Securely manages API credentials for multiple providers (Anthropic Claude, Google Gemini, GitHub). Use when skills need to access stored API keys for external service invocations.

Observe Before Editing

Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

Parallel Agent Orchestration

Agent Context Isolation

Friendly onboarding when users ask about capabilities

Hook Development Rules

Completion Check: Verify Infrastructure Is Wired

Implement technical plans from thoughts/shared/plans with verification

Formal theorem proving with research, testing, and verification phases

Planning agent that creates implementation plans and handoffs from conversation context

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,...

|

Guide to the math cognitive stack - what tools exist and when to use each

Search past reasoning for relevant decisions and approaches

Modular Code Organization

Orchestrator-only workflow for migrating/rewriting codebases with full TDD and agent delegation

Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

|

Check reference SDK implementations using btca ask