source-coding
Problem-solving strategies for source coding in information theory
math-router
Deterministic router for math cognitive stack - maps user intent to exact CLI commands
remember
Store a learning, pattern, or decision in the memory system for future recall
repo-research-analyst
Analyze repository structure, patterns, conventions, and documentation for understanding a new codebase
fields
Problem-solving strategies for fields in abstract algebra
matrices
Problem-solving strategies for matrices in linear algebra
repoprompt
Use RepoPrompt CLI for token-efficient codebase exploration
explicit-identity
Explicit Identity Across Boundaries
explore
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
resume-handoff
Resume work from handoff document with context analysis and validation
root-finding
Problem-solving strategies for root finding in numerical methods
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".
completion-check
Completion Check: Verify Infrastructure Is Wired
complete-skill
A complete skill for E2E testing
commit
Create git commits with user approval and no Claude attribution
cli-reference
Claude Code CLI commands, flags, headless mode, and automation patterns
build
Workflow orchestrator that chains existing skills for feature development
braintrust-tracing
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
agent-orchestration
Agent Orchestration Rules
refactor
Code refactoring workflow - analyze → plan → implement → review → validate
tour
Friendly onboarding when users ask about capabilities
tldr-stats
Show full session token usage, costs, TLDR savings, and hook activity
tldr-router
Maps questions to the optimal tldr command. Use this to pick the right layer
tldr-overview
Get a token-efficient overview of any project using the TLDR stack
tldr-deep
Full 5-layer analysis of a specific function. Use when debugging or deeply understanding code.
tldr-code
Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.
test
Comprehensive testing workflow - unit tests ∥ integration tests → E2E tests
recall
Query the memory system for relevant learnings from past sessions
tdd
Test-driven development workflow with philosophy guide - plan → write tests → implement → validate
tdd-migration-pipeline
Orchestrator-only workflow for migrating/rewriting codebases with full TDD and agent delegation
async-repl-protocol
Async REPL Protocol
recall-reasoning
Search past reasoning for relevant decisions and approaches
leann-search
Semantic search across codebase using LEANN vector index
router-first-architecture
Router-First Architecture
search-hierarchy
Search Tool Hierarchy
search-tools
Search Tool Hierarchy
ast-grep-find
AST-based code search and refactoring via ast-grep MCP
background-agent-pings
Background Agent Pings
braintrust-analyze
Analyze Claude Code sessions via Braintrust
continuity-ledger
Create or update continuity ledger for state preservation across clears
create-handoff
Create handoff document for transferring work to another session
tdd-migrate
TDD workflow for migrations - orchestrate agents, zero main context growth
dead-code
Find unused functions and dead code in the codebase
debug-hooks
Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.
debug
Debug issues by investigating logs, database state, and git history
describe-pr
Generate comprehensive PR descriptions following repository templates
agent-context-isolation
Agent Context Isolation
system-overview
Show users how Continuous Claude works - the opinionated setup with hooks, memory, and coordination
pint-compute
Unit-aware computation with Pint - convert units, dimensional analysis, unit arithmetic
parallel-agents
Parallel Agent Orchestration
Page 119 of 1666 · 83252 results
