Search

OpenAI · For data scientists

99 skills found, page 2.
Search results
#SkillRepositoryStarsUsed inTokensAuto-checkLicenceUpdated
49

A skill your agent uses when certifying mesh-llm KV/cache stability under repeated OpenAI tool-call loops, same-prefix cache reuse, suffix-prefill limits, or native Skippy slot/decode/eviction…

Mesh-LLM/mesh-llm3.5k—~704Automated safety check: PassApache-2.0today
50

A skill your agent uses when composing prompts targeting GPT-6 Sol (GPT 디폴트), GPT-6 Astra, GPT-6 Luna, GPT-5.6 Sol (직전 디폴트), legacy GPT-5.5/5.4/5.2 — lean outcome-first 7블록 규칙 + LEGACY 섹션(구 XML 스택)을…

treylom/prompt-engineering-skills185—~334Automated safety check: PassUnknown14 days ago
51

Continue's prompt caching is opt-in via config and off by default.

OnlyTerp/prompt-cache-skills114—~977Automated safety check: PassUnknown1 mo ago
52

Build AI agents with tools, memory, and multi-step reasoning - ChatGPT, Claude, Gemini integration patterns

claude-office-skills/skills505—~3.1kAutomated safety check: PassMIT8 mo ago
53

当系统提示词需要设计多代理协作架构、子代理专业化分工、代理间上下文隔离与传递机制、任务生命周期管理时调用此 Skill。适用于 AI Agent 平台、多工具编排系统、代码审查流水线、跨应用协作场景等。不适用于:单代理系统(无委派需求)、简单工具调用(无子代理概念)、纯 API 编排(无 AI 决策)。当需求聚焦于"单代理内的对话路由"而非"多代理间的任务分配"时,应该用…

kangarooking/system-prompt-skills208—~897Automated safety check: PassMIT5 mo ago
54

Build a low-latency, Iron Man-inspired tactical voice assistant (F.R.I.D.A.Y.) using Pipecat, Gemini, and OpenAI.

sickn33/agentic-awesome-skills47k2 repos~872Automated safety check: NotesMITyesterday
55

📝 Prompt Library workflow skill. An agent skill from diegosouzapw/awesome-omni-skills.

diegosouzapw/awesome-omni-skills159—~3.1kAutomated safety check: PassMIT3 mo ago
56

Curated upstream guidance for Longbridge Quant; use when the workflow matches the user goal.

sickn33/agentic-awesome-skills47k1 repo~1.5kAutomated safety check: PassMITyesterday
57

当系统提示需要设计引用格式、信息溯源机制、来源标注系统时调用。适用于文档问答、搜索增强生成(RAG)、代码引用、浏览器辅助等需要让用户追溯信息来源的场景。不适用于纯创作类输出(如故事、诗歌),不适用于无需溯源的常识问答,也不适用于注入防御(虽然两者都涉及内容可信度)。

kangarooking/system-prompt-skills208—~655Automated safety check: PassMIT5 mo ago
58
58.Self

Answer questions about how 'mi' works, write new tools, or modify the harness.

av/mi102—~1.4kAutomated safety check: PassNo licence15 days ago
59

A skill your agent uses when running, configuring, debugging, or embedding skippy-serving, binary stage transport, OpenAI frontend integration, activation wire dtype settings, stage configs…

Mesh-LLM/mesh-llm3.5k—~380Automated safety check: PassApache-2.0today
60

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems.

davila7/claude-code-templates33k3 repos~565Automated safety check: PassMITyesterday
61

Applies the reasoning style of Ilya Sutskever (deep learning pioneer, co-founder of OpenAI and Safe Superintelligence Inc.) to problems involving AI architecture, scaling laws, alignment, and…

K-Dense-AI/mimeo282—~1.7kAutomated safety check: PassMIT1 mo ago
62

Optimize LLM prompt caching hit rate to reduce API costs and improve latency.

affaan-m/ECC276k—~2.5kAutomated safety check: PassMITyesterday
63

Vector database implementation for AI/ML applications, semantic search, and RAG systems.

ancoleman/ai-design-components525—~3.5kAutomated safety check: PassMIT10 mo ago
64
64.Prompt OptimizerOfficial

Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates.

getsentry/skills1k—~1.2kAutomated safety check: PassApache-2.02 days ago
65

通用 AI 生图:文生图 / 图生图 / 图像变体。当用户说 AI 生图、AI 画图、文生图、图生图、生成图片、生成配图、图像生成、AI 出图、AI 作图、换图、改图、图像编辑、给我画一张、生成一张图 时使用。支持 OpenAI 兼容 API 与 apimart 异步 API,用户自备 API key。

ZJU-REAL/Easel3.4k—~787Automated safety check: NotesApache-2.02 days ago
66

Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI.

sickn33/agentic-awesome-skills47k2 repos~447Automated safety check: PassMIT2 days ago
67

Evolve prompts/regex/SQL/code with Imbue's evolution loop. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent1712 repos~2.1kAutomated safety check: WarnMIT3 days ago
68

Integrate RouterBase as an OpenAI-compatible model gateway for routing GPT, Claude, Gemini, media, audio, and embedding requests.

sickn33/agentic-awesome-skills47k1 repo~1.8kAutomated safety check: PassMIT-02 days ago
69

A skill your agent uses when a user provides ChatGPT web AI-search keywords, repeat count, target entity, entity type, OpenCLI profile, and crawl interval preference, then needs repeated crawls…

yaojingang/yao-geo-skills871—~456Automated safety check: PassMIT10 days ago
70

Grade or filter workflow HDF5 episodes with an OpenAI-compatible vision model.

