Tests the full prefix lifecycle: detecting 'i-' from i-teach-impeccable,
undoing prefix (rename folders + strip from SKILL.md cross-references),
and re-applying prefix after update. Covers the scenario where
npx skills update needs unprefixed names from its lock file.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When skills are prefixed (e.g. i-audit), npx skills update would fail
because its lock file tracks unprefixed names. Now detects the prefix
via teach-impeccable naming, temporarily undoes the prefix (renaming
folders + reverting SKILL.md content), runs npx skills update, then
re-applies the prefix. If update fails, prefix is still restored.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
E2e tests covering: already-installed detection, prefix rename with
cross-reference updates, direct-download update fallback, and full
npx-skills install flow (skipped if npx skills unavailable).
Fixed prefix rename to handle npx-skills symlink layout: real dirs
in .agents/ are renamed and content-prefixed, then symlinks in
.claude/ are recreated to point to the renamed targets. Uses
unlinkSync (not rmSync) for symlinks to directories.
Added -y/--yes flag for non-interactive CI mode, --prefix= flag
for headless prefix selection.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Mirrors the build pipeline's prefixSkillReferences logic: when prefixing
skills after install, now also replaces /command-name invocations and
"the command-name skill" prose references throughout each SKILL.md body.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Check for existing installation (looks for teach-impeccable skill),
bail with message unless --force is passed
- After npx skills add, prompt to prefix commands (default: i-)
with custom prefix support; renames folders and updates frontmatter
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New `impeccable skills` CLI with three subcommands:
- `skills help`: fetches and displays all 20 commands from the API
- `skills install`: delegates to `npx skills add pbakaus/impeccable`
- `skills update`: tries `npx skills update` first; if skills aren't
managed by the skills CLI, downloads the universal bundle from
impeccable.style and overwrites provider folders directly, with
git-based modification detection and confirmation prompt
Also fixes npm metadata: homepage -> impeccable.style, license -> Apache-2.0
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Rename bin/impeccable.mjs to bin/impeccable (npm rejects .mjs in bin)
- Shebang: #!/usr/bin/env node (works without Bun)
- Add README.npm.md with CLI-focused docs, swapped in during publish
- Build browser script to source/ dir so URL scanning works in npm pkg
- Include browser script in files field
- Move website-only deps (archiver, motion, playwright) to devDependencies
- jsdom as dependency, puppeteer as optionalDependency
- Bump version to 2.0.1 across package.json, plugin.json, marketplace.json
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Replace hover outline-offset with outline-color transition (no flicker)
- Label shows type name by default; on hover, detail slides up to replace
it ticker-style with a dark background for visual distinction
- Banner: horizontal scroll with scroll-snap for findings, fixed controls
- Add toggle button to show/hide all overlays
- Overlays use pointer-events:none so page interactions (text selection,
clicks, links) pass through; hover driven via target mouseenter/leave
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When an element already has an overlay from per-element checks (e.g.
side-tab), layout findings (e.g. nested-cards) now merge into the
same overlay label instead of creating a duplicate stacked on top.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Use a document-level transitionend listener instead of per-element
listeners, so overlays reposition when a parent's transform transition
ends (e.g. reveal animations with translateY on an ancestor container).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Overlays for elements inside position:fixed contexts now use
position:fixed with viewport-relative coords, so they stay pinned
on scroll. Extracted shared positionOverlay() helper for consistent
coordinate handling across highlight, reposition, and IO callbacks.
Updated fixture with a real fixed footer scenario.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Overlays are now created hidden and revealed by an IntersectionObserver
(rootMargin: 99999px), so they automatically show/hide when their target
becomes visible or invisible -- handles closed <details>, display:none,
hidden modals, overflow:hidden clipping, etc. without polling.
