter, Roboto, Open Sans, Lato, Montserrat)
that duplicated SKILL.md's authoritative <font_selection_procedure> with
its 23-font list. Removed the duplicate procedure and deferred to SKILL.md
for the banned list. Kept the unique material: anti-reflex corrections,
system-font note, pairing principles, web font loading, OpenType, fluid
type guidance, accessibility — and all of the scale/rhythm/measure
content that SKILL.md doesn't cover.
pin.md removed for the same reason as context.md: SKILL.md's inlined
pin section already covers what an agent needs (what pin does, usage,
valid commands, how to report back). No value in the indirection.
SKILL.md: 386 → 388 lines (slight growth from inlining pin details)
typography.md: 142 → 132 lines
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The main skill now has enough detail to stand alone: two files, load
command, no-truncate rule, never-infer warning, session cache, teach
fallback, DESIGN.md nudge, and the live-mode "already warmed"
exception. context.md was indirection without added value.
Inlined the two bits from context.md worth keeping:
- Content validity: treat empty / <200 chars / [TODO]-placeholder
PRODUCT.md as missing
- live.mjs auto-warms, don't double-load with load-context.mjs
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Before: 422 lines. After: 386 lines. The cut is conservative because
evals/AGENT.md revealed that most of what looked like bloat is actually
load-bearing: the font_selection_procedure with its 23-font ban list
(lesson 6), the theme_selection with audience examples (lesson 9), and
the absolute_bans with literal CSS patterns (lesson 7) all drive
measurable eval improvements and must stay inline.
What moved out of SKILL.md:
- Context Gathering Protocol (52 → ~18 lines). The full protocol — cache
semantics, dispatch tree, teach/document/live exceptions, why-it-matters
— moved to reference/context.md. SKILL.md keeps only the compact hook:
load command, "never infer from codebase" warning, and pointer.
- Pin/Unpin (14 → 6 lines). Details moved to reference/pin.md.
- Spatial principles: dropped 4pt-vs-8pt rationale, gap-vs-margins CSS
technicality, and container-queries-vs-viewport explanation (not
load-bearing in the main skill). Kept all load-bearing rules
including the 80-char body-text line (detector-backed).
What did NOT move (load-bearing per evals):
- <font_selection_procedure> with the 23-font ban list
- <theme_selection> with the 8 audience examples
- <absolute_bans> with literal CSS patterns
- All XML tag structure (lesson 8: XML works better than markdown
for reasoning models, especially OpenAI)
Also added:
- reference/context.md (new) — full context protocol
- reference/pin.md (new) — full pin/unpin docs
- "Never infer brand, audience, or tone from the codebase" warning
restored to SKILL.md (was dropped in an earlier refactor)
Fixed:
- reference/colorize.md had "Accent borders: Add colored left/top
borders to cards or sections" which directly contradicted
SKILL.md's absolute_ban on border-left/right > 1px. Rewrote the
accent-border advice to use hairline borders, surface tints, or
leading glyphs instead, with an explicit reference to the ban.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two observed failure modes:
1. Smoke-test style truncation (`| head -N`) in bash commands defeats the
whole point of load-context.mjs — Claude needs the FULL file contents,
not the first few lines of JSON.
2. The old protocol didn't clearly explain session caching, leading to
repeated load-context.mjs calls across commands in the same session
(thousands of wasted tokens on 3-5KB files re-fetched 3-5 times).
Context Gathering Protocol rewrite:
- PRODUCT.md required (blocker), DESIGN.md optional (one-line nudge if
missing). Greenfield projects can't yet have a DESIGN.md to document.
- Explicit session cache: if content is in conversation history, do not
re-fetch. Exceptions listed (after teach/document/manual edit).
- Explicit "never truncate" rule: consume the full load-context.mjs
output, never pipe through head/tail/grep/jq with field filters.
- Content validity check: hasProduct=true but content <200 chars or
full of [TODO] markers = treat as missing, run teach.
- Missing-PRODUCT.md flow spells out task resumption: user asked for
/impeccable polish ButtonGroup, we must run teach, then RESUME polish
of ButtonGroup with fresh context — not silently abandon intent.
- Three explicit exceptions to the protocol:
- /impeccable teach skips it (teach creates PRODUCT.md)
- /impeccable document loads PRODUCT.md only (creates DESIGN.md)
- /impeccable live already warms context via live.mjs — don't also
run load-context.mjs
teach.md Step 6 and document.md Step 5 now re-run load-context.mjs at
the end so the freshly-written files surface in conversation history
and subsequent commands use the new version, not a stale earlier read.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The format at https://stitch.withgoogle.com/docs/design-md/format/ defines
exactly six sections in a fixed order: Overview, Colors, Typography,
Elevation, Components, Do's and Don'ts. Our previous format used
non-compliant names (Visual Theme & Atmosphere, Color Palette & Roles,
Typography Rules, Component Stylings), a non-existent "Layout Principles"
section, and had no Do's and Don'ts.
