数据与 AI类 Agent Skills（共 17,456 条）
全库共 17,456 条 Skill 属于“数据与 AI”，分类由名称、路径与描述关键词在构建时推导。下面是其中 Star 最高的 100 条，已标注许可证与安全规则命中情况。在目录中看全部 →
- 1
claude-api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-l…
- 2
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (…
- 3
Atelier Zero — Image Generation Prompt Pack
This pack is consumed by the `open-design-landing` skill. Every page-level image is rendered with `gpt-image-fal` (preferred) or `gpt-image-azure`.
- 4
github-dashboard
Create a single-screen GitHub repository analytics dashboard in the FlowAI / Soft Paper Workspace visual style: warm off-white canvas, white rounded panels, a fixed left sidebar, compact KPI cards, pastel pills, dense tables, and low-contr…
- 5
image-poster
Produce **one** finished image asset per turn unless the user asks for variations. Image generation rewards a tight, structured prompt — your job is to assemble that prompt from the user's brief, then dispatch.
- 6
dashboard
Produce a single-screen admin / analytics dashboard.
- 7
social-media-dashboard
Produce a single-screen, creator-facing social media analytics dashboard.
- 8
create-video-storyboard
Use this plugin when the user wants a video concept, storyboard, shot list, prompt pack, or render-ready motion brief for a product, campaign, or explainer.
- 9
dashboard
Admin / analytics dashboard in a single HTML file. Fixed left sidebar, top bar with user/search, main grid of KPI cards and one or two charts. Use when the brief asks for a "dashboard", "admin", "analytics", or "control panel" screen.
- 10
enhance-prompt
Improve prompts with design specs and UI/UX vocabulary. Useful for design-to-code workflows and clarifying requests for visual output.
- 11
fal-kling-o3
Generate images and videos with Kling O3 — Kling's most powerful model family — via fal.ai.
- 12
fs-notebook-tabs
A computer-science capstone: an on-device ML keyboard that predicts next words privately — problem, method, evaluation, and defense answers. Built as a decision-grade coursework defense deck for professor, defense committee.
- 13
full-output-enforcement
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
- 14
github-dashboard
GitHub repository analytics dashboard — stars, forks, contributors, issues, pull requests, recent activity, and top contributors. Use when the brief asks for a GitHub repo dashboard, open-source growth report, repository health page, or Gi…
- 15
hand-drawn-diagrams
Generate hand-drawn Excalidraw diagrams from a prompt — animated SVG, hosted edit link, and PNG export. Works with Claude Code, Codex, Gemini CLI, and any agent supporting standard skill paths.
- 16
html-ppt-hermes-cyber-terminal
Open Design + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
- 17
html-ppt-hermes-cyber-terminal
Open Design + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
- 18
html-ppt-presenter-mode
Open Design live demo: from a one-line prompt to runnable design in a single session — the flow, live. Built as a decision-grade AI literacy deck for developers, prospects, community.
- 19
html-ppt-presenter-mode
Open Design live demo: from a one-line prompt to runnable design in a single session — the flow, live. Built as a decision-grade AI literacy deck for developers, prospects, community.
- 20
html-ppt-zhangzara-long-table
Open Design's unit-economics and BYOK cost model: the assumptions, the sensitivity, and why it scales. Built as a decision-grade data & finance deck for CFO, investors.
- 21
ppt-keynote
An operating-model redesign for a scaling logistics firm — the diagnosis, the target model, and the transition roadmap. Built as a decision-grade consulting deck for client sponsor, ops leaders.
- 22
social-media-dashboard
Creator-facing social media analytics dashboard in a single HTML file. A platform switcher (X / LinkedIn / YouTube / Instagram), a row of KPI cards (followers, engagement rate, likes, reposts), a follower-growth chart, a "top post this wee…
- 23
social-media-matrix-tracker-template
社媒矩阵数据追踪面板模板（Social Media Matrix Tracker）。 Use when users ask for a cinematic, data-dense social media analytics dashboard with multi-platform metrics, interactive charts, hover insights, range compare, and dark/light theme switching in a…
- 24
social-media-matrix-tracker-template
社媒矩阵数据追踪面板模板（Social Media Matrix Tracker）。 Use when users ask for a cinematic, data-dense social media analytics dashboard with multi-platform metrics, interactive charts, hover insights, range compare, and dark/light theme switching in a…
- 25
ai-ml-api-automation
Automate AI ML API tasks via Rube MCP (Composio). Always search tools first for current schemas.
- 26
Customer.io Automation
Automate customer engagement workflows including broadcast triggers, message analytics, segment management, and newsletter tracking through Customer.io via Composio
- 27
Gong Automation
Automate Gong conversation intelligence -- retrieve call recordings, transcripts, detailed analytics, speaker stats, and workspace data -- using natural language through the Composio MCP integration.
