A community-driven registry for Claude, Cursor, Windsurf, Cline & more. Not affiliated with Anthropic.
Are you the author? Sign in to claim
A collection of my favorite custom Claude Code resources to make life easier.
A growing collection of custom Claude Code resources built for real workflows.
When you use a tool like Claude Code, it's your responsibility to assume everything is possible.
I built these tools using that mindset.
Dream big. Happy building.
— TÂCHES
Commands (27 total) - Slash commands that expand into structured workflows
Skills (9 total) - Autonomous workflows that research, generate, and self-heal
Agents (3 total) - Specialized subagents for validation and quality
# Add the marketplace
claude plugin marketplace add glittercowboy/taches-cc-resources
# Install the plugin
claude plugin install taches-cc-resources
Start a new Claude Code session to use the commands and skills.
# Clone the repo
git clone https://github.com/glittercowboy/taches-cc-resources.git
cd taches-cc-resources
# Install commands
cp -r commands/* ~/.claude/commands/
# Install skills
cp -r skills/* ~/.claude/skills/
Commands install globally to ~/.claude/commands/. Skills install to ~/.claude/skills/. Project-specific data (prompts, todos) lives in each project's working directory.
Separate analysis from execution. Describe what you want in natural language, Claude generates a rigorous prompt, then runs it in a fresh sub-agent context.
/create-prompt - Generate optimized prompts with XML structure/run-prompt - Execute saved prompts in sub-agent contextsCapture ideas mid-conversation without derailing current work. Resume later with full context intact.
/add-to-todos - Capture tasks with full context/check-todos - Resume work on captured tasksCreate structured handoff documents to continue work in a fresh context. Reference with @whats-next.md to resume seamlessly.
/whats-next - Create handoff document for fresh contextWrapper commands that invoke the skills below.
/create-agent-skill - Create a new skill/create-meta-prompt - Create staged workflow prompts/create-slash-command - Create a new slash command/create-subagent - Create a new subagent/create-hook - Create a new hookInvoke auditor subagents.
/audit-skill - Audit skill for best practices/audit-slash-command - Audit command for best practices/audit-subagent - Audit subagent for best practices/heal-skill - Fix skills based on execution issuesApply mental frameworks to decisions and problems.
/consider:pareto - Apply 80/20 rule to focus on what matters/consider:first-principles - Break down to fundamentals and rebuild/consider:inversion - Solve backwards (what guarantees failure?)/consider:second-order - Think through consequences of consequences/consider:5-whys - Drill to root cause/consider:occams-razor - Find simplest explanation/consider:one-thing - Identify highest-leverage action/consider:swot - Map strengths, weaknesses, opportunities, threats/consider:eisenhower-matrix - Prioritize by urgent/important/consider:10-10-10 - Evaluate across time horizons/consider:opportunity-cost - Analyze what you give up/consider:via-negativa - Improve by removingSystematic debugging with methodical investigation.
/debug - Apply expert debugging methodology to investigate issuesSpecialized subagents used by the audit commands.
skill-auditor - Expert skill auditor for best practices complianceslash-command-auditor - Expert slash command auditorsubagent-auditor - Expert subagent configuration auditorHierarchical project planning optimized for solo developer + Claude. Create executable plans that Claude runs, not enterprise documentation that sits unused.
PLAN.md IS the prompt - not documentation that gets transformed later. Brief → Roadmap → Research (if needed) → PLAN.md → Execute → SUMMARY.md.
Domain-aware: Optionally loads framework-specific expertise from ~/.claude/skills/expertise/ (e.g., macos-apps, iphone-apps) to make plans concrete instead of generic. Domain expertise skills are created with create-agent-skills - exhaustive knowledge bases (5k-10k+ lines) that make task specifications framework-appropriate.
Quality controls: Research includes verification checklists, blind spots review, critical claims audits, and streaming writes to prevent gaps and token limit failures.
Context management: Auto-handoff at 10% tokens remaining. Git versioning commits outcomes, not process.
Commands: /create-plan (invoke skill), /run-plan <path> (execute PLAN.md with intelligent segmentation)
See create-plans README for full documentation.
Build skills by describing what you want. Asks clarifying questions, researches APIs if needed, and generates properly structured skill files.
Two types of skills:
~/.claude/skills/expertise/ and provide framework-specific context to other skills like create-plansContext-aware: Detects if you're in a skill directory and presents relevant options. Progressive disclosure guides you through complex choices.
When things don't work perfectly, /heal-skill analyzes what went wrong and updates the skill based on what actually worked.
Commands: /create-agent-skill, /heal-skill, /audit-skill
The skill-based evolution of the meta-prompting system. Builds prompts with structured outputs (research.md, plan.md) that subsequent prompts can parse. Adds automatic dependency detection to chain research → plan → implement workflows.
Note: For end-to-end project building, consider create-plans - it's the more structured evolution of this approach with full lifecycle management (brief → roadmap → execution → handoffs). Use create-meta-prompts for abstract workflows and Claude→Claude pipelines. Use create-plans for actually building projects.
Commands: /create-meta-prompt
Build commands that expand into full prompts when invoked. Describe the command you want, get proper YAML configuration with arguments, tool restrictions, and dynamic context loading.
Commands: /create-slash-command, /audit-slash-command
Build specialized Claude instances that run in isolated contexts. Describe the agent's purpose, get optimized system prompts with the right tool access and orchestration patterns.
Commands: /create-subagent, /audit-subagent
Build event-driven automation that triggers on tool calls, session events, or prompt submissions. Describe what you want to automate, get working hook configurations.
Commands: /create-hook
Build Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude. Supports Python and TypeScript implementations with API research, OAuth handling, and response optimization.
Architecture patterns: Traditional (1-2 operations) or on-demand discovery (3+ operations) based on complexity.
Includes: Adaptive intake, API research via subagent, code generation from templates, environment variable security, and installation in Claude Code + Claude Desktop.
Commands: /create-mcp-servers (via skill routing)
Deep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous verification. Use when standard troubleshooting fails or when issues require systematic root cause analysis.
Commands: /debug
Set up Geoffrey Huntley's Ralph Wiggum autonomous coding loop. Ralph is an autonomous AI coding methodology that uses iterative loops with task selection, execution, and validation. Fresh context every iteration prevents context poisoning.
Three phases: Planning (gap analysis → TODO list), Building (implement one task, validate, commit), Observation (you engineer the environment).
Key concepts: Backpressure via tests/lints/builds, file I/O as state (IMPLEMENTATION_PLAN.md), parallel subagents for reads, prompts evolve through observation.
Commands: /setup-ralph
See setup-ralph README for full documentation.
For building projects: Use /create-plan to invoke the create-plans skill. After planning, use /run-plan <path-to-PLAN.md> to execute phases with intelligent segmentation. This provides hierarchical planning (BRIEF.md → ROADMAP.md → phases/PLAN.md), domain-aware task generation, context management with handoffs, and git versioning.
For domain expertise: Use create-agent-skills to create exhaustive knowledge bases in ~/.claude/skills/expertise/. These skills are automatically loaded by create-plans to make task specifications framework-specific instead of generic.
Other tools: The create-meta-prompts skill and /create-prompt + /run-prompt commands are available for custom Claude→Claude pipelines that don't fit the project planning structure.
More resources coming soon.
Community Ports: OpenCode
—TÂCHES
干净、强大、属于你的 AI Agent 平台 --AI agents, without the clutter.
Pocket Flow: Codebase to Tutorial
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
Native macOS app to monitor Claude AI usage limits and watch your coding sessions live