SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags

oh-my-codex
Durable multi-worker orchestration: queueing, worker leases, review gates, and tmux-aware lifecycle for long-running work.

cowork-plugins
Orchestrator that converts a product brief into images, a short cinematic video and channel-ready variants for Korean e‑commerce.

agentops
Orchestrates a three-phase RPI lifecycle (discovery → implementation → validation) for autonomous agent workflows, including complexity classification, routing,

claude-skills-pack
Defines an inter-skill artifact protocol: how skills produce, publish, discover, and consume handoff manifests to enable reliable skill chaining and artifact li

codescalebench
Launch, manage, and rerun CodeScaleBench benchmark suites with safety guardrails, paired baseline+full execution, and orchestration utilities.

atypica-research-skill
Connector skill that exposes atypica.ai multi-agent research tools via MCP for consumer research, market analysis, and report/podcast artifact generation.

claude-skill-registry
Multi-agent RFC and requirements workflow for producing structured RFCs, findings, and progress artifacts. Orchestrates subagents, routing, and quality gates fo

orchestkit
Patterns and workflows for creating, sequencing, and managing task dependencies using TaskCreate/TaskUpdate/TaskGet/TaskList tools to coordinate multi-step impl

awesome-codex-plugins
Runs an opt-in session-orchestration loop that auto-starts routine sessions when confidence is high, enforcing post-session kill-switches and resource caps.

the-startup
Orchestrates multi-phase feature implementations by delegating tasks to specialist agents, enforcing phase checkpoints, drift validation, and human approval at

gateflow-plugin
Orchestrates SystemVerilog/RTL development: plan, generate, verify, and iterate using specialist agents to deliver working, lint-clean, tested RTL.

slot-machine
Run N independent implementations of the same clear spec in parallel, review each, and pick or synthesize the best result to maximize quality when design choice

openteams
Automate Composio Goody toolkit workflows via Rube MCP: discover tools, check connections, and execute schema-compliant operations.

codex-deck
Operator client for orchestrating persistent multi-agent coding workflows backed by a JSON workflow file under ./.codex-deck/ with strict create/validate/trigge

citedy-seo-agent
MCP-first orchestrator that generates short vertical UGC videos: scripts, avatar reuse/generation, video rendering, and optional auto-publish to Reels/Shorts.

reaper
Provide structured critique of investigation results via human feedback, Codex consultation, or agent self-review to uncover gaps, alternative hypotheses, and n

swarm-cli
Orchestrate multi-agent AI workflows using swarm-cli compose (swarm.yaml) files with planner/doer/reviewer pipelines and DAG task dependencies.

epistemic-protocols
Orchestrates delegated, multi-issue workflows: categorizes issues by project northstar, fans out per-category PRs, then inscribes reviewer rejections back to is

bob
Orchestrates a team-based development workflow using agent teams: INIT → WORKTREE → BRAINSTORM → PLAN → EXECUTE → REVIEW → COMPLETE, with explicit rules for spa

aiwg
Orchestrate automated SDLC gate validations with specialist subagents and synthesize a clear pass/fail report.

citadel
Interactive first-run wizard that installs hooks, detects project stack, generates harness config, and runs a short live demo to register skills and protect the

orchestrate
Launch and manage agent runs: compose prompts, route models to the correct CLI, log artifacts, and inspect run history.

xagent
Creates and configures custom AI agents: select tools, knowledge bases, and settings so users get an agent tuned for a specific task.

Maister
Orchestrates implementation plans by delegating task groups to a task-group-implementer subagent, enforcing test-driven, wave-based parallel execution and lazy

oh-my-claudecode
Launch N CLI worker processes (claude/codex/gemini) in tmux panes to run tasks in parallel for multi-agent CLI-first workflows.

claude-skill-registry
Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges

Kurtosis
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.

airflow-vscode-extension
Manage Apache Airflow from an agent using VS Code extension tools: list, run, debug DAGs, view logs, and check server health — without shell commands.

openclaw-skill-claude-code
Run Claude Code asynchronously with thread-safe Telegram/WhatsApp notifications, heartbeats, and an E2E operator validation workflow for long-running code and r

cowork-os
Run a consensus-style multi-agent review of a pull request and produce severity-ranked findings and actionable remediation steps.