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`.
Adds the gtag.js snippet (G-TEXGHC7V34) to both HTML pages for
tracking pageviews and usage.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Slash commands do work in Antigravity, so the asterisk and tooltip
warning on the Antigravity badge were incorrect. Removes both.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Previously only .claude/skills/ was synced from dist after build. Now
all 8 provider directories are synced (.claude, .cursor, .gemini, .codex,
.agents, .kiro, .opencode, .pi) so each provider's output can be tested
directly in this repo.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Addresses #51 -- Antigravity doesn't support slash commands, only
auto-activated skills. Adds a tooltip on the Antigravity* badge in the
downloads section explaining the limitation and how to invoke skills by
name. Also adds hover tooltips showing provider names on the hero logo
icons.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
PR #50 fixed the output SKILL.md files but the source files, build
scripts, tests, docs, and server code still used the wrong spelling.
Claude Code expects `user-invocable` (with c) for slash command
autocomplete to work.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Paul BakausandClaude Opus 4.6
everforge
Gabi
rohan-tessl
rohan-tesslandGitHub
shog86
Matt Van HornandClaude Opus 4.6