Skill Claude CodeCodex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
Skill Claude CodeCodex
SkillsBench contribution workflow. Use when: (1) Creating benchmark tasks, (2) Understanding repo structure, (3) Preparing PRs for task submission.
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
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…
Instructions file CodexOpenCode
Instructions for benchflow-ai/skillsbench, covering skillsbench, commands, task layout, rules and key references.
Instructions file
Instructions for benchflow-ai/skillsbench: See AGENTS.md for project overview and contribution guidelines.
Skill Claude CodeCodex
Reference for COBOL COMP-3 (packed decimal / BCD) numeric storage -- layout on disk, declaring it in the FD, and pitfalls when carrying the decoded value through working storage and into later arithmetic. Useful when an input record holds a balance, rate, or carry-forward as packed decimal rather than a printable…
Skill Claude CodeCodex
Reference for the EBCDIC "overpunch" / zoned-decimal sign convention where the units position of a numeric field is replaced with a letter that encodes both a digit and a sign. Useful when reading mainframe-style fixed-length tapes whose amount fields appear as digits followed by a letter (e.g. "0000000000123D" or…
Skill Claude CodeCodex
Background on general-ledger batch posting codes (HD/DR/CR/RV plus signed "other" rows). Reference only -- follow the task instruction for the exact rules, which may differ per account type.
Skill Claude CodeCodex
GnuCOBOL toolchain pointers for mainframe-style batch programs (LINE/RECORD SEQUENTIAL files, PIC clauses, cobc build flags).
Skill Claude CodeCodex
Reference for paired-reversal handling on GL batch tapes: an RV row whose ref-trace points at an earlier row cancels BOTH legs (the RV and the row it references) — but ONLY when the two value-dates fall within the shop's reversal settlement window; an RV that references a too-old posting is NOT a cancellation and…
Skill Claude CodeCodex
Reference for multi-hop / triangulated currency conversion on batch rate tapes. When a rate row carries an explicit "via" currency, the row's rate is only one leg of the conversion, and the via currency may ITSELF be quoted through another via — so the effective rate is the product of every leg, resolved by walking…
Skill Claude CodeCodex
Implement paper-defined attention variants by extracting mechanism invariants, mapping tensor shapes, preserving module interfaces, validating numerical behavior, and integrating the custom attention into an existing transformer stack.
Skill Claude CodeCodex
Run 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.
Skill Claude CodeCodex
PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.
Skill Claude CodeCodex
Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics.
Skill Claude CodeCodex
Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom…
Skill Claude CodeCodex
The gh CLI is GitHub's official command line tool for interacting with GitHub repositories, issues, pull requests, and more. When needs to interact with GitHub repositories, issues, pull requests, and more, use this skill.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
Design deterministic online scheduling policies from current observations. Use when assigning arriving work to limited resources without seeing future requests.
Skill Claude CodeCodex
Implement 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).
Skill Claude CodeCodex
Train GPT-2 scale models (124M parameters) efficiently on a single GPU. Covers GPT-124M architecture, tokenized dataset loading (e.g., HuggingFace Hub shards), modern optimizers (Muon, AdamW), mixed precision training, and training loop implementation.
Skill Claude CodeCodex
Methodology for clause-by-clause review of a contract against a structured deviation policy ("playbook"). Covers how to walk a playbook, locate the matching provision in the contract, apply rule types (max-value, must-be-present, must-be-absent, acceptable-set, must-have-feature), classify the result (ok / risk /…