For data scientists

Catches unusual performance changes across your accounts — CPC spikes, CVR drops, spend surges, impression collapses, CTR shifts — and flags them with context about what likely changed.

irinabuht12-oss/marketing-skills

Projects your ROAS for the next 30, 60, and 90 days based on current performance trends, seasonality patterns from your historical data, and planned budget or campaign changes.

irinabuht12-oss/marketing-skills

Conversion funnel analysis with drop-off investigation. An agent skill from nimrodfisher/data-analytics-skills.

nimrodfisher/data-analytics-skills

Run TAO Data Services TMM unique-neighbor matching mining from embedding parquet files for object detection workflows.

NVIDIA/skills

Generate atmospheric sound-design / SFX (NOT speech, NOT the front-of-blog BGM) via OpenRouter using Google Lyria 3 Pro.

QinghongLin/data2story-skill

Initialize or hydrate the agent's memory system and verify configuration.

Qredence/agentic-fleet

ComfyUI node output types - NodeOutput, UI outputs, PreviewImage, PreviewMask, SavedImages, PreviewAudio, PreviewText, PreviewVideo.

jtydhr88/comfyui-custom-node-skills

استخدمه عندما يطلب المستخدم إنشاء أو تهيئة أو تعديل دفاتر Jupyter (.ipynb) للتجارب أو الاستكشافات أو الدروس التعليمية؛ فضّل القوالب المضمّنة وقم بتشغيل سكربت المساعدة newnotebook.py لتوليد دفتر بدءٍ…

microsoft/ai-agents-for-beginners

OpenCode places cachePoint on Bedrock messages containing DocumentBlocks, which produces a "nothing available to cache" error.

OnlyTerp/prompt-cache-skills

Search and download images via Google Custom Search API with LLM-powered selection.

glebis/claude-skills

Generate output schemas (datasetschema.json, outputschema.json, keyvaluestoreschema.json) for an Apify Actor by analyzing its source code.

sickn33/agentic-awesome-skills

Spectral vector search using graph Laplacian eigenstructure.

sickn33/agentic-awesome-skills

Web and App implementation guide for Dashboard Design. An agent skill from sickn33/agentic-awesome-skills.

sickn33/agentic-awesome-skills

Event register: type, date and time, venue, organizer, audience, budget against actual cost, RSVP and attendance counts and feedback score.

sickn33/agentic-awesome-skills

Build an automated SLA breach alerting system for vulnerability remediation, including a database schema for SLA tracking, breach detection logic, notification dispatch, a scheduled check runner…

mukul975/Anthropic-Cybersecurity-Skills

When a ticket must go to a human before any reply is sent, and how the first reply should read.

Kiln-AI/Kiln

Fetch, organize, and analyze LangSmith traces for debugging and evaluation.

soba-labs/langchain-agent-skills

Master API Platform State Providers and Processors (v5, 4.4, 4.3) (ProviderInterface/ProcessorInterface) to decouple data retrieval and persistence from entities

dev-toolings/superpowers-symfony

Use as stage 2 of the Butterbase journey, after journey-idea has written 01-idea.md.

butterbase-ai/butterbase-skills

Convert robot trajectory datasets between formats — currently agibot v1 → LeRobot v2.1 (parquet + HEVC/PNG-encoded MP4).

AgibotTech/genie_sim

Search the Genie Sim asset library by natural-language keyword via the generator's searchassets MCP tool (RAG over ASSETSINDEX), and look up asset interaction metadata via getinteractions.

AgibotTech/genie_sim

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/mimeo

When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).

tjboudreaux/cc-thinking-skills

A skill your agent uses for Plotly Dash app layouts, callbacks, pages, assets, configuration, clientside callbacks, Jupyter display, CSP, and app-level debugging.

VectorSpaceLab/AREX-Skill

Run the same scrape or task across many accounts at once - each in its own browser profile with its own fingerprint, cookies and exit IP - and read data from sites that need a session or that answer…

antibrow/anti-detect-browser-skills

Audit every surface that renders a dataset's indicators — charts, map tabs, MDim views, explorer views, narrative charts, and article references — for views whose pinned entity selection has no data…

owid/etl

Help users index MUD Store events, process on-chain table mutations, store in PostgreSQL or EF Core, normalise schemas, run continuous sync.

Nethereum/Nethereum

Build and run the public 64x64 x 128-token tiled circular tensor matmul example on the encrypted Edge Verilator simulator.

exeex/edge-cores

A skill your agent uses when needing Google Gems 프롬프트 생성기. An agent skill from treylom/prompt-engineering-skills.

treylom/prompt-engineering-skills

A skill your agent uses when the user asks to "check if our surfaces have drifted from the canon", "watch for competitor repositioning", or "define when we should reposition"; produces a drift…

aaron-he-zhu/aaron-marketing-skills

Add or repair Alembic migrations for specx SQLAlchemy services.

maksimzayats/specx

Search ALL installed skills (including ones not shown in AVAILABLE SKILLS) by keyword.

clacky-ai/openclacky

Only reach for external web search when the local corpus comes back empty or clearly insufficient.

lyonzin/knowledge-rag

Production-ready microscopy image analysis and quantitative imaging data skill for colony morphometry, cell counting, fluorescence quantification, and statistical analysis of imaging-derived…

wu-yc/LabClaw

A skill your agent uses when the user asks "why is this B200/Blackwell kernel slow, what should I optimize first, should I fuse or move to Tensor Cores/TMA".

mirage-project/mirage

A skill your agent uses when the user needs to choose the tile, dtype, ctagroup::1/2, SMEM operand layout, or TMEM accumulator mapping for a tcgen05 MMA on B200/Blackwell, or to implement an…

mirage-project/mirage

A skill your agent uses when the user prompts "write about for".

romeerez/orchid-orm

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

affaan-m/ECC

Review prediction-market, basket, oracle, and trading-agent workflows for compliance, safety, data-quality, privacy, and execution risk.

affaan-m/ECC

Eval-driven development (EDD) framework for AI coding sessions — define capability and regression evals before coding, grade with code-based, model-based, rule, or human graders, and track pass@k…

affaan-m/ECC

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

affaan-m/ECC

Review an AlbumentationsX transform for correctness, public API coherence, performance, documentation, and test coverage.

albumentations-team/AlbumentationsX

Trace relationships between semantic models and downstream reports across Fabric workspaces.

data-goblin/power-bi-agentic-development

Measure local AI task latency, token usage, errors and verified outcomes using Pudu AI hardware evidence and installed Ollama models.

davila7/claude-code-templates

Best practices for object detection tasks. An agent skill from aiming-lab/AutoResearchClaw.

aiