Results for “task”

Delegates tasks to specialized AI agents running in parallel via the Box0 platform, enabling code review, security checks, research, and documentation.

Executes approved Flow plans one atomic task at a time with test-first implementation, fresh verification, blocker handling, and durable evidence.

Loads a written implementation plan, reviews it critically, executes all tasks with verification, and reports completion, stopping to ask for help when blocked.

Configures and operates moonrepo monorepo build systems, covering workspace and project configuration, task orchestration, toolchain management, CI integration, Docker support, and querying.

Measurement-driven model router for Claude Code. Routes Haiku/Sonnet/Opus per task class, logs every routed task with real $ numbers, and A/B tests cheaper tiers before you trust the savings.

Self-referential loop until task completion with architect verification

List all scheduled cron tasks managed by Custodian

当使用 delegate_task 派生子代理生成文件时，子代理的文件在其隔离上下文中，主代理无法直接读取。本技能记录文件交付的坑点和解决方案。

Self-referential loop until task completion with architect verification

Only to be triggered by explicit /parallel-task commands.

Analyzes development requirements and generates structured acceptance criteria for AEM Edge Delivery Services tasks, including task breakdowns and edge case identification.

Creates professional GitHub issues—bug reports, feature requests, and technical tasks—with clear context, acceptance criteria, and labels for immediate action.

Orchestrates multi-agent teams using the ClawTeam CLI, enabling task management, inter-agent messaging, git context integration, runtime profiles, and monitoring dashboards.

Captures ideas, tasks, or issues during a GSD session as structured todos for later work, enabling a thought-to-capture-to-continue flow without losing context.

Design and author reusable subagents for specialized AI tasks. Use when the task needs an isolated agent persona, scoped system prompt, or reusable domain-specific assistant rather than a general skill.

Create, transition, query, and link WorkItems — tasks, stories, bugs, epics. Use when the user asks to add, update, query, or link work items — backlog items, tasks, bugs, user stories, or epics.

Schedule recurring tasks with cron on Linux/macOS. Use when a user asks to run scripts on a schedule, set up automated backups, schedule data processing, or configure periodic tasks on a server.

When tackling a task that requires domain expertise beyond general coding ability — architecture patterns, framework-specific gotchas, deployment strategies, security anti-patterns, or specialized workflows — call the windags_skill_graft MCP tool with your task description. You'll receive expert knowledge including decision trees, failure modes, worked examples, and anti-patterns from a library of 503+ curated skills. Only graft when the task genuinely requires specialized knowledge. Simple tasks (rename a variable, fix a typo, format code) do not need grafting.

Executes a written implementation plan in a separate session, reviewing it critically, running tasks with verification, and stopping to ask for help when blocked.

Routes tasks to locally installed CLI tools using semantic matching. Triggers on tasks requiring shell commands, file operations, code search, data processing, visualization, or external tool invocation. Uses cli-index for semantic routing.

Assign a task to a specific role on your team.

Delete a scheduled cron task by name or ID

Execute TODO.md steps via unattended Claude Code sessions

Benchmark LLM performance across tasks — latency, quality, cost comparison.

Self-referential loop until task completion with configurable verification reviewer

Use for lightweight implementation, edits, and straightforward coding tasks.

Provides Gemini CLI delegation workflows for large-context analysis tasks, including English prompt formulation, execution flags, and safe result handling. Use when the user explicitly asks to use Gemini for a specific task such as broad codebase analysis or long-document processing. Triggers on "use gemini", "delegate to gemini", "run gemini cli", "ask gemini", "use gemini for this task".

Creates detailed, step-by-step implementation plans from specs or requirements, with task decomposition, file structure, and test-driven development instructions.

Design a usability test plan with tasks, success metrics, participant criteria, and facilitation guide for moderated or unmoderated sessions.

Decomposes an approved specification into dependency-aware waves and atomic executable tasks with exact file scope, test-first actions, verification commands, and an execution gate.

Query and manage ClickUp tasks, spaces, lists, and assignees via the REST API, with helper scripts for common operations and guidance on pagination and subtasks.

Routes content creation requests to the appropriate specialist skill, directing writing and brand voice tasks to content-production and planning tasks to content-strategy.

Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.

Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.

Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.

Use this skill for context gathering, file triage, source maps, assumptions, task framing, prompt hygiene. Trigger when the task involves programming work related to Context Engineering, production implementation, audits, debugging, strategy, or validation.