Agent Tooling
Skills that build, configure or extend agents and other skills.
Search and filter within Agent Tooling
1967 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| helpcomposio-community/awesome-claude-pluginsShow skill-bus overview, status, and available commands. Quick reference for all skill-bus features. | Stars: 2k | Updated | Claude CodeCodex | Unverified | Install |
| list-subscomposio-community/awesome-claude-pluginsList all active skill-bus subscriptions across global and project scopes, showing merge status, insert-level and subscription-level conditions, effective condition stacking, and what would fire for each skill. | Stars: 2k | Updated | Claude CodeCodex | Unverified | Install |
| pause-subscomposio-community/awesome-claude-pluginsTemporarily disable the skill bus. Quick toggle to stop all subscriptions from firing without removing them. | Stars: 2k | Updated | Claude CodeCodex | Unverified | Install |
| reflecting-on-sessionscomposio-community/awesome-claude-pluginsUse when completing a plan, finishing a development branch, wrapping up a session, or at any natural transition between work phases — reviews skill-bus telemetry to identify subscription gaps and suggest improvements | Stars: 2k | Updated | Claude CodeCodex | Unverified | Install |
| remove-subcomposio-community/awesome-claude-pluginsUnsubscribe from a skill event. Removes or disables subscriptions with scope-aware options. | Stars: 2k | Updated | Claude CodeCodex | Unverified | Install |
| unpause-subscomposio-community/awesome-claude-pluginsRe-enable the skill bus after pausing. Restores subscription processing. | Stars: 2k | Updated | Claude CodeCodex | Unverified | Install |
| math-modelingXiaoMaColtAI/math-modeling-skill当用户要求数学建模、建模竞赛、建模分析、代码求解、结果可视化或生成数学建模论文时使用。支持完整三阶段流程、单独执行任一角色,以及在关键节点使用独立 Subagent 进行阶段内质检;默认只启用质检 Subagent,用户可明确选择额外协作。 | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| math-modelingXiaoMaColtAI/math-modeling-skill当用户要求数学建模、建模竞赛、建模分析、代码求解、结果可视化或生成数学建模论文时使用。支持完整三阶段流程、单独执行任一角色,以及在关键节点使用独立 Subagent 进行阶段内质检;默认只启用质检 Subagent,用户可明确选择额外协作。 | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| babysit-babysitter-issuesa5c-ai/babysitterThis skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo. | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| babysita5c-ai/babysitterOrchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.) | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| agent-dispatcha5c-ai/babysitter | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| agent-coordinationa5c-ai/babysitterCoordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle. | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| convoy-managementa5c-ai/babysitterCreate, track, and land convoys of related beads as primary work orders in the Gas Town multi-agent orchestration framework. | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| merge-queuea5c-ai/babysitterProcess the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration. | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| patrol-monitoringa5c-ai/babysitterContinuous monitoring using Deacon/Witness patterns for agent health checks, stuck detection, and automated recovery. | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| session-managementa5c-ai/babysitterManage agent sessions including initialization, handoffs, revival (seance), and persistent identity for Polecats and Crew agents. | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| context-engineeringa5c-ai/babysitterContext window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full 200k tokens. Provides warnings at thresholds, context-aware summarization triggers, and wave-level budget planning. | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| gsd-toolsa5c-ai/babysitterCentral utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init). | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| model-profile-resolutiona5c-ai/babysitterResolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role. | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| external-tool-coordinationa5c-ai/babysitterCoordinate external AI tool integration (OpenAI Codex, Google Gemini) for cross-model adversarial review and delegated implementation. | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| codebase-researcha5c-ai/babysitterSystematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents. | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| agent-boostera5c-ai/babysitterWASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost. | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| consensus-mechanismsa5c-ai/babysitterMulti-protocol consensus for agent swarms supporting Raft leader election, Byzantine fault tolerance, Gossip state propagation, and CRDT conflict-free merging. | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| smart-routinga5c-ai/babysitterComplexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection. | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| dispatching-parallel-agentsa5c-ai/babysitterUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies. | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| subagent-driven-developmenta5c-ai/babysitterUse when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent per task. | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| writing-skillsa5c-ai/babysitter | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| autogen-setupa5c-ai/babysitterMicrosoft AutoGen multi-agent configuration for conversational AI systems | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| chain-of-thought-promptsa5c-ai/babysitterChain-of-thought and step-by-step reasoning prompts for complex problem solving | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |
| constitutional-ai-promptsa5c-ai/babysitterConstitutional AI and safety guardrail prompts for aligned LLM behavior | Stars: 1.9k | Updated | Claude CodeCodex | Unverified | Install |