Results for “task-framing”

Train, evaluate, export, quantize, and run inference for a TAO OneFormer model that performs panoptic, instance, and semantic segmentation using task-conditioned queries.

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

`task-agent`/`review-agent`: use when CPU, memory, I/O, database, network, rendering, or cost needs measured bottleneck evidence; skip without a profiling need.

Decompose a task into parallel workstreams, assign agent ownership, run integration at dependency boundaries, and synthesize results.

Use with analysis-agent or task-agent for task-local transaction, isolation, and conflict decisions. Do not use without a transaction decision or as task owner.

Modify a classroom task with language scaffolds that preserve cognitive demand for EAL learners. Use when adapting existing tasks for students at different English proficiency levels.

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

`task-agent`: use when local, server, global, derived, optimistic, persisted, form, auth, or cache state ownership changes; skip when state boundaries are unaffected.

Orchestrates multi-agent workflows defined in YAML piece files, delegating tasks to team members and managing state transitions.

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

Use with analysis-agent, task-agent, or review-agent for task-local authentication lifecycle and recovery risk. Do not use without that decision or as task owner.

Two-party working posture — user as director, agent as executor. Every fork, tradeoff, and taste choice is surfaced via batched AskUserQuestion with structural framing, a recommended default, and concrete previews when comparison is visual, so the human steers direction while the agent handles implementation. Eliminates the review-bottleneck (no giant diff to approve at the end — review is distributed across picks) and prevents codebase-understanding debt (the user remembers the architecture because they picked it). Use whenever the user invokes /duet, or says "work with me", "ask before", "check with me", "I want to decide", "don't assume", "human-in-the-loop", "co-author", "pair with me", "duet", or whenever a task clearly involves aesthetic, architectural, or irreversible strategic decisions — even without those exact words. Pair with the Duet output style to minimize cognitive load between picks.