- 28
google-search-console-automation
Automate Google Search Console tasks via Rube MCP (Composio): query search analytics, list sites, inspect URLs, submit sitemaps, monitor search performance. Always search tools first for current schemas.
- 29
googleads-automation
Automate Google Ads analytics tasks via Rube MCP (Composio): list Google Ads links, run GA4 reports, check compatibility, list properties and accounts. Always search tools first for current schemas.
- 30
GroqCloud Automation
Automate AI inference, chat completions, audio translation, and TTS voice management through GroqCloud's high-performance API via Composio
- 31
Instantly Automation
Automate Instantly cold email outreach -- manage campaigns, sending accounts, lead lists, bulk lead imports, and campaign analytics -- using natural language through the Composio MCP integration.
- 32
MailerLite Automation
Automate email marketing workflows including subscriber management, campaign analytics, group segmentation, and account monitoring through MailerLite via Composio
- 33
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (…
- 34
Microsoft Clarity Automation
Automate user behavior analytics with Microsoft Clarity -- export heatmap data, session metrics, and engagement analytics segmented by browser, device, country, source, and more through the Composio Microsoft Clarity integration.
- 35
microsoft_clarity-automation
Automate Microsoft Clarity tasks via Rube MCP (Composio): session recordings, heatmaps, and user behavior analytics. Always search tools first for current schemas.
- 36
Mistral AI Automation
Automate Mistral AI operations -- manage files and libraries, upload documents for fine-tuning, batch processing, and OCR, track fine-tuning jobs, and build RAG pipelines via the Composio MCP integration.
- 37
mistral_ai-automation
Automate Mistral AI tasks via Rube MCP (Composio): completions, embeddings, fine-tuning, and model management. Always search tools first for current schemas.
- 38
Replicate Automation
Automate Replicate AI model operations -- run predictions, upload files, inspect model schemas, list versions, and manage prediction history via the Composio MCP integration.
- 39
rosette-text-analytics-automation
Automate Rosette Text Analytics tasks via Rube MCP (Composio). Always search tools first for current schemas.
- 40
simple-analytics-automation
Automate Simple Analytics tasks via Rube MCP (Composio). Always search tools first for current schemas.
- 41
survey_monkey-automation
Automate SurveyMonkey tasks via Rube MCP (Composio): surveys, responses, collectors, and survey analytics. Always search tools first for current schemas.
- 42
bmad-advanced-elicitation
Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.
- 43
bmad-deep-recon
Decision-grade research, three ways: draft a deep-research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), process a finished research report — file it, distill a succinct cited summary with metadata th…
- 44
adhx
Fetch any X/Twitter post as clean LLM-friendly JSON. Converts x.com, twitter.com, or adhx.com links into structured data with full article content, author info, and engagement metrics. No scraping or browser required.
- 45
advanced-evaluation
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipeline…
- 46
advanced-evaluation
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipeline…
- 47
ai-dev-jobs-mcp
Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP
- 48
ai-dev-jobs-mcp
Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP
- 49
ai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.
- 50
ai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.
- 51
ai-ml
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
- 52
ai-ml
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
- 53
ai-seo
Optimize content for AI search and LLM citations across AI Overviews, ChatGPT, Perplexity, Claude, Gemini, and similar systems. Use when improving AI visibility, answer engine optimization, or citation readiness.
- 54
ai-seo
Optimize content for AI search and LLM citations across AI Overviews, ChatGPT, Perplexity, Claude, Gemini, and similar systems. Use when improving AI visibility, answer engine optimization, or citation readiness.
- 55
analytics-product
Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.
- 56
analytics-product
Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.
- 57
analytics-product
Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.
- 58
analytics-product
Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.
- 59
analytics-product
Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.
- 60
andrej-karpathy
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
- 61
andrej-karpathy
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
- 62
apify-actor-development
Important: Before you begin, fill in the generatedBy property in the meta section of .actor/actor.json. Replace it with the tool and model you're currently using, such as \"Claude Code with Claude Sonnet 4.5\". This helps Apify monitor and…
- 63
apify-actor-development
Important: Before you begin, fill in the generatedBy property in the meta section of .actor/actor.json. Replace it with the tool and model you're currently using, such as \"Claude Code with Claude Sonnet 4.5\". This helps Apify monitor and…
- 64
apify-content-analytics
Track engagement metrics, measure campaign ROI, and analyze content performance across Instagram, Facebook, YouTube, and TikTok.
- 65
apify-content-analytics
Track engagement metrics, measure campaign ROI, and analyze content performance across Instagram, Facebook, YouTube, and TikTok.
- 66
arrowspace
Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.
- 67
arrowspace
Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.
- 68
azure-cosmos-java
Azure Cosmos DB SDK for Java. NoSQL database operations with global distribution, multi-model support, and reactive patterns.
- 69
azure-cosmos-java
Azure Cosmos DB SDK for Java. NoSQL database operations with global distribution, multi-model support, and reactive patterns.