Changes to reference/document.md:
- Fixed section list to match the spec character-for-character
- Added mandatory "Creative North Star" pattern at top of Overview
- Added Named Rules pattern (e.g. "The No-Line Rule") — stickier than
bullet lists for AI consumers, mirrors Stitch's own generator output
- Added explicit Do's and Don'ts section with concrete, forceful guardrails
- Elevation is now its own section (was buried in Components)
- Layout/motion/responsive content folds into Overview + Components
rather than inventing new top-level sections
- Guidance on forceful voice ("prohibited"/"forbidden"/"never") matching
PRODUCT.md's expert-decisive tone
- Pitfalls section warns against renaming sections or adding new ones
Changes to our DESIGN.md:
- Rewrote to use spec-compliant section headers with evocative subtitles
(e.g. "## 2. Colors: The Warm-Paper Palette")
- Opened with "Creative North Star: The Editorial Sanctuary"
- Added 11 Named Rules across sections (The One Voice Rule, The Paper-
Not-White Rule, The OKLCH-Only Rule, The Italic-Is-Voice Rule,
The 1.6 Leading Rule, The Fluid-Headlines-Only Rule, The Flat-By-
Default Rule, The Low-Alpha Rule, The Tinted-Shadow-Only-For-Accent
Rule, plus the existing implicit ones)
- Full Do's and Don'ts section with 10 Dos and 15 Don'ts, many of which
translate PRODUCT.md anti-references into concrete prohibitions
- Elevation section documents shadow vocabulary separately from Components
- Layout/spacing/motion content relocated to a sub-section under Components
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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>
Previously only bolder/quieter/animate/colorize/typeset/layout had
variant diversity rules. Added the same level of guidance for distill,
polish, adapt, delight, and overdrive so every live action has a
clear "each variant must differ on THIS axis" rule.
Also noted that overdrive should skip its reference's "propose and ask"
step in live mode (it's non-interactive — the user picks from variants).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two failure modes observed:
1. Claude generates N near-identical variants (small shade/size tweaks)
instead of meaningfully different design directions
2. When a sub-command like /bolder is chosen in the picker, Claude skips
loading reference/bolder.md and generates generic variants
Fixes:
- "Load reference file" is now a MANDATORY Step 2a, separate and
non-negotiable, called out as a critical failure to skip
- Added Step 2b "Plan 3+ distinctly different directions" with 7
structural axes variants must differ on (hierarchy, layout topology,
typography system, color strategy, density, tone, decomposition)
- Added action-specific diversity rules (bolder = different dimensions,
animate = different motion vocabulary, colorize = different hues, etc.)
- Freeform prompt guidance: honor the prompt direction but explore
meaningfully different interpretations, not three near-copies
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Previously, starting live mode required ~5-6 sequential bash calls:
read .impeccable.md, start server, check config, read reference, inject
tag, verify. The new live.mjs does all of this in a single command
(~340ms cold, ~90ms when reusing a running server) and returns everything
the agent needs in one JSON blob.
Workflow is now:
1. node live.mjs # start + inject + load context (1 bash call)
2. navigate browser # optional MCP call
3. node live-poll.mjs # enter poll loop
Reference doc collapsed to a single "Start Live Mode" section with the
one-command path plus a first-time config creation fallback.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
First live run: agent auto-detects framework and writes a small config.json
(file, insertBefore/insertAfter anchor, comment syntax). Every subsequent
run: live-inject.mjs handles insert/remove deterministically, no LLM needed.
The config lives at {scripts_path}/config.json and is gitignored — it's a
per-project cache that wipes on skill update and regenerates on next use.
- New live-inject.mjs: --port (insert), --remove, --check modes
- Idempotent insert: re-running with a different port replaces cleanly
- Reference doc: one-time detection step, then instant insert/remove
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Arrow keys now pass through to element picker when the freeform input
is empty, instead of being swallowed by stopPropagation
- Arrow nav works in both PICKING and CONFIGURING states, so you can
change your element selection while the config bar is open
- Clicking outside the selected element and bar returns to PICKING mode,
matching the expected deselect behavior
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Accept and discard in live variant mode are now handled by a deterministic
script (live-accept.mjs) that runs inside the poller before returning to
the agent. The browser updates the DOM instantly on click (fire-and-forget)
so the user is never blocked waiting for LLM-driven file cleanup.
Key changes:
- New live-accept.mjs: deterministic accept/discard file operations
- Poller auto-runs accept script for accept/discard events (_acceptResult)
- Browser handleAccept() now commits DOM change instantly, no SAVING state
- CSS+HTML colocated in one write (style tag inside variant wrapper)
- SSE heartbeat every 30s prevents silent connection drops
- Poll timeout increased from 2min to 10min
- EventSource onopen resets retry counter for reliable reconnection
- Server --background flag for clean single-command startup
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Comprehensive architecture decision record covering the live variant
mode: context, key decisions (source modification over DOM patching,
SSE over WebSocket, self-contained skill scripts, HTTP long-poll for
agent), full architecture diagram with message flows, variant wrapper
format, browser UI states, session persistence, security model,
server resilience, performance optimizations, test coverage, known
limitations, and future work.
Also picks up improvements from parallel thread: poll timeout bumped
to 10 min, SSE heartbeat every 30s, and other minor fixes.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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>
CI was running `bun test` which ran jsdom fixture tests in bun, causing
timeouts. Now uses `bun run test` which runs unit tests in bun and fixture
tests in node.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add first-class Pi (pi.dev) provider with transformer, tests, and build integration
- Fix CODEOWNERS username (@paulbakaus → @pbakaus)
- Add missing providers to issue/PR templates (Copilot, Kiro, OpenCode, Pi)
- Add Pi and OpenCode logos to homepage hero and install sections
- Move /onboard from "system" to "enhancement" category
- Update README and DEVELOP.md with all supported providers
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Run tests on push and PR to main
- Build project and upload artifacts
- Use Bun for fast JavaScript runtime
This ensures code quality and prevents regressions.
