Agents
AI agents and automation
agent-teams
by DmitriyYukhanov
Set up and orchestrate Claude Code agent teams - multiple Claude Code instances working together with shared tasks, inter-agent messaging, and centralized management. Use when the user wants to (1) create or start an agent team for parallel work, (2) configure agent team settings like display mode or teammate mode or permissions, (3) coordinate teammates for code review or debugging or feature development or research, (4) understand when to use agent teams vs subagents, (5) troubleshoot agent team issues. Triggers include mentions of "agent team", "team of agents", "parallel agents", "teammates", "split pane", "tmux teammates", "delegate mode", "spawn teammates", or wanting multiple Claude instances collaborating.
cross-review
by DmitriyYukhanov
This skill should be used when performing cross-review, dual review, or multi-model review of plans, implementations, architecture, or code. Applies when the user wants to "review with codex", "get a second opinion", "validate with another model", "dual review", or wants multiple AI perspectives on quality. Orchestrates review-triage-fix cycles between Claude and Codex CLI using the best available skill, repeating until clean or a decision is needed.
cdt
by rube-de
"Multi-agent development workflow using Agent Teams. Supports four modes: plan (architect teammate + PM teammate debate → plan.md), dev (developer teammate + code-tester teammate + qa-tester teammate + reviewer teammate iterate → code), full (plan → approval gate → dev), and auto (plan → dev, no gate). Use when tasks benefit from collaborative agent teammates with peer messaging."
analyzing-domains
by axiomantic
Use when entering unfamiliar domains, modeling complex business logic, or when terms/concepts are unclear. Triggers: "what are the domain concepts", "define the entities", "model this domain", "DDD", "ubiquitous language", "bounded context", or when implementing-features Phase 1.2 detects unfamiliar domain.
nats-design-subject
by TrogonStack
Design NATS subject hierarchies for messaging patterns (pub/sub, request/reply, streaming). Apply naming conventions, segmentation strategies, and wildcard patterns to create scalable subject architectures. Use when designing NATS messaging systems, planning multi-tenant communication, or auditing existing subject hierarchies. Do not use for: (1) NATS server configuration or cluster setup, (2) client library implementation or connection code, (3) debugging connectivity or performance issues, (4) choosing between NATS and other messaging systems.
temporal
by rube-de
Help developers use Temporal for durable execution workflows. Covers CLI commands, SDK patterns (Go, TypeScript, Python, Java), workflow orchestration, and architectural decisions.
autonomous-roundtable
by axiomantic
"Meta-orchestrator for Forged autonomous development: decompose projects into features, execute through DISCOVER→DESIGN→PLAN→IMPLEMENT→COMPLETE, convene roundtables, coordinate skills."
pm
by rube-de
Project manager for GitHub issues: create structured issues optimized for LLM agent teams, triage and recommend what to work on next, audit and clean up stale issues, or deep-validate a single issue against the codebase. Triggers: create issue, plan work, new task, project manager, write ticket, draft issue, plan feature, plan project, start project, create ticket, review issue, pm.
designing-workflows
by axiomantic
"Use when designing systems with explicit states, transitions, or multi-step flows. Triggers: \"design a workflow\", \"state machine\", \"approval flow\", \"pipeline stages\", \"what states does X have\", \"how does X transition\", or when implementing-features Phase 2.1 detects workflow patterns."
git-workflow
by TrevorS
Handle squashing multiple commits and rebasing feature branches safely. Use when consolidating commits into a single commit, or rebasing feature branches onto updated development branches. Falls back from jj when not available.
isolated-testing
by axiomantic
Use when testing theories during debugging, or when chaos is detected. Triggers: "let me try", "maybe if I", "what about", "quick test", "see if", rapid context switching, multiple changes without isolation. Enforces one-theory-one-test discipline. Invoked automatically by debugging, scientific-debugging, systematic-debugging before any experiment execution.
instruction-engineering
by axiomantic
"Use when crafting, improving, or reviewing prompts, system prompts, skill instructions, or any text that instructs an LLM. Triggers: 'write a prompt', 'prompt engineering', 'improve this prompt', 'design a system prompt', 'write skill instructions', 'craft agent instructions'. Provides CSO (Claude Search Optimization) guidance for skill descriptions. Also invoked by writing-skills."
scientific-workflows
by jkitchin
Expert assistant for choosing and implementing scientific workflow tools - from simple joblib caching to complex orchestration with Prefect, Parsl, FireWorks, and quacc. Recommends the simplest solution that meets requirements.
sparda-mcp
by zyx77550
Drive a SPARDA-generated MCP server to its full potential. Use this whenever you are connected to an MCP server built by SPARDA (sparda-mcp) — recognizable by the tools sparda_get_context, sparda_info, sparda_confirm, or composite tools labelled "[Labs circuit]". It teaches the call-context-first workflow, how to exploit the response-recycling flywheel, the circuit-breaker, crystallized circuits and adaptive immunity, and the mandatory two-phase confirm protocol for write tools. Reach for it before calling raw endpoints, before any write, or when a tool returns 202 (awaiting confirmation) or 503 (quarantined).
documenting-code
by alexei-led
Update project documentation based on recent changes. Use when user says "update docs", "document", "add documentation", "update readme", "write docs", or wants to improve documentation.
reviewing-code
by alexei-led
Multi-agent code review for security, quality, and architecture. Use when user says "review", "review code", "check code", "code review", "review my changes", "review this", or wants feedback on their code.
cloudflare-workflows
by jackspace
Complete knowledge domain for Cloudflare Workflows - durable execution framework for building multi-step applications on Workers that automatically retry, persist state, and run for hours or days. Use when: creating long-running workflows, implementing retry logic, building event-driven processes, scheduling multi-step tasks, coordinating between APIs, or encountering "NonRetryableError", "I/O context", "workflow execution failed", "serialization error", or "WorkflowEvent not found" errors. Keywords: cloudflare workflows, workflows workers, durable execution, workflow step, WorkflowEntrypoint, step.do, step.sleep, workflow retries, NonRetryableError, workflow state, wrangler workflows, workflow events, long-running tasks, step.sleepUntil, step.waitForEvent, workflow bindings
cloudflare-agents
by jackspace
Comprehensive guide for the Cloudflare Agents SDK - build AI-powered autonomous agents on Workers + Durable Objects. Use when: building AI agents, creating stateful agents with WebSockets, implementing chat agents with streaming, scheduling tasks with cron/delays, running asynchronous workflows, building RAG (Retrieval Augmented Generation) systems with Vectorize, creating MCP (Model Context Protocol) servers, implementing human-in-the-loop workflows, browsing the web with Browser Rendering, managing agent state with SQL, syncing state between agents and clients, calling agents from Workers, building multi-agent systems, or encountering Agent configuration errors. Prevents 15+ documented issues: migrations not atomic, missing new_sqlite_classes, Agent class not exported, binding name mismatch, global uniqueness gotchas, WebSocket state handling, scheduled task callback errors, state size limits, workflow binding missing, browser binding required, vectorize index not found, MCP transport confusion, authentication bypassed, instance naming errors, and state sync failures. Keywords: Cloudflare Agents, agents sdk, cloudflare agents sdk, Agent class, Durable Objects agents, stateful agents, WebSocket agents, this.setState, this.sql, this.schedule, schedule tasks, cron agents, run workflows, agent workflows, browse web, puppeteer agents, browser rendering, rag agents, vectorize agents, embeddings, mcp server, McpAgent, mcp tools, model context protocol, routeAgentRequest, getAgentByName, useAgent hook, AgentClient, agentFetch, useAgentChat, AIChatAgent, chat agents, streaming chat, human in the loop, hitl agents, multi-agent, agent orchestration, autonomous agents, long-running agents, AI SDK, Workers AI, "Agent class must extend", "new_sqlite_classes", "migrations required", "binding not found", "agent not exported", "callback does not exist", "state limit exceeded"
commit
by maroffo
"Create a git commit using conventional commit format. Use for committing staged changes. Not for branch strategy, rebasing, or git workflow questions (use source-control skill)."
workflow-implement-phases
by charlesjones-dev
"Orchestrates multi-phase implementation from a plan document using intelligent parallel/sequential execution strategy."
workflow-plan-phases
by charlesjones-dev
"Creates a structured implementation plan document with properly sized phases for efficient sub-agent execution."
agent-md-refactor
by dirnbauer
Refactor bloated agent instruction files (AGENTS.md, CLAUDE.md, COPILOT.md, etc.) to follow progressive disclosure principles - keeping essentials at root and organizing the rest into linked, categorized files. Use when agent instruction files are too long, contain contradictions, or need restructuring.
audio-editing
by guia-matthieu
"Master the essential audio post-production techniques—normalization, compression, EQ, and noise reduction—using the correct processing order to achieve professional-quality audio. Use when: Editing podcast episodes or video soundtracks; Cleaning up recorded voiceovers; Improving audio quality for marketing content; Preparing audio files for distribution; Troubleshooting common audio issues"
git
by tao3k
Use when committing code, managing branches, pushing to remote, creating pull requests, or performing version control operations. Conforms to docs/reference/skill-routing-value-standard.md.