benchflow-ai

Choose placements that preserve useful residual capacity. Use for bin packing, GPU sharing, accelerator placement, and multi-resource scheduling where stranded capacity hurts future fit.

Validate and repair proposed resource allocations by replaying them against temporary capacity. Use when actions consume several resource dimensions such as CPU, memory, GPUs, or accelerators.

Design deterministic online scheduling policies from current observations. Use when assigning arriving work to limited resources without seeing future requests.

Three.js scene-graph parsing and export workflows: mesh baking, InstancedMesh expansion, part partitioning, per-link OBJ export, and URDF articulation.

Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.

SkillsBench task authoring — walk a contributor from idea to submission-ready task following CONTRIBUTING.md and the task-implementation rubric. Use when the user wants to create a new SkillsBench task, scaffold a task from an existing workflow (notebook, Excel workbook, document, dataset), convert a prompt or a benchmark item into a SkillsBench task, write skills for a task, or prepare a SkillsBench PR. Pairs with `task-review` (run that as a self-check before submitting).

SkillsBench task PR review — classifies the task track (standard / research / multimodal), runs static policy checks against the track-specific rubric, benchmarks the task across oracle plus Claude and Codex (with and without skills), audits trajectories for cheating and skill invocation, and produces a `pr-N-task-timestamp-run.txt` review report alongside a `prN.zip` bundle of trajectories. Use when reviewing a SkillsBench task PR (by number, branch, or local task path), when the user asks to review a task, run benchmarks on a PR, audit a submission, classify a task as research or multimodal track, or prepare a comment to post on a SkillsBench PR.

Use this skill when implementing the inner control loop for a quadrotor — attitude (roll/pitch/yaw) PID control and attitude planning (converting desired acceleration to desired Euler angles). Covers gain layout, integral reset pattern, and the attitude planner inverse kinematics.

Incorporate feedback from an independent code reviewer to improve your solution. The reviewer is a different agent that analyzed your work.

Run agent benchmarks, create tasks, analyze results, and manage agents using BenchFlow. Use when asked to benchmark an AI coding agent, run a benchmark suite, create tasks, view trajectories, or compare agent performance.

Verify academic citations, detect hallucinated BibTeX entries, repair DOI metadata, and produce normalized bibliography outputs without inventing sources.

Delegate complex coding tasks to a specialist model. Use when facing algorithmic challenges, performance optimization, or tricky debugging that benefits from focused code expertise.

Run agent benchmarks, create tasks, analyze results, and manage agents using BenchFlow. Use when asked to benchmark an AI coding agent, run a benchmark suite, create tasks, view trajectories, or compare agent performance.

Pre-push branch reviewer — runs lint+typecheck+tests, then fans /code-cleanup, /test-review, /docs-review at the branch diff, merges findings by file

Two-pass subagent sweep for trivial/small refactoring wins — find candidates, then verify each before recommending

Review benchflow documentation for drift, staleness, duplication, and alignment