Adds overlay-positioning.html test fixture with 9 scenario groups
covering transforms, closed details, sticky, overflow, position offsets,
flex/grid, containing-block creators, and combinations.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Each assessment now creates its own tab and labels it ([LLM] or [Human])
so parallel sub-agents don't fight over the same page state.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Merges 54 commits from main including factory-based build system, Trae support,
improved skill descriptions, and security hardening. Consolidates the critique
skill to combine v2.0's sub-agent architecture and automated anti-pattern
detection with main's Nielsen heuristics scoring, cognitive load assessment,
persona-based testing, and structured follow-up workflow. Fixes browser detector
build to create target directory after skill sync.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Restructure the Install section into a "Get Started" two-step flow:
1. Install the skills (npx as primary, alternatives collapsible)
2. Stay up to date (embedded Substack subscribe form)
- Elevate npx command as the sole primary install method
- Collapse Claude Code marketplace and manual ZIP into expandable alternatives
- Replace hidden prefix toggle with prominent radio card selector
- Download button dynamically updates label based on prefix choice
- Add Substack newsletter embed (impeccablestyle.substack.com)
- Add newsletter link to footer alongside blog link
- Normalize button styles for consistency (square corners for actions)
- Add newsletter icon assets (SVG + PNG) for Substack branding
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add floating bottom section nav (appears after hero, hides at footer)
- Fix hero split comparison to default 50/50 instead of 70/30
- Remove duplicate "Works with" badges from Install section
- Periodic table: restore compact elements, add inline hover tooltips
- Truncate command descriptions in Commands section for scannability
- Collapse older changelog entries behind "View older releases"
- Add GitHub star count (13.3k) next to repo link
- Fix meta theme-color to match light mode
- Reduce hero top padding, update section 03 subtitle
- Clean up footer: remove redundant tagline and anchor links
- Fix divider line accumulation in changelog and FAQ sections
- Center glass terminal vertically in viewport
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Simplified to substantive changes only (no whitespace reformatting):
- Add escapeHtml() for API-derived text in pattern tab/panel rendering
- Add CSS.escape() + null guard for tab panel selector lookup
- Add clipboard fallback for non-HTTPS / older browsers
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Take PR's improved skill descriptions (with "Use when..." trigger
phrases) and combine with main's argument-hint format. Drop old args
blocks and deleted transformer files.
Rebuild all providers so descriptions propagate everywhere.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Resolve DEVELOP.md conflict by keeping our rewritten version which
already covers the factory architecture.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Remove references to individual transformer files, args arrays, and
per-provider body transforms. Document the new factory/providers
architecture, provider config options, and how to add new providers.
Point to HARNESSES.md for capabilities details.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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>
Skill cross-references like "Use the frontend-design skill" and
"run teach-impeccable" now use {{command_prefix}} so each provider
gets the correct invocation syntax (/ for most, $ for Codex).
Prose references to skill content ("guidelines in the frontend-design
skill") are left unchanged since they're not invocation instructions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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>
Research each harness's official documentation to verify and correct
provider frontmatter configs. Remove Codex/Gemini body transforms that
targeted their commands systems, not skills.
- Add compatibility + metadata to Cursor and Agents (Copilot)
- Add allowed-tools to Pi
- Remove Codex $ARGNAME and Gemini {{args}} body transforms
- Add HARNESSES.md as source of truth for harness capabilities
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Fixes#67: argument-hint values starting with [ were parsed as YAML flow
sequences. Replace structured args arrays in source files with pre-formatted
argument-hint strings, and quote values starting with [ or { in
generateYamlFrontmatter().
Also consolidates 8 nearly-identical transformer files into a single
config-driven createTransformer() factory. Adding a new provider now
requires only a config object in providers.js instead of a full file.
- Replace args source frontmatter with argument-hint strings
- Add YAML quoting for values starting with [ or {
- Add quote stripping to parseFrontmatter() for round-trip support
- Create factory.js + providers.js, delete 8 individual transformers
- Replace 16 explicit build.js calls with a loop over PROVIDERS
- Consolidate 8 test files into 2 (factory + providers)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Critique was vibes-only before. Now it scores against Nielsen's 10 heuristics
(0-4 each, /40 total) so you get a number, not just feelings. Added 5 user
personas that auto-select based on the interface type — a power user and a
first-timer break different things, turns out. Cognitive load checklist catches
the "why does this screen make my brain hurt" problems.
Audit gets the same treatment: 0-4 per dimension, /20 total, P0-P3 severity
instead of the vague Critical/High/Medium/Low labels nobody agrees on.
Both now present recommendations inline — no plan file, no /next or /fix-all
commands. Just tell the AI what to fix and it does it. Simpler.
New reference files: heuristics-scoring, personas, cognitive-load.
The build system hardcoded `/` as the command prefix for every provider,
but Codex CLI uses `$`. Added command_prefix to PROVIDER_PLACEHOLDERS
so replacePlaceholders and prefixSkillReferences use the right one.
Now `$normalize` shows up in Codex output instead of `/normalize`.
Paul BakausandClaude Opus 4.6
everforge
Gabi
rohan-tessl
rohan-tesslandGitHub
shog86