NVIDIA/skills3.6k1 repo~1.5kAutomated safety check: PassApache-2.02 days ago
71

Run the corpus benchmark — booster locally, optional Gemini/Sonnet/Opus baselines — and persist a verifiable measured-vs-claimed table

ruvnet/ruflo74k—~745Automated safety check: NotesMITyesterday
72

Connect a ChatGPT or Claude account and sync its conversation history into the brain automatically.

garrytan/gbrain31k—~2.8kAutomated safety check: PassMITyesterday
73

当系统提示词需要定义 AI 如何分类用户意图、路由到不同处理流程、决定澄清策略和自主度级别时调用此 Skill。适用于多任务型 AI 助手、客服机器人、编程工具、研究助手等需要结构化对话管理的场景。不适用于:纯问答型系统(无任务执行)、单轮交互(无对话状态)、简单的 prompt 模板(无路由逻辑)。当需求仅涉及"输出什么格式"而非"如何决定输出什么"时,应该用…

kangarooking/system-prompt-skills208—~788Automated safety check: PassMIT5 mo ago
74

Knowledge base from "Spinning Up in Deep RL" by Joshua Achiam (OpenAI, MIT-licensed).

alirezarezvani/claude-skills28k—~2.8kAutomated safety check: PassMIT1 mo ago
75

Tests/benchmarks a third-party LLM endpoint (OpenAI- or Anthropic-compatible): availability, fidelity, speed, concurrency, protocol compliance, quality regression.

daymade/claude-code-skills1.4k—~4.7kAutomated safety check: PassMITyesterday
76

Generate and improve prompts using best practices for OpenAI GPT-5 and other LLMs.

jamesrochabrun/skills216—~4.2kAutomated safety check: PassMIT9 mo ago
77

Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.

aiskillstore/marketplace4333 repos~3.9kAutomated safety check: PassNo licenceyesterday
78

AI crawler access analysis.

sickn33/agentic-awesome-skills47k1 repo~4.8kAutomated safety check: NotesMIT2 days ago
79

Save the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuning

AgentToolkit/altk-evolve123—~1.4kAutomated safety check: PassApache-2.02 days ago
80

Enable and configure Moltbot/Clawdbot memory search for persistent context.

sundial-org/awesome-openclaw-skills6631 repo~1kAutomated safety check: PassNo licence7 mo ago
81

Web research API with OpenAI-compatible chat completions and async tasks

gooseworks-ai/goose-skills1.2k1 repo~3kAutomated safety check: PassMIT2 days ago
82

Integrate and route AI model requests through RouterBase. An agent skill from davepoon/buildwithclaude.

davepoon/buildwithclaude3.6k—~1.1kAutomated safety check: PassMIT2 days ago
83

A skill your agent uses when benchmarking browsing-skills actions, comparing a maintained site skill against a no-skill browser agent, measuring OpenAI API token usage, wall time, API calls…

browsing-skills/browsing-skills117—~596Automated safety check: PassMIT4 mo ago
84

Generate or edit raster images through an OpenAI-compatible image API.

hashgraph-online/awesome-codex-plugins1.3k—~852Automated safety check: PassApache-2.0yesterday
85

Migrate an application to or from Cohere with a provider adapter, parallel embedding index, quality evaluation, canary traffic, and rollback.

jeremylongshore/tons-of-skills-marketplace2.8k—~1.1kAutomated safety check: PassMITyesterday
86

Encapsulate Together AI SDK v2 behind a typed adapter with catalog-resolved models, bounded retries, streaming normalization, usage capture, and OpenAI-compatible migration seams.

jeremylongshore/tons-of-skills-marketplace2.8k—~1kAutomated safety check: PassMITyesterday
87

Use Venice's Alpha POST /responses endpoint - an OpenAI-compatible, stateless Responses API with typed output blocks (reasoning, message, functioncall, websearchcall).

veniceai/skills144—~3.7kAutomated safety check: PassMIT5 days ago
88

Adding provider-backed LLM text generation to an Effect-based Golem agent with effect/unstable/ai and an Effect AI provider.

golemcloud/golem1.5k—~3.3kAutomated safety check: PassUnknownyesterday
89

Check whether a website's robots.txt allows the AI crawlers that decide visibility in ChatGPT Search, Perplexity, Claude, Gemini, and Microsoft Copilot.

davepoon/buildwithclaude3.6k—~1.5kAutomated safety check: PassMIT2 days ago
90

添加和配置第三方 API 中转站供应商到 OpenClaw。当用户需要添加新的 API 供应商、配置中转站、设置自定义模型端点时使用此技能。支持 Anthropic 兼容和 OpenAI 兼容的 API 格式。

aAAaqwq/AGI-Super-Team1051 repo~1.8kAutomated safety check: PassMIT2 days ago
91

Check OpenAI API access and list the models your key can use.

Anil-matcha/awesome-muse-connectors1.3k—~395Automated safety check: PassMIT5 days ago
92

Local TensorZero documentation reference (latest). An agent skill from olorehq/olore.

olorehq/olore104—~1.6kAutomated safety check: PassMITyesterday
93

Call POST /chat/completions on Venice. An agent skill from veniceai/skills.

veniceai/skills144—~5.9kAutomated safety check: PassMIT5 days ago
94

Analyze images and multi-frame sequences using OpenAI GPT vision models

benchflow-ai/skillsbench1.8k—~5kAutomated safety check: PassApache-2.02 mo ago
95

See and understand images when you (the current model) have no native vision.

aiskillstore/marketplace433—~1.1kAutomated safety check: PassNo licenceyesterday
96

Route text-labeling requests across LDA topic modeling, sklearn baselines, pretrained transformer models, and OpenAI-compatible LLM labeling.

Drchronx/ai-agent-research-starter-kit139—~1.1kAutomated safety check: PassUnknown4 mo ago