skillfactor-pipeline/skills/data-scientist/references/ai-skills.md

External AI agent skills — data-scientist

Proven, publicly available AI agent skills mapped to this occupation. Nothing is copied from the sources: every entry is a name, a one-line summary and a link to the upstream skill package. Each section names its source repository, commit, license and retrieval date.

Tiers: core = the skill directly exercises a top-20 market hard skill or an essential ESCO competence of this occupation; adjacent = plausibly useful, secondary. Entries are capped at 10 per source (core first); everything beyond the cap is excluded and logged in the pipeline audit trail, not in this package.

Matched deterministically (ISCO group + title/competence keywords, tiered against market evidence + ESCO essentials) by pipeline/p5_enrich_ai_skills.py on 2026-07-07.

Source: anthropics/skills

• Repository: https://github.com/anthropics/skills (commit 9d2f1ae, retrieved 2026-07-07)
• License: Apache-2.0; the document skills (docx/pdf/pptx/xlsx) are source-available — see the LICENSE.txt in the upstream skill folder

Skill	Tier	What it adds	Upstream
docx	adjacent	Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting …	source
mcp-builder	adjacent	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 …	source
webapp-testing	adjacent	Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.	source
claude-api	adjacent	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 …	source
pdf	adjacent	Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating …	source

Source: obra/superpowers

• Repository: https://github.com/obra/superpowers (commit d884ae0, retrieved 2026-07-07)
• License: MIT (c) Jesse Vincent

Skill	Tier	What it adds	Upstream
finishing-a-development-branch	adjacent	Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup	source
subagent-driven-development	adjacent	Use when executing implementation plans with independent tasks in the current session	source
brainstorming	adjacent	You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.	source
executing-plans	adjacent	Use when you have a written implementation plan to execute in a separate session with review checkpoints	source
receiving-code-review	adjacent	Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation	source
test-driven-development	adjacent	Use when implementing any feature or bugfix, before writing implementation code	source
using-git-worktrees	adjacent	Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback	source
dispatching-parallel-agents	adjacent	Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies	source
requesting-code-review	adjacent	Use when completing tasks, implementing major features, or before merging to verify work meets requirements	source
systematic-debugging	adjacent	Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes	source

Source: wshobson/agents

• Repository: https://github.com/wshobson/agents (commit 6fd3247, retrieved 2026-07-07)
• License: MIT (c) Seth Hobson

Skill	Tier	What it adds	Upstream
rag-implementation	core	Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge …	source
recsys-pipeline-architect	core	Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced X For You algorithm. Use when building any system that picks …	source
auth-implementation-patterns	core	Master authentication and authorization patterns including JWT, OAuth2, session management, and RBAC to build secure, scalable access control systems. Use when implementing auth systems, securing APIs, or debugging security issues.	source
dbt-transformation-patterns	core	Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best …	source
uv-package-manager	core	Master the uv package manager for fast Python dependency management, virtual environments, and modern Python project workflows. Use when setting up Python projects, managing dependencies, or optimizing Python development workflows with uv.	source
code-documentation-docs-architect (agent)	core	Creates comprehensive technical documentation from existing codebases. Analyzes architecture, design patterns, and implementation details to produce long-form technical manuals and ebooks. Use PROACTIVELY for system documentation, …	source
codebase-cleanup-test-automator (agent)	core	Master AI-powered test automation with modern frameworks, self-healing tests, and comprehensive quality engineering. Build scalable testing strategies with advanced CI/CD integration. Use PROACTIVELY for testing automation or quality …	source
embedding-strategies	core	Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.	source
llm-evaluation	core	Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.	source
prompt-engineering-patterns	core	This skill should be used when the user asks to "optimize a prompt", "improve prompt performance", "design a prompt template", "write better prompts", "debug prompt issues", "use chain-of-thought", "structured prompting", "few-shot …	source

Source: google/skills

• Repository: https://github.com/google/skills (commit b15f327, retrieved 2026-07-07)
• License: Apache-2.0

