benchflow-ai/skillsbench

---

name: comp3-packed-decimal

description: 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 digit string.

---

name: ebcdic-overpunch-decoding

description: 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 "0000000000045M").

---

name: gl-posting-codes

description: 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.

---

name: gnucobol-mainframe-batch

description: GnuCOBOL toolchain pointers for mainframe-style batch programs (LINE/RECORD SEQUENTIAL files, PIC clauses, cobc build flags).

---

name: paired-reversal-cancellation

description: 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 posts one-sided. Useful when the posting tape carries a reference-trace column alongside reversal codes and the running balance is off by twice the reversal magnitude, or by a whole leg on stale references.

---

name: triangulated-fx-rates

description: 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 the chain until a direct quote is reached. Useful when an FX feed lists some pairs directly to the reporting currency and others as triangulated (or doubly-triangulated) quotes through vehicle currencies.

---

name: attention-variants-from-papers

description: 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.

---

name: modal-gpu

description: 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.

---

name: pdf

description: PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.

---

name: pubchem-database

description: Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics.

---

name: rdkit

description: 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 sanitization, specialized algorithms.

---

name: gh-cli

description: 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.

---

name: fragmentation-aware-packing

description: 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.

---

name: multi-resource-allocation-validation

description: 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.

---

name: online-resource-scheduling

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

---

name: mhc-algorithm

description: 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).

---

name: modal-gpu

description: 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.

---

name: nanogpt-training

description: 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.

---

name: contract-playbook-review

description: 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 / reject), choose the prescribed action, and ground each finding in a verbatim excerpt. Use whenever reviewing any contract — NDA, MSA, vendor DD questionnaire, lease, DPA — against a structured rules-based playbook.

---

name: nda-clause-taxonomy

description: Reference for the standard clauses found in commercial non-disclosure agreements (mutual and one-way) — what each clause does, the surface forms it appears in, and how to recognise it in unfamiliar drafting. Use when reviewing, comparing, or extracting provisions from any confidentiality / NDA / mutual NDA / standstill-and-confidentiality agreement.

---

name: xlsx-parsing

description: Read Microsoft Excel (.xlsx) files robustly with `openpyxl` (or `pandas`). Covers multi-sheet workbooks, header rows, empty cells, merged cells, comma-separated list cells, and converting a sheet to a list-of-dicts the rest of your code can consume. Use when a task input or reference document is an `.xlsx` file rather than JSON/CSV.

---

name: gemini-count-in-video

description: Analyze and count objects in videos using Google Gemini API (object counting, pedestrian detection, vehicle tracking, and surveillance video analysis).

---

name: gemini-video-understanding

description: Analyze videos with Google Gemini API (summaries, Q&A, transcription with timestamps + visual context, scene/timeline detection, video clipping, FPS control, multi-video comparison, and YouTube URL analysis).

---

name: gpt-multimodal

description: Analyze images and multi-frame sequences using OpenAI GPT series

---

name: video-frame-extraction

description: Extract frames from video files and save them as images using OpenCV

---

name: audiobook

description: Create audiobooks from web content or text files. Handles content fetching, text processing, and TTS conversion with automatic fallback between ElevenLabs, OpenAI TTS, and gTTS.

---

name: elevenlabs-tts

description: ElevenLabs Text-to-Speech API for high-quality speech synthesis.

---

name: gtts

description: Google Text-to-Speech (gTTS) for converting text to audio. Use when creating audiobooks, podcasts, or speech synthesis from text. Handles long text by chunking at sentence boundaries and concatenating audio segments with pydub.

---

name: openai-tts

description: OpenAI Text-to-Speech API for high-quality speech synthesis. Use for generating natural-sounding audio from text with customizable voices and tones.

---

name: constraint-parser

description: Parse scheduling constraints from a email text.