Added "The current year is 2025" note to all 4 research agents so they
don't assume outdated dates when searching for documentation:
- best-practices-researcher
- framework-docs-researcher
- git-history-analyzer
- repo-research-analyst
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Replace vague "keep asking questions until user is happy" ending with
AskUserQuestion tool presenting structured options. Users now see 4
explicit choices after plan generation: Start /work, Run /plan_review,
Simplify, or Rework.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Update all documentation to show the correct command syntax:
- `/plan`, `/review`, `/work`, `/codify` (short form, autocompletes)
Previously showed `/workflows:plan` etc. which doesn't work.
The `name:` field in frontmatter determines the short command name.
Fixes#19🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Applied Hunt/Thomas and Joel Spolsky writing principles:
- Concrete before abstract (stories and examples first)
- Physical analogies for technical concepts
- Conversational voice with "you" and contractions
- Removed passive voice and weasel words
- Added memorable metaphors and hooks
Pages updated:
- index.html: New hero, philosophy section with N+1 query story
- agents.html: Each agent described with concrete scenarios
- commands.html: Action-oriented descriptions
- getting-started.html: Direct, conversational guide
- skills.html: Clear "when to use this" for each skill
- mcp-servers.html: Concrete examples of what each tool does
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
GitHub Pages is configured to serve from /docs in main branch.
Moved documentation site from plugins/compounding-engineering/docs/
to repository root /docs folder.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Removed over-styled elements that were added during design iterations:
- Remove pulse, icon-float, badge-pulse, server-pulse animations
- Remove diamond-spin and slide-in animations
- Remove scanline repeating-linear-gradient effects
- Simplify hover transforms from -4px/-6px to -2px
- Simplify complex multi-layer box shadows to single shadows
- Remove shine effect on primary buttons
- Clean up duplicate/corrupted CSS rules
Net result: -205 lines of CSS, cleaner and more minimal design
following LaunchKit's "purposeful restraint" philosophy.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Adds automated deployment of documentation to GitHub Pages when
changes are pushed to the docs directory on the main branch.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add /release-docs command for regenerating documentation site
- Add commands/README.md with usage instructions for all commands
- Add changelog.html page rendering CHANGELOG.md in HTML format
- Add changelog CSS styles to docs.css
- Update navigation in all docs pages to include changelog link
- Fix command count from 16 to 13 in navigation
- Update CLAUDE.md with:
- Documentation Site section explaining structure
- /release-docs command in update checklist
- Instructions for keeping docs up-to-date
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add agents.html with full documentation for all 24 agents
- Add commands.html with full documentation for all 16 commands
- Add skills.html with full documentation for all 11 skills
- Add mcp-servers.html with Playwright and Context7 documentation
- Enhance landing page philosophy section with four pillars and compounding effect timeline
- Add CSS styles for philosophy section components
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Create landing page with Evil Martians devtool-template styling
- Add dark theme with accent colors and responsive design
- Document all 24 agents, 16 commands, 11 skills, and 2 MCP servers
- Add Getting Started guide with installation and configuration
- Include FAQ section, philosophy explanation, and code examples
- Add CSS with mobile-responsive layouts and smooth animations
- Include JavaScript for mobile nav, smooth scroll, and copy code
Built with LaunchKit template from Evil Martians.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- New slash command that guides users through structured bug reporting
- Collects bug category, component, actual vs expected behavior, repro steps
- Auto-gathers environment info (plugin version, Claude Code version, OS)
- Creates GitHub issues in EveryInc/every-marketplace via gh CLI
- Includes privacy notice and error handling
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add focused screenshot guidance: always capture target element, not full page
- Include browser_resize recommendations for different component sizes
- Add element-targeted screenshot workflow using browser_snapshot refs
- Add step to load relevant design skills before starting iterations
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add required "type": "stdio" to playwright MCP server config
- MCP servers require explicit type declaration to load properly
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update description to emphasize proactive use when design work isn't coming together
- Add examples showing how to suggest 5x or 10x iterations after initial changes fail
- Include guidance for when colors feel wrong or layouts aren't balanced
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add CLAUDE.md with versioning checklist and pre-commit requirements
- Add docs/solutions/plugin-versioning-requirements.md with detailed workflow
- Bump version to 2.0.1
- Update CHANGELOG with v2.0.1 entry
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Adds pip installable dependencies for the gemini-imagegen skill:
- google-genai>=1.0.0
- Pillow>=10.0.0
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add gemini-imagegen skill for image generation with Gemini API
- Fix component counts: 17 agents (was 15), 6 commands, 1 skill
- Add comprehensive README documenting all components
- Add CHANGELOG tracking version history
- Bump version to 1.1.0
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Two corrections based on feedback:
1. Remove plugin README - only the marketplace README is needed
2. Update all command references to use correct prefix format:
- /plan → /compounding-engineering:plan
- /work → /compounding-engineering:work
- /review → /compounding-engineering:review
- All other commands updated similarly
This ensures the documentation accurately reflects how users actually invoke the commands.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Expand the marketplace README to include the full compounding engineering plugin documentation. This makes it immediately clear to visitors what the plugin does and how to use it.
Key additions:
- Detailed explanation of the three-step workflow (Plan → Work → Review)
- Practical examples for each core command
- Complete list of all six commands and 17 agents
- Philosophy and benefits of compounding engineering
- Clear getting started guide
Kept the original installation instructions and added the detailed documentation below, making the marketplace README a comprehensive resource.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Create a new README that clearly explains how to use the plugin with focus on the three core commands: /plan, /work, and /review. The README:
- Explains the compounding engineering philosophy
- Provides clear workflow guidance (Plan → Work → Review)
- Includes practical quick start examples
- Lists all 17 agents and six commands
- Follows Every's style guide conventions
This makes it much easier for new users to understand how to use the plugin effectively.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>