Agent Skills: task-review
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.
ID: benchflow-ai/skillsbench/task-review
1,819369
Install this agent skill to your local
Skill Files
The files that make up task-review.
Loading file tree…
More agent skills
- mhc-algorithmImplement mHC (Manifold-Constrained Hyper-Connections) for stabilizing deep network training. Use when implementing residual connection improvements with doubly stochastic matrices via Sinkhorn-Knopp algorithm. Based on DeepSeek's 2025 paper (arXiv:2512.24880).
- modal-gpuRun Python code on cloud GPUs using Modal serverless platform. Use when you need A100/T4/A10G GPU access for training ML models. Covers Modal app setup, GPU selection, data downloading inside functions, and result handling.
- cvss-score-extractionExtract CVSS (Common Vulnerability Scoring System) scores from vulnerability data sources with proper fallback handling. This skill covers understanding CVSS v3, handling multiple score sources (NVD, GHSA, RedHat), implementing source priority logic, and dealing with missing scores in security reporting.
- erlang-concurrencyUse when erlang's concurrency model including lightweight processes, message passing, process links and monitors, error handling patterns, selective receive, and building massively concurrent systems on the BEAM VM.
- glm-basicsBasic usage of the General Lake Model (GLM) for lake temperature simulation. Use when you need to run GLM, understand input files, or modify configuration parameters.
- jax-skillsHigh-performance numerical computing and machine learning workflows using JAX. Supports array operations, automatic differentiation, JIT compilation, RNN-style scans, map/reduce operations, and gradient computations. Ideal for scientific computing, ML models, and dynamic array transformations.