Run TensorRT-LLM test cases, benchmarks, evaluations, or custom scripts by checking the environment (local GPU or Slurm), selecting the appropriate Docker image, and executing either locally or via Slurm job submission. Accepts pre-built command strings — command construction for trtllm-bench, trtllm-eval, and…
Use when a task file exists in .hyperflow/tasks/ and workers need dispatching. Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy. Trigger with /hyperflow:dispatch, "run the plan", "execute the task", "build it"…
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
Security-focused command execution techniques for penetration testing. Use this skill when executing system commands during authorized security assessments. Covers Windows and Linux command execution, common security testing commands, and best practices for avoiding detection.
A change-management framework for introducing only one or two new team routines each quarter. A routine is a repeated way of working, such as a daily meeting, one-to-one, or planning review.
Trigger Falcon Fusion workflows, monitor execution status, and debug failures. TRIGGER when user asks to run a workflow, check execution status, tail logs, get execution results, or debug a workflow failure. DO NOT TRIGGER for writing YAML (use authoring) or importing/releasing workflows (use deployment).
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
Use when writing a product spec, feature spec, API contract, agent task spec, or any other specification where a zero-question document is required. Encodes outcome-first methodology, acceptance criteria taxonomy, scope boundary protocol, executor context model, and ambiguity resolution framework.
Coordinate N parallel agents on a shared task list using the Agent tool and TeamCreate. Use for multi-lane execution, fan-out, shared delivery+verification, and long-running lanes tracked across a session.
Execute a single Todo task through In Progress to Review, meeting every acceptance criterion with tests and vibe-lint checks. Refuses Planning-status tasks. Invoked as /agiflow:run-task . Uses gettask, updatetask, createtaskcomment.
Execute a work unit end-to-end: sequence tasks by dependency, implement, test between tasks, commit, and track progress. Use to deliver a complete feature in one session. Invoked as /agiflow:run-work . Uses getworkunit, listtasks, updatetask, getworkunitprogress.