Results for “tasks”

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.

Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements. Routes cheap tasks to Haiku/GPT-4o-mini and complex tasks to Sonnet/Opus/o1. Use when deciding which model to call, optimizing LLM costs, or building multi-model agent systems. Activate on "which model", "model selection", "route to model", "LLM cost", "model routing", "cheap vs expensive model". NOT for prompt engineering (use prompt-engineer), model fine-tuning, or training custom models.

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

Routes NVIDIA Nemotron Speech (Riva) NIM tasks for ASR, TTS, and NMT, covering cloud-hosted inference, self-hosted Docker deployment, and custom model builds.

Builds reliable browser automation skills through iterative experimentation, running an inner agent to browse sites and improving navigation instructions until tasks pass consistently.

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.

Automate Benchmark Email marketing tasks through Composio's Rube MCP integration, including contact management, campaign creation, and email sending.

Automate Wave Accounting tasks including invoices, customers, payments, and small business accounting via Composio's Wave Accounting toolkit and Rube MCP.

Automate Anthropic Admin tasks including API keys, usage, workspaces, and organization management via Composio's Anthropic Admin toolkit and Rube MCP.

Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.

Use `review-agent` for a high-risk Engineering Brief when a critical path, architecture boundary, material risk, or multiple downstream tasks need deeper design evidence. Skip ordinary work without those signals.

Discovers and invokes agent skills by mapping tasks to development phases, with core operating behaviors for assumption surfacing, confusion management, and scope discipline.

Discovers and installs agent skills from the open ecosystem when users ask for help with specific tasks or express interest in extending capabilities.

Integrate with Azure AI services including Search, Speech, OpenAI, and Document Intelligence for search, transcription, OCR, and text-to-speech tasks.

Enables AI agents to pay humans with USDC via molty.cash, supporting tips, hiring for tasks, and creating gigs with on-chain settlement on Base.

Guides data analysis, EDA, and ML tasks by teaching, diagnosing MCPs, and deciding with the user, offering multiple options and documenting decisions.

Trains LLMs with SimPO, a reference-free preference optimization method that outperforms DPO, using configurable hyperparameters and workflows for various models and tasks.

Benchmarks medical AI agents on synthetic EHR tasks, measuring success rates for data retrieval, temporal aggregation, and threshold-based conditional logic with exact-match scoring.

Use `analysis-agent` to create a Task DAG from an accepted source-backed Brief when 2+ tasks have dependencies, parallel value, integration, or release order. Skip single edits, accepted DAGs, and unanalysed requests.

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

Agent spawning, lifecycle management, and coordination patterns. Manages 60+ agent types with specialized capabilities. Use when: spawning agents, coordinating multi-agent tasks, managing agent pools. Skip when: single-agent work, no coordination needed.

Write high-performance GPU kernels using cuTile's tile-based programming model with validation and optimization, including deep agent orchestration for complex multi-kernel tasks.

Automate Google Admin tasks including user management, org units, groups, and domain administration via Rube MCP and Composio's Google Admin toolkit.

Orchestrate multi-agent coding tasks via Claude DevFleet: plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.

Discovers and installs agent skills from the open ecosystem using the Skills CLI, helping users find capabilities for tasks like web development, testing, and design.

Map which elements of an assignment benefit from AI assistance vs. which AI use undermines. Use when redesigning tasks for AI-age classrooms or setting defensible AI use policies for specific assignments.

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.

Tactical fast path: turn a small problem, bug report, edit request, or narrow refactor into three deliverables — a brief change-spec (docs/specs/), a detailed implementation-ready plan (docs/plans/), and a TODO.md with agent-pickable tasks and milestones. Load when the user describes a tactical problem and wants quick planning artifacts, says "plan this change", "create a TODO", "write a plan for this", "problem to plan", "break this into tasks for agents", "I want to change X — plan it", or when process-decomposer routes here after determining the user needs lightweight planning deliverables. Also triggers on "create tasks from this problem", "make this actionable", or "turn this into a plan agents can execute". For feature-sized work that needs an executable spec + constitution + cross-check gate, route to `spec-driven-development` (or `feature-spec`) instead.

Perform time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search using a scikit-learn compatible Python toolkit.

Evaluates open-ended generation quality of multilingual LLMs across brainstorming, planning, and long-form tasks, using AYA and DOLLY datasets with qualitative fluency and quality scoring.

Fine-tune, evaluate, run inference, and export Cosmos-Embed1 video-text embedding models for tasks like text-to-video retrieval and semantic deduplication.

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.

Run ML workloads on Modal's serverless GPU cloud: deploy models as auto-scaling APIs, run batch jobs, and schedule tasks with pay-per-second GPU pricing.

This skill should be used when the user asks to "/do-agent", asks for "Execute complex tasks using multi-agent architecture with context protection", or needs the workflow previously provided by the /do-agent slash command.

Integrate Xquik into apps, scripts, data pipelines, or AI agents for X API tasks like tweet search, user lookup, follower export, media actions, and webhook verification.