Results for “task”

Orchestrates teams of specialized AI agents with role-based collaboration, memory, and sequential or hierarchical execution for complex multi-step tasks.

Guides AI agents through engineering workflows with eval-first execution, task decomposition, cost-aware model routing, and review focus for generated code.

Guides project-level decisions for LLM-powered systems: task-model fit, pipeline architecture, token and cost estimation, and agent-assisted iteration.

Automates ClickUp task, list, folder, and space management via the REST API v2, including time tracking, goals, custom fields, dependencies, and webhooks.

Designs collaborative AI agent teams using the CrewAI framework, covering agent roles, task decomposition, crew orchestration, process types, memory systems, and event-driven flows.

Drives a PRD-based persistence loop that iterates on a task until all user stories pass and are reviewer-verified, with automatic retry and progress tracking.

Use when passing work, tasks, or deliverables between agents. This skill provides a standardized protocol for agent-to-agent handoffs, ensuring context, requirements, and expectations are clearly communicated during task delegation or escalation.

N coordinated agents on shared task list using tmux-based orchestration

Structured task planning with clear breakdowns, dependencies, and verification criteria.

N coordinated agents on shared task list using tmux-based orchestration

Navigation aid for the processkit skill catalog — maps natural-language cues and task types to the right skill. Read this when you are unsure which skill applies to the current task, when the user names a task without naming a skill, or at session start when orienting to an unfamiliar project. Always the first skill to consult; never the last.

Divide un cambio de diseño aprobado en tareas concretas, ordenadas por dependencias y agrupadas por fase, con criterios de done y un forecast de workload para revisión.

Retrieve task-relevant project and global memory without loading everything. Load when the user asks what we decided, recall prior context, find memory about a feature, explain past rationale, resume a task, or check deferred ideas.

P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when coordinating 3+ parallel agents. Produces: Task Prompts (六要素) + P8 team delivery.

Coordinate multi-agent development pipelines using shared JSON task files. Use when dispatching work across dev team agents (code-agent, test-agent, docs-agent, monitor-bot), tracking pipeline progress, or running sequential/parallel workflows. Covers project init, task assignment, status tracking, agent dispatch via sessions_send, and result collection. Supports two modes: linear (sequential pipeline) and dag (dependency graph with parallel execution).

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining, covering SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Generates task-oriented technical documentation with progressive disclosure for READMEs, API docs, architecture docs, and security reports after reverse engineering, penetration testing, or CTF tasks.

Guides agents to delegate tasks to specialized sub-agents using a decision tree and automatic triggers, with recursive spawning and integration with an agent-router MCP.

P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when coordinating 3+ parallel agents. Produces: Task Prompts (六要素) + P8 team delivery.

Capture idea or task as todo from current conversation context

Team worker protocol (ACK, mailbox, task lifecycle) for tmux-based OMX teams

飞书任务：管理任务和清单。创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员。当用户需要创建待办事项、查看任务列表、跟踪任务进度、管理项目清单或给他人分配任务时使用。

Team worker protocol (ACK, mailbox, task lifecycle) for tmux-based OMX teams

Use when specialized expertise is needed to unblock delivery on this task.

Use for high-throughput implementation tasks from clear specs and acceptance criteria.

Queue processing with fresh context per phase. Processes N tasks from the queue, spawning isolated subagents to prevent context contamination. Supports serial, parallel, batch filter, and dry run modes. Triggers on "/ralph", "/ralph N", "process queue", "run pipeline tasks".

Build automated AI workflows combining multiple models and services for batch processing, scheduled tasks, event-driven pipelines, and agent loops using the inference.sh CLI.

Provides proven architectural patterns for building n8n workflows, covering webhook processing, HTTP API integration, database operations, AI agent workflows, batch processing, and scheduled tasks.

Generate a Notion-style live team dashboard with KPI cards, 7-day sparklines, activity feed, and task table, using seed data when no data source is available.

Create a new AgentHub collaboration session with task, agent count, and evaluation criteria.

N coordinated agents on shared task list using Claude Code implicit agent teams

Recommends the optimal Claude model tier (Opus, Sonnet, or Haiku) for a given task by analyzing reasoning depth, blast radius, domain expertise, output length, and correctness cost, and suggests parallelization opportunities.

Runs Google Workspace cross-service workflows via the gws CLI, with helpers for standup reports, meeting prep, email-to-task conversion, weekly digests, and file announcements.

Use before touching any code when user gives a task, spec, or feature request. Forces writing a plan before implementation. Examples: 'implement X', 'add feature Y', 'fix Z and also update A', any multi-step task that would touch 2+ files.

Launch N parallel subagents in isolated git worktrees to compete on the session task.

Generate a map of all files relevant to a task before making changes