By ichabodcole
Reusable project recipes - executable blueprints for scaffolding and implementing specific technology stacks and patterns
Implement an agent feedback reporting system where AI agents can report difficulties, unclear instructions, or failure patterns via a tool call, with results stored and reviewed in an admin UI. Use when the user asks to "add a feedback tool to an agent", "let an agent report issues", "collect agent self-reports", "build an admin view for agent feedback", "capture agent difficulties during generation", or "give an agent a way to surface problems".
Implement a multi-provider AI abstraction layer with a factory function, unified provider interface, and pluggable backends. Use when the user asks to "add AI provider abstraction", "support multiple AI models", "multi-provider AI", "LLM provider factory", "swap AI providers", "AI provider interface", "OpenRouter Ollama integration", "abstract LLM providers", or wants to support cloud and local AI inference behind a single API.
Add a cloud-hosted MCP (Model Context Protocol) server to a Bun/Elysia API with multi-tenant isolation, agent key authentication, and database-backed sessions. Use when the user asks to "add MCP to an API", "set up an MCP server for agents", "implement MCP endpoint with authentication", "add AI agent access to my API", "create an MCP server with bcrypt key validation", or wants to let AI agents access cloud-hosted data through the MCP protocol.
Implement a document auto-save system with dual-layer debouncing that balances responsive undo/redo with batched database writes. Use when the user asks to "add auto-save", "implement debounced save", "add undo redo with auto-save", "build document auto-save architecture", "implement dual debounce save", "add editor auto-save", or wants responsive editing with efficient persistence.
Analyze a project or subsystem and extract its structure, patterns, and integration glue into a reusable recipe skill. Use when the user asks to "create a recipe", "extract a recipe from this project", "turn this into a reusable pattern", "make a recipe skill", "capture this as a recipe", or wants to package a working implementation as a repeatable blueprint for other projects.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Cookiecutter template that instantly generates a complete, standardized documentation structure for software projects.
Instead of creating documentation folders ad-hoc or copy-pasting from old projects, get a battle-tested, consistent structure in seconds. Perfect for developers and teams who want organized, AI-assistant-friendly documentation without building the structure from scratch each time.
Key benefits:
This template creates a complete documentation structure for your project, including:
This template is designed to work with the project-docs Claude Code plugin, which provides commands and skills for managing your documentation structure:
Commands (explicit user actions):
/project-docs:project-summary - Generate comprehensive project state
analysis/project-docs:project-recipe - Extract reusable project patterns/project-docs:update-deps - Automated dependency management/project-docs:init-branch - Initialize a new branch from develop/project-docs:project-manifesto - Discover and articulate project purpose/project-docs:start-worktree - Bootstrap an agent session in a worktreeSkills (auto-surfaced by agent + user-invocable):
/project-docs:create-project - Scaffold a new project folder with proposal/project-docs:generate-dev-plan - Create development plan from proposal/project-docs:generate-design-resolution - Resolve design ambiguity via Q&A/project-docs:generate-test-plan - Generate tiered verification scenarios/project-docs:finalize-branch - Code review, documentation, and merge
workflow/project-docs:review-docs - Documentation health checks with parallel agents/project-docs:parallel-worktree-dev - Orchestrate parallel worktree
developmentInstallation:
# Add this repository as a marketplace
/plugin marketplace add ichabodcole/project-docs-scaffold-template
# Install the project-docs plugin
/plugin install project-docs
See plugins/project-docs/README.md for detailed documentation on each command.
The skills from this project follow the Agent Skills
open standard and work with any tool that supports SKILL.md files. Pre-built
distribution packages are available in the dist/ directory.
OpenPackage (recommended):
opkg install gh@ichabodcole/project-docs-scaffold-template/dist/project-docs
Direct clone:
git clone https://github.com/ichabodcole/project-docs-scaffold-template.git
Then point your tool's skills path at dist/<plugin>/skills/. See each plugin's
dist README for tool-specific configuration examples.
| Package | Skills | Description |
|---|---|---|
dist/project-docs | 22 | Documentation workflow skills |
dist/recipes | 14 | Implementation recipe blueprints |
dist/operator | 2 | Operator document triage skills |
Note: Agents and commands are Claude Code-specific. Other tools will load only the skills.
First, ensure you have Cookiecutter installed:
pip install cookiecutter
Generate a new project documentation structure:
cookiecutter gh:ichabodcole/project-docs-scaffold-template
You'll be prompted to provide:
npx claudepluginhub ichabodcole/project-docs-scaffold-template --plugin recipesAgent-conjured apps — Bun-served surfaces with an agent as the runtime. Cantrips (cast-and-resolve) and conjurations (standing daemons).
Skills and commands for managing structured project documentation, proposals, plans, and reports
Specialized commands for user operator with the project docs structure
Specialist development utilities — testing, optimization, and tooling skills that aren't specific to project documentation
Skills for the Agent Bridge system — cross-project knowledge sharing and agent-to-agent communication via the agent-bridge MCP server
Lightweight documentation memory for AI coding agents: scaffold a docs tree, validate it, and auto-load recent context each session.
Complete development toolkit - documentation, PRDs, design docs, debugging, PR workflows, and planning
AI-powered cascading development framework with design document system and multi-agent collaboration. Breaks down projects into Features (Mega Plan), Features into Stories (Hybrid Ralph), with auto-generated technical design docs, dependency-driven batch execution, Git Worktree isolation, and support for multiple AI agents (Codex, Amp, Aider, etc.).
Core knowledge management, documentation generation, and strategic analysis for Claude Code
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.