- 70
azure-functions
Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns. Covers .NET, Python, and Node.js programming models.
- 71
azure-mgmt-weightsandbiases-dotnet
Azure Weights & Biases SDK for .NET. ML experiment tracking and model management via Azure Marketplace. Use for creating W&B instances, managing SSO, marketplace integration, and ML observability.
- 72
azure-mgmt-weightsandbiases-dotnet
Azure Weights & Biases SDK for .NET. ML experiment tracking and model management via Azure Marketplace. Use for creating W&B instances, managing SSO, marketplace integration, and ML observability.
- 73
azure-monitor-query-java
Azure Monitor Query SDK for Java. Execute Kusto queries against Log Analytics workspaces and query metrics from Azure resources.
- 74
azure-monitor-query-java
Azure Monitor Query SDK for Java. Execute Kusto queries against Log Analytics workspaces and query metrics from Azure resources.
- 75
azure-storage-file-datalake-py
Azure Data Lake Storage Gen2 SDK for Python. Use for hierarchical file systems, big data analytics, and file/directory operations.
- 76
azure-storage-file-datalake-py
Azure Data Lake Storage Gen2 SDK for Python. Use for hierarchical file systems, big data analytics, and file/directory operations.
- 77
bdi-mental-states
This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belief-desire-intention models", "transform RDF to beliefs", "build cognitive agent", or mentions BDI ontology, mental state…
- 78
bdi-mental-states
This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belief-desire-intention models", "transform RDF to beliefs", "build cognitive agent", or mentions BDI ontology, mental state…
- 79
bdistill-behavioral-xray
X-ray any AI model's behavioral patterns — refusal boundaries, hallucination tendencies, reasoning style, formatting defaults. No API key needed.
- 80
bdistill-behavioral-xray
X-ray any AI model's behavioral patterns — refusal boundaries, hallucination tendencies, reasoning style, formatting defaults. No API key needed.
- 81
brave-man
Runs a structured clarifying interview for new project requests before building. Instead of writing code, it outputs a fully specified prompt.md for a fresh agent session to execute, preventing expensive mistakes.
- 82
brave-man
Runs a structured clarifying interview for new project requests before building. Instead of writing code, it outputs a fully specified prompt.md for a fresh agent session to execute, preventing expensive mistakes.
- 83
business-analyst
Master modern business analysis with AI-powered analytics, real-time dashboards, and data-driven insights. Build comprehensive KPI frameworks, predictive models, and strategic recommendations.
- 84
business-analyst
Master modern business analysis with AI-powered analytics, real-time dashboards, and data-driven insights. Build comprehensive KPI frameworks, predictive models, and strategic recommendations.
- 85
business-analyst
Master modern business analysis with AI-powered analytics, real-time dashboards, and data-driven insights. Build comprehensive KPI frameworks, predictive models, and strategic recommendations.
- 86
business-analyst
Master modern business analysis with AI-powered analytics, real-time dashboards, and data-driven insights. Build comprehensive KPI frameworks, predictive models, and strategic recommendations.
- 87
clarity-gate
**Purpose:** Pre-ingestion verification system that enforces epistemic quality before documents enter RAG knowledge bases. Produces Clarity-Gated Documents (CGD) compliant with the Clarity Gate Format Specification v2.1.
- 88
clarity-gate
**Purpose:** Pre-ingestion verification system that enforces epistemic quality before documents enter RAG knowledge bases. Produces Clarity-Gated Documents (CGD) compliant with the Clarity Gate Format Specification v2.1.
- 89
clean-code-guard
Review generated or changed production code with Clean Code, SOLID, DRY, KISS, YAGNI, and LLM-specific failure-mode checks.
- 90
clean-code-guard
Review generated or changed production code with Clean Code, SOLID, DRY, KISS, YAGNI, and LLM-specific failure-mode checks.
- 91
context-fundamentals
Context is the complete state available to a language model at inference time. It includes everything the model can attend to when generating responses: system instructions, tool definitions, retrieved documents, message history, and tool…
- 92
context-fundamentals
Context is the complete state available to a language model at inference time. It includes everything the model can attend to when generating responses: system instructions, tool definitions, retrieved documents, message history, and tool…
- 93
context-manager
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems.
- 94
context-manager
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems.
- 95
dashboard-design
Web and App implementation guide for Dashboard Design. Trigger when user wants analytics-focused layouts, data visualization, and modular overview screens.
- 96
dashboard-design
Web and App implementation guide for Dashboard Design. Trigger when user wants analytics-focused layouts, data visualization, and modular overview screens.
- 97
data-quality-frameworks
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
- 98
data-scientist
Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence.
- 99
data-scientist
Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence.
- 100
database-architect
Expert database architect specializing in data layer design from scratch, technology selection, schema modeling, and scalable database architectures.