Skill	Tier	What it adds	Upstream
agent-platform-eval-flywheel	core	Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing …	source
bigquery-basics	adjacent	Manages datasets, tables, and jobs in BigQuery. Use when you need to interact with BigQuery, run SQL queries, manage BigQuery resources (datasets, tables, views), or perform basic data ingestion and analysis.	source
datalineage-bigquery-asset-impact-analysis	adjacent	Analyzes the downstream impact (blast radius) when a BigQuery table or view is broken, stale, or modified. Identifies all downstream tables, dashboards, and processes that will be affected. Use when: - Performing a blast radius or impact …	source
bigquery-ai-ml	adjacent	Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, detect outliers, find key drivers, or leverage generative AI …	source
agent-platform-alert-configuration	adjacent	Configures best-practice alerting policies for Google Cloud Vertex AI / Agent Platform agents on Agent Runtime. Use when analyzing, writing, or deploying alerting policies to monitor agent latency, error rates, and quality metrics …	source
alloydb-basics	adjacent	Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB model context protocol (MCP) tools for automated database operations.	source
cloud-sql-basics	adjacent	This file generates or explains Cloud SQL resources. Use this file when the user asks to create a Cloud SQL instance or database for MySQL, PostgreSQL, or SQL Server. Cloud SQL manages third-party MySQL, PostgreSQL, and SQL Server …	source
gke-observability	adjacent	Configures GKE observability, including Cloud Logging, Cloud Monitoring, and managed Prometheus. Use when configuring GKE monitoring, setting up GKE logging, or configuring Prometheus metrics collection. Don't use to configure local …	source
google-analytics-admin-api-basics	adjacent	Manages Google Analytics account and property settings, enables the Analytics Admin API via the Cloud CLI, lists accounts and properties, and manages data streams, custom dimensions, conversion events, and integrations. Use when you need …	source
google-analytics-data-api-basics	adjacent	Manages Google Analytics reporting data, enables the Analytics Data API via the Cloud CLI, and creates reports using the Google Analytics Data API (v1beta). Use when you need to interact with Google Analytics properties, run customized …	source

Source: czlonkowski/n8n-skills

• Repository: https://github.com/czlonkowski/n8n-skills (commit 9ea3aa5, retrieved 2026-07-07)
• License: MIT

Skill	Tier	What it adds	Upstream
n8n-agents	adjacent	Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain.* AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool …	source
n8n-subworkflows	adjacent	Build reusable, composable n8n sub-workflows. Use when extracting shared logic, building anything multi-step or reused across workflows, or any workflow over ~10 nodes — and whenever the user mentions sub-workflows, Execute Workflow, …	source
n8n-validation-expert	adjacent	Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about …	source
n8n-workflow-patterns	adjacent	Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API …	source
n8n-binary-and-data	adjacent	Handle files and binary data in n8n correctly. Use when working with files, images, PDFs, attachments, uploads or downloads, base64, vision/multimodal input, or when an AI agent needs a file as tool input or output — and whenever the user …	source
n8n-code-javascript	adjacent	Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with this.helpers / the $helpers global, working with dates using DateTime, troubleshooting Code node …	source
n8n-code-python	adjacent	Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes. Use this skill when the user specifically …	source
n8n-code-tool	adjacent	Write JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when building a Code Tool attached to an AI Agent, writing code that an LLM will …	source
n8n-multi-instance	adjacent	Use when an n8n-mcp account targets more than one n8n instance — i.e. the n8n_instances tool is available, the user mentions multiple n8n instances or environments (prod vs staging, several teams or clients), a workflow / datatable / …	source
n8n-node-configuration	adjacent	Operation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining required fields, choosing between get_node detail levels, or learning common configuration patterns by node type. …	source

Source: NVIDIA/skills

• Repository: https://github.com/NVIDIA/skills (commit 153b14b, retrieved 2026-07-07)
• License: CC-BY-4.0 (skills/docs), Apache-2.0 (code)

Skill	Tier	What it adds	Upstream
nemo-rl-auto-research	core	Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching …	source
vss-generate-video-report	core	Use this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics. Not for standalone video summarization, real-time alerts or ad-hoc Q&A.	source
tilegym-monkey-patch-kernels-to-transformers	core	Integrate TileGym kernels into Hugging Face transformers models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating …	source
earth2studio-discover	core	Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.	source
earth2studio-install	core	Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment. Do NOT use for writing inference code, choosing models, or PhysicsNeMo questions.	source
nemo-mbridge-multi-node-slurm	core	Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container setup, NCCL timeouts, OOM sizing for MoE models, and interactive …	source
tao-finetune-cosmos-reason	core	Cosmos3-Nano video QA supervised fine-tuning with FSDP parallelism. Use when training or evaluating video question-answering models, fine-tuning Cosmos3-Nano or compatible Cosmos Reason models with SFT/LoRA, or working with Cosmos-RL. …	source
tao-run-automl-deft-pipeline	core	Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), Phase 3 AutoML refinement on the DEFT-augmented dataset. Use when the user asks to …	source
nemo-rl-brev-etiquette	adjacent	Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. Use when running nemo-rl-auto-research campaigns, …	source
nemo-rl-session-memory	adjacent	Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written …	source

