Results for “task”

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.

Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.

Execute phased plans with multiple independent tasks per phase by fanning out one agent per task, reconciling outcomes per wave, gating between phases with verify commands, and emitting a phase × outcome report. Triggers include "execute this plan", "work through these phases", "swarm over this backlog", "parallelize this plan".

Summarize Microsoft Teams conversations, triage unread or recent activity, draft follow-ups, and manage Planner tasks through connected Teams data. Use when the user wants to review chats or channels, identify owners and next steps, prepare a safe reply or post, or turn Teams follow-ups into Microsoft Planner tasks.

Universal project workflow with built-in quality auditing. Quick mode (fast brainstorm, ~5 min) or Deep mode (full plan with audits, ~30 min). Auto-picks based on task size. Trigger: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', or any project-level task.

Executes trivial coding tasks inline without subagent overhead, committing changes atomically.

Python asyncio - Modern concurrent programming with async/await, event loops, tasks, coroutines, primitives, aiohttp, and FastAPI async patterns

Practical async patterns using TaskEither - clean pipelines instead of try/catch hell, with real API examples

Stop throwing everywhere - handle errors as values using Either and TaskEither for cleaner, more predictable code

Delegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code with topic-aware sessions

Practical async patterns using TaskEither - clean pipelines instead of try/catch hell, with real API examples

Use when you have a spec or requirements for a multi-step task, before touching code

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

Use when you have a spec or requirements for a multi-step task, before touching code

Orchestrate multi-agent workflows with task decomposition, role assignment, handoff protocols, and per-session context budgeting.

Guidance on security analysis, compliance auditing, and vulnerability assessment techniques relevant to legal and regulatory compliance tasks

Set up application performance monitoring tools. TRIGGERS - Use when user needs help with apm-setup related tasks.

Design APQP plans for product quality. TRIGGERS - Use when user needs help with apqp-plan related tasks.

Create production call sheets with logistics. TRIGGERS - Use when user needs help with call-sheet related tasks.

Create comprehensive event plans with logistics. TRIGGERS - Use when user needs help with event-plan related tasks.

Write FAQ pages with comprehensive answers. TRIGGERS - Use when user needs help with faq-writer related tasks.

Conduct failure mode and effects analyses. TRIGGERS - Use when user needs help with fmea-guide related tasks.

Design Security Operations Centers with processes. TRIGGERS - Use when user needs help with soc-design related tasks.

Create stage plots for live performances. TRIGGERS - Use when user needs help with stage-plot related tasks.

Audit web applications for WCAG compliance. TRIGGERS - Use when user needs help with wcag-audit related tasks.

Write exam questions with difficulty progression. TRIGGERS - Use when user needs help with exam-writer related tasks.

Create RACI matrices for role assignment. TRIGGERS - Use when user needs help with raci-matrix related tasks.

Design CDN strategies for content delivery. TRIGGERS - Use when user needs help with cdn-strategy related tasks.

Create informed consent forms for procedures. TRIGGERS - Use when user needs help with consent-form related tasks.

Write ebooks with chapters and design. TRIGGERS - Use when user needs help with ebook-writer related tasks.

Design EHR templates for clinical documentation. TRIGGERS - Use when user needs help with ehr-template related tasks.

Conduct energy audits with efficiency recommendations. TRIGGERS - Use when user needs help with energy-audit related tasks.

Write HIPAA privacy notices and acknowledgments. TRIGGERS - Use when user needs help with hipaa-notice related tasks.

Create IEP templates for individualized education. TRIGGERS - Use when user needs help with iep-template related tasks.

Design JWT strategies with refresh tokens. TRIGGERS - Use when user needs help with jwt-strategy related tasks.