What it does
This repo is a collection of 235 skills
- Connects Instruction files the AI reads, with steps that call an outside service
- Account or key Some steps need a key for MODAL_TOKEN_SECRET, Anthropic, OpenAI (per the README)
- Category 自动化与智能体
Maker’s original description
SkillsBench evaluates how well skills work and how effective agents are at using them.给作者:在 README 中加徽章
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/benchflow-ai-skillsbench)相似的 Skill
同类工作,排序与 Skill 列表相同
benchflow-ai 提供的 235 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
Pick the skill to install
Install only the ones you use. Open a skill to see how to install it
This set has 235 skills, too many to install at once: every installed skill’s description loads into every chat, so the AI picks the wrong one more easily. Pick only the ones you use from the list below
Showing 28 of 235 See all on GitHub
- attention-variants-from-papers
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.
- comp3-packed-decimal
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 t…
- contract-playbook-review
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 resu…
- ebcdic-overpunch-decoding
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. "00…
- fragmentation-aware-packing
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.
- gemini-count-in-video
Analyze and count objects in videos using Google Gemini API (object counting, pedestrian detection, vehicle tracking, and surveillance video analysis).
- gemini-video-understanding
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).
- gh-cli
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.
- gl-posting-codes
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.
- gnucobol-mainframe-batch
GnuCOBOL toolchain pointers for mainframe-style batch programs (LINE/RECORD SEQUENTIAL files, PIC clauses, cobc build flags).
- gpt-multimodal
Analyze images and multi-frame sequences using OpenAI GPT series
- mhc-algorithm
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).
- modal-gpu
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.
- multi-resource-allocation-validation
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.
- nanogpt-training
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.
- nda-clause-taxonomy
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 / mu…
- online-resource-scheduling
Design deterministic online scheduling policies from current observations. Use when assigning arriving work to limited resources without seeing future requests.
- paired-reversal-cancellation
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 c…
- pdf
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
- pubchem-database
Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics.
- rdkit
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…
- skill-creator
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.
- skillsbench
SkillsBench contribution workflow. Use when: (1) Creating benchmark tasks, (2) Understanding repo structure, (3) Preparing PRs for task submission.
- task-creator
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…
- 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 produ…
- triangulated-fx-rates
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, re…
- video-frame-extraction
Extract frames from video files and save them as images using OpenCV
- xlsx-parsing
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…
Skill 和 MCP 有什么不同
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
适用的应用
Codex
依据开发者 README 和 repo 中的文件夹
安装
Pick a skill first
This repo has 235 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
来自 GitHub
- GitHub 星标
- 1,924
Stars are for the whole repo, not each skill - 开发者
- benchflow-ai
- 许可证
- Apache-2.0
- 最近代码更新
- 2026年11月17日
- repo 中的 SKILL.md 文件(含译本和模板)
- 30
- 主题
- benchmark, skillsbench