Source: phuryn/pm-skills

• Repository: https://github.com/phuryn/pm-skills (commit 18468a9, retrieved 2026-07-07)
• License: MIT

Skill	Tier	What it adds	Upstream
ab-test-analysis	core	Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split …	source
cohort-analysis	adjacent	Perform cohort analysis on user engagement data — retention curves, feature adoption trends, and segment-level insights. Use when analyzing user retention by cohort, studying feature adoption over time, investigating churn patterns, or …	source
sql-queries	adjacent	Generate SQL queries from natural language descriptions. Supports BigQuery, PostgreSQL, MySQL, and other dialects. Reads database schemas from uploaded diagrams or documentation. Use when writing SQL, building data reports, exploring …	source
dummy-dataset	adjacent	Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and …	source
lean-canvas	adjacent	Generate a Lean Canvas with problem, solution, metrics, cost structure, UVP, unfair advantage, channels, segments, and revenue. Use when exploring a lean startup canvas, testing a business hypothesis, or modeling a new venture.	source
metrics-dashboard	adjacent	Define and design a product metrics dashboard with key metrics, data sources, visualization types, and alert thresholds. Use when creating a metrics dashboard, defining KPIs, setting up product analytics, or building a data monitoring plan.	source
gtm-strategy	adjacent	Create a go-to-market strategy covering marketing channels, messaging, success metrics, and launch timeline. Use when planning a product launch, creating a GTM plan from scratch, or defining a launch strategy for a new market.	source
north-star-metric	adjacent	Define a North Star Metric and 3-5 supporting input metrics that form a metrics constellation. Classify the business game (Attention, Transaction, Productivity) and validate against 7 criteria for an effective North Star. Use when choosing …	source
product-strategy	adjacent	Create a comprehensive product strategy using the 9-section Product Strategy Canvas — vision, segments, costs, value propositions, trade-offs, metrics, growth, capabilities, and defensibility. Use when building a product strategy, creating …	source

Source: veniceai/skills

• Repository: https://github.com/veniceai/skills (commit de089fa, retrieved 2026-07-07)
• License: MIT

Skill	Tier	What it adds	Upstream
venice-api-keys	adjacent	Manage Venice API keys. Covers GET/POST/PATCH/DELETE /api_keys, GET /api_keys/{id}, GET /api_keys/rate_limits, GET /api_keys/rate_limits/log, the two-step /api_keys/generate_web3_key wallet flow, INFERENCE vs ADMIN key types, and per-key …	source
venice-characters	adjacent	Discover and use Venice public characters (persona-driven system prompts with a bound model). Covers GET /characters (search/filter/sort), /characters/{slug}, /characters/{slug}/reviews, the Character schema, and how to apply a character …	source
venice-errors	adjacent	Handle Venice API errors correctly. Covers the StandardError / DetailedError / ContentViolationError / X402InferencePaymentRequired body shapes, every meaningful status code (400, 401, 402, 403, 415, 422, 429, 500, 503, 504), the 402 …	source
venice-api-overview	adjacent	High-level map of the Venice.ai API - base URL, authentication modes, endpoint categories, response headers, pricing model, error shape, and versioning. Load this first when starting any Venice integration.	source
venice-auth	adjacent	Authenticate to the Venice API with a Bearer API key or with an x402 / SIWE wallet. Covers header formats, the SIWE message fields, TTL and nonce rules, the venice-x402-client SDK, and how to choose between the two modes.	source
venice-embeddings	adjacent	Call POST /embeddings on Venice. Covers request shape (input, model, encoding_format, dimensions, user), OpenAI compatibility, response compression (gzip/br), and practical usage for retrieval, clustering, and RAG.	source
venice-image-edit	adjacent	Transform existing images with Venice. Covers POST /image/edit (prompt-driven single-image edit), /image/multi-edit (compose 1-3 images), /image/upscale (2-4x upscale + enhance), and /image/background-remove. Accepts base64, file upload, …	source
venice-image-generate	adjacent	Generate images with Venice. Covers POST /image/generate (Venice-native), POST /images/generations (OpenAI-compatible), GET /image/styles (style presets), request fields (prompt, dimensions, cfg_scale, seed, variants, style_preset, …	source
venice-responses	adjacent	Use Venice's Alpha POST /responses endpoint - an OpenAI-compatible Responses API with typed output blocks (reasoning, message, function_call, web_search_call). Covers request shape, streaming, differences from /chat/completions, supported …	source