自动化
工作流自动化与调度
codex
NeverSight
Hand off a task to Codex CLI for autonomous execution. Use when a task would benefit from a capable subagent to implement, fix, investigate, or review code. Codex has full codebase access and can make changes.
codex
NeverSight
Hand off a task to Codex CLI for autonomous execution. Use when a task would benefit from a capable subagent to implement, fix, investigate, or review code. Codex has full codebase access and can make changes.
orchestrator
p-wegner
Delegating orchestrator — breaks work into sub-tasks and delegates to subagents or board tickets instead of doing everything itself
monitor-nudge
p-wegner
Message sent to agents that have been running for more than 5 minutes without exiting — customize to change nudge behavior
dependency-analyzer
p-wegner
Analyze a ticket and its relationships to other open tickets, suggest dependency updates
iterative-retrieval
xu-xiang
用于逐步优化上下文检索以解决子智能体（subagent）上下文问题的模式
Playwright Browser Automation
smallnest
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
webapp-testing
smallnest
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
request-analyzer
smallnest
Proactively analyze user requests at the start of conversations to determine task type, assess prompt quality, and intelligently recommend which skills to activate. Should activate for ALL user requests to ensure optimal workflow. Evaluates clarity, specificity, and completeness to suggest prompt-optimizer when needed. Identifies UI design tasks for ui-analyzer and component requests for react-component-generator. Acts as intelligent skill coordinator.
context-management
89jobrien
Context management specialist for multi-agent workflows and long-running
spec-executor
ky1ejs
Execute implementation specs with batched checkpoints. Follows specs exactly, stops on blockers, supports parallelization.
platxa-skill-generator
platxa
Autonomous skill creator for Claude Code CLI. Uses multi-phase orchestrated workflow with Task tool subagents to research domains, design architecture, generate content, and validate quality. Creates production-ready skills following Anthropic's Agent Skills specification.
kanban-video-orchestrator
wundercorp
Plan and run multi-agent video production pipelines.
archify
wundercorp
Validated interactive HTML diagrams, upstream-maintained.
audiocraft-audio-generation
wundercorp
"AudioCraft: MusicGen text-to-music, AudioGen text-to-sound."
modal
wundercorp
Serverless GPU cloud for ML jobs and model APIs.
flash-attention
wundercorp
Speed up long-sequence transformer training and inference.
pipeline
agenticnotetaking
End-to-end source processing -- seed, reduce, process all claims through reflect/reweave/verify, archive. The full pipeline in one command. Triggers on "/pipeline", "/pipeline [file]", "process this end to end", "full pipeline".
Beads Decompose
wcygan
Configuration for Development Environments
phase1-lite
nguyenthienthanh
"Ultra-compact Phase 1 requirements output. HARD CAP: 500 tokens."
clone-sprint
wcygan
Sprint-scoped MVP builder that consumes clone-research output. Decomposes research into a beads task DAG (epics per bounded context, subtasks per feature slice), spawns worktree-isolated builder agents in batches of 2-3, merges via bd merge-slot, and reports progress. Idempotent: first invocation creates the DAG; subsequent invocations run the next sprint via bd ready. Keywords: clone, build, sprint, MVP, beads, worktree, parallel, task DAG, feature slice
Beads Assign
wcygan
Configuration for Development Environments
session-continuation
nguyenthienthanh
"Manage workflow state across sessions with handoff and resume. TOON-based state persistence."
brainstorm
wcygan
Multi-agent brainstorming for software design decisions and architecture choices. Spawns parallel agents with differentiated roles (codebase explorer, trade-off analyst, devil's advocate) to evaluate options, surface blind spots, and produce structured analysis including trade-off matrices, pre-mortems, and ADR-ready summaries. Use when making architecture decisions, choosing between approaches, or evaluating trade-offs. Keywords: brainstorm, decision, trade-off, architecture, design, evaluate, options, approach, choose, pros cons, ADR, pre-mortem, WWHTBT