SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
osmo
Manage OSMO cloud compute: check pools, GPUs, quotas, submit and monitor workflows, inspect logs, and create apps using the OSMO CLI.
orchestkit
Deep pull-request code review using parallel specialized agents (quality, security, tests, architecture, performance) and synthesized review reports for approve
maestro-orchestrate
Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.
ash-ai
SDK skill for deploying and managing hosted AI agents with Ash: create clients and sessions, stream SSE responses, handle lifecycle and errors, using TypeScript
crucible
Orchestrates an end-to-end development pipeline: interactive design, planning, autonomous execution, and quality gates with TDD and iterative reviews.
specs.md
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
bitterbot-desktop
Control tmux sessions for interactive TTYs: send keystrokes, capture panes, orchestrate parallel coding agents, and monitor output safely.
clawkeeper
Orchestrates fetching GitHub issues, spawning parallel sub-agents to implement fixes, open PRs, and handle review comments using the GitHub REST API.
citadel
A single-session meta-orchestrator that parses a direction, chains existing skills, and executes multi-step tasks end-to-end without unnecessary user prompts.
oh-my-codex
Durable multi-worker orchestration: queueing, worker leases, review gates, and tmux-aware lifecycle for long-running work.
rune
Monitors git changes against a planned task to detect and quantify scope creep, classifying drift into actionable tiers (ON_TRACK → OUT_OF_CONTROL).
AgentOps
Orchestrates a three-phase RPI lifecycle (discovery → implementation → validation) for autonomous agent workflows, including complexity classification, routing,
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.
orchestkit
Patterns and workflows for creating, sequencing, and managing task dependencies using TaskCreate/TaskUpdate/TaskGet/TaskList tools to coordinate multi-step impl
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
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
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.
recursive-mode
Orchestrates recursive repository workflows: phased runs, locks, audits, and durable memory updates for long-running agentic tasks.
cowork-os
Run a consensus-style multi-agent review of a pull request and produce severity-ranked findings and actionable remediation steps.
task-orchestrator
Turn conversation context into MCP work items: infer type/priority, anchor into containers (Bugs, Features, Tech Debt), create single items or work trees, and p
llm-autonomous-agent-plugin-for-claude
Guidelines and communication patterns for coordinating four agent groups (analysis, decision, execution, validation) to enable reliable feedback loops, knowledg
genie
Dispatch a dedicated fixer subagent to address FIX-FIRST gaps, re-run a separate review up to 2 loops, and escalate to a human if unresolved.
turkey-build
Multi-agent app builder and orchestrator: bootstraps projects, creates feature branches, and runs runtime-verified builds with a PM conductor and QA gates.
forgewright
A production-grade thinking partner that researches, analyzes, and helps decide what to build before execution — ideal for pre-flight consultations and complex
reprompter
Turn messy prompts into structured, scoreable prompts or multi-agent plans; also reverse-engineer great outputs into reusable prompts.
skillshub
QA orchestration skill: defines test strategy, assigns unit/integration/E2E suites, enforces coverage thresholds, and coordinates CI test execution.
box0
Run and coordinate parallel AI sub-agents locally or on a server to delegate reviews, tests, research, and other specialist tasks.
