自动化
工作流自动化与调度
agencycli
chenhg5
"Manage AI agent teams with agencycli — a CLI tool for organising AI agents (Claude Code, Codex, Gemini, Cursor, etc.) into hierarchical teams (Agency → Team → Role → Project → Agent). Key capabilities: create agencies and teams, hire agents with merged context layers, assign and run tasks with priority queues, manage autonomous playbooks (wakeup.md), send async inbox messages between human and agents, configure heartbeat schedules and cron jobs, run agents inside Docker sandboxes, forward/confirm tasks via inbox, manage templates, and more. Use this skill whenever you need to: create or manage an agencycli workspace, hire/fire/sync agents, add/run/cancel tasks, check inbox confirmations, send messages, configure heartbeats or crons, start the scheduler, or work with agency templates."
backlog-technical-project-manager
MrLesk
Technical project management for Backlog.md workstreams using coordinated sub-agents. Use only when the user explicitly asks Codex to take over one or more existing Backlog.md tasks (for example: "act as TPM", "coordinate these tasks", "delegate to sub-agents"). Orchestrate planning, implementation, and finalization; manage dependencies and overlapping code areas; review and approve sub-agent plans before implementation.
doc-workflow
TokenRollAI
"Use when user asks about 'documentation workflow', 'how to document', 'doc system', 'what is llmdoc', 'how does llmdoc work', or needs guidance on the documentation system."
openspec-apply-change
PBH-BTN
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
ticktick
NeverSight
Manage TickTick tasks and projects for JMO. Use when the user asks to add, create, or capture a task or todo; list, show, or review pending tasks; complete or check off a task; update a task's priority, due date, notes, or tags; delete a task or list; create or manage a project/list; or see what's due today or overdue. Also handles quick captures like "remind me to..." or "don't let me forget...".
test
ClickHouse
Run ClickHouse stateless or integration tests. Use when the user wants to run or execute tests.
build
ClickHouse
Build ClickHouse with various configurations (Release, Debug, ASAN, TSAN, etc.). Use when the user wants to compile ClickHouse.
security
elie222
Security guidelines for API route development
e2e
elie222
Run and debug E2E flow tests. Use when triggering E2E tests, checking test status, debugging failures with Axiom logs, or setting up local E2E testing. E2E tests run from the inbox-zero-e2e repo and test real email workflows.
review
elie222
Review code changes, auto-fix safe issues, and report bugs
clerk
clerk
Clerk authentication router. Use when user asks about adding authentication, setting up Clerk, custom sign-in flows, Next.js patterns, organizations, syncing users, or testing. Automatically routes to the specific skill based on their task.
ray-data
Orchestra-Research
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
skypilot-multi-cloud-orchestration
Orchestra-Research
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
pytorch-lightning
Orchestra-Research
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
ML Training Recipes
Orchestra-Research
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.
optimizing-attention-flash
Orchestra-Research
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
transformer-lens-interpretability
Orchestra-Research
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
distributed-llm-pretraining-torchtitan
Orchestra-Research
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
index-knowledge
tursodatabase
Generate hierarchical AGENTS.md knowledge base for a codebase. Creates root + complexity-scored subdirectory documentation.
git-workflow
agno-agi
Git workflow guidance for commits, branches, and pull requests
webapp-testing
snyk
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.
docx
snyk
"Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks"
wolf-scripts-agents
majiayu000
Agent coordination, orchestration, and multi-agent workflow management scripts
codex-delegator
majiayu000
Automatically delegate complex, logic-intensive tasks to OpenAI Codex CLI via codex exec --full-auto. Claude Code uses this skill to invoke Codex for complex backend logic, intricate algorithms, or persistent bugs. Enables seamless AI-to-AI collaboration where Claude Code analyzes and Codex executes.