Results for “task”

Routes operational tasks across analytics, finance, infrastructure, legal, studio production, and support sub-skills, applying behavioral science and governance gates.

Discovers and installs agent skills from the open ecosystem using the Skills CLI, helping users find relevant skills for their tasks.

Tracks Claude Code tool usage and prompts via hooks to analyze patterns and suggest new skills for repetitive tasks.

High-performance graph analysis for beads issue tracker using 9 metrics (PageRank, Betweenness, HITS, Critical Path, etc). Provides AI-driven task prioritization, dependency analysis, and architectural health monitoring via robot protocol.

Use when the user explicitly enters TURBO, mode TURBO, enable TURBO, or TURBO for this task, and Codex should optimize for maximum quality without normal token-cost restraint.

Trigger: standard work, deming first, feedback loop checks, decision rights, delegation check. Scope: Engineering operating models, team governance, task feedback loops. Boundary: Excludes direct code implementation or design templates.

Orchestrate the full MoonSpec lifecycle from a preselected single-story feature request or active feature directory through specification, planning, TDD task generation, artifact alignment, implementation, and final verification. Use when the user asks for an end-to-end MoonSpec run and the input has already been routed to one independently testable story, or when Codex needs to coordinate `moonspec-specify`, `moonspec-plan`, `moonspec-tasks`, `moonspec-align`, `moonspec-implement`, and `moonspec-verify` without manual analyze/remediation prompts.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than relying on arbitrary auto-compaction.

Automate Google Classroom tasks including course management, assignments, student rosters, and announcements via Composio's toolkit and Rube MCP.

Orquesta el ecosistema de agentes: decide qué modelo o tier usar, delega tareas a sub-agentes especializados y planifica arquitectura técnica.

Routes tasks to specialized agent offices and applies behavioral science frameworks to every output, with confidence tagging and session memory.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Use when work should be delegated to Claude Code CLI, especially headless `claude -p` runs, automation scripts, CI jobs, resumable sessions, or requests to use Claude/Claude Code for a task.

当用户已有确认过的行为规格（理想来自 write-spec），要在编码前把技术问题问清楚、比较方案、锁定技术决策——技术选型、架构、数据模型、接口契约、错误处理、测试策略——并沉淀成可 review 的技术设计依据时使用。不要用于：行为/需求还没钉死（先 write-spec）、想法还模糊（先 refine-idea）、任务拆解或实现计划（那是下游 split-task）、调试或代码评审。

当一段开发完成，要给当前分支 / worktree 收尾时使用——如"收尾、把这个分支收掉、开发完了怎么处理、合并还是留着"。通常由 execute-task 执行完后调用。先只读预检状态，再清除本次开发遗留的调试代码、跑最终测试，然后给出合并/本地保留/创建 PR/丢弃选项；提交、合并、推送、删除与移除工作树都交用户拍板。不要用于：开发还没完、建立工作区（那是 setup-worktree）。

Use when users do not know which skill fits a task, need to search available skill catalogs, compare candidates, install a matching skill, or route work to the best existing capability.

Write growth logs that extract reusable patterns from complex tasks, failures, and learning moments, using a structured template and quality checklist.

Automates Capsule CRM operations including contacts, opportunities, cases, tasks, and pipeline management via Composio's Capsule CRM toolkit through Rube MCP.

Automates file conversion tasks using Composio's Conversion Tools toolkit via Rube MCP, with dynamic tool discovery and connection management.

Surface the most valuable next action by combining task stack, queue state, inbox pressure, health, and goals. Recommends one specific action with rationale. Triggers on "/next", "what should I do", "what's next".

Add a source file to the processing queue. Checks for duplicates, creates archive folder, moves source from inbox, creates extract task, and updates queue. Triggers on "/seed", "/seed [file]", "queue this for processing".

Launch N parallel subagents in isolated git worktrees to compete on the session task. Use when the user runs /hub:spawn or asks to start the competing agents for an initialized AgentHub session.

Use when a task needs a browser — reading a page, filling a form, taking a look at something, or reaching anything behind a login. Always run this skill before the `playwright-cli` skill.

Launch N parallel subagents in isolated git worktrees to compete on the session task. Use when the user runs /hub:spawn or asks to start the competing agents for an initialized AgentHub session.

Use this skill for removing accidental complexity, reducing duplication, clarifying boundaries, preserving behavior. Trigger when the task involves programming work related to Code Simplification, production implementation, audits, debugging, strategy, or validation.

Use this skill for dependency upgrades, SDK migrations, breaking changes, compatibility plans, rollback. Trigger when the task involves programming work related to Deprecation Migration, production implementation, audits, debugging, strategy, or validation.

Orchestrate token-heavy research, coding, and testing by delegating bounded tasks to cheaper subagents while reserving Claude Fable for architecture, synthesis, and final review.

Automate Zoho Mail tasks including email sending, folder and label management, and mailbox operations via Composio's Zoho Mail toolkit through Rube MCP.

Automate Zoho Inventory tasks via Rube MCP (Composio): items, orders, warehouses, shipments, and stock management. Always search tools first for current schemas.

Turns a spec or requirements into a detailed, bite-sized implementation plan with exact file paths, code, and test steps for engineers with no codebase context.

Composes ad-hoc teams of AI agents from local markdown personas and dispatches them in parallel on a task, then synthesizes their outputs.

Orchestrates VPN switching, geo-block diagnostics, and leak-aware task resumption by coordinating shell, curl, WireGuard, Tailscale, DNS, IPinfo, and MoltGuard skills.

当要在开始一段开发、或并行多个任务前，建立隔离的 git 工作区（worktree）以免污染当前工作区时使用——如"开个 worktree、隔离工作区、并行任务各自隔离"。通常由 execute-task 在执行前调用。先锁定 expected base，再选择能保证该基线的创建方式，并在创建后验证 HEAD。不要用于：不需要隔离的小改动、收尾/合并/清理（那是 finish-branch）、非 git 仓库。

Selects a minimal, non-redundant set of facts, artifacts, skills, and references for a working decision when context is stale, uncertain, or over budget.

Use this skill for queues, retries, idempotency, cron, dead-letter queues, background processing. Trigger when the task involves programming work related to Background Jobs Queues, implementation, audits, debugging, strategy, or validation.

Use this skill when you need guidance on which skill to use for any task. Recommends the perfect skill, creates skill combinations, and helps you discover capabilities you didn't know you had.