Firecrawl Scrape
Scrape web pages and extract content via Firecrawl MCP
Ast Grep Find
AST-based code search and refactoring via ast-grep MCP
Build
Workflow orchestrator that chains existing skills for feature development
Agentic Workflow
Agentic Workflow Pattern
Commit
Create git commits with user approval and no Claude attribution
Implement Plan
Implement technical plans from thoughts/shared/plans with verification
Search Tools
Search Tool Hierarchy
Braintrust Analyze
Analyze Claude Code sessions via Braintrust
Describe Pr
Generate comprehensive PR descriptions following repository templates
Hook Developer
Complete Claude Code hooks reference - input/output schemas, registration, testing patterns
Debug Hooks
Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.
Explore
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
Complete Skill
A complete skill for E2E testing
Leann Search
Semantic search across codebase using LEANN vector index
Agentica Spawn
Spawn Agentica multi-agent patterns
Background Agent Pings
Background Agent Pings
Search Hierarchy
Search Tool Hierarchy
Agentica Sdk
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration
Agentica Claude Proxy
Guide for integrating Agentica SDK with Claude Code CLI proxy
Trace Claude Code
|
Discovery Interview
Deep interview process to transform vague ideas into detailed specs. Works for technical and non-technical users.
Fix
Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.
Index At Creation
Index at Creation Time
Environment Triage
Environment Triage
Graceful Degradation
Graceful Degradation with Helpful Messages
Implement Plan Micro
Implement technical plans from thoughts/shared/plans with verification
Braintrust Tracing
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
Cli Reference
Claude Code CLI commands, flags, headless mode, and automation patterns
Git Commits
Git Commit Rules
Compound Learnings
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".
Debug
Debug issues by investigating logs, database state, and git history
Agentica Prompts
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
Agentica Infrastructure
Reference guide for Agentica multi-agent infrastructure APIs
Dead Code
Find unused functions and dead code in the codebase
Agent Context Isolation
Agent Context Isolation
Idempotent Redundancy
Idempotent Redundancy
Explicit Identity
Explicit Identity Across Boundaries
Completion Check
Completion Check: Verify Infrastructure Is Wired
Agentica Server
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
Help
Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available
Llm Tuning Patterns
LLM Tuning Patterns
Create Handoff
Create handoff document for transferring work to another session
Continuity Ledger
Create or update continuity ledger for state preservation across clears
Async Repl Protocol
Async REPL Protocol
Router First Architecture
Router-First Architecture
Agent Orchestration
Agent Orchestration Rules
Implement Task
Implementation agent that executes a single task and creates handoff on completion
Hooks
Hook Development Rules
Github Search
Search GitHub code, repositories, issues, and PRs via MCP
Continuous Claude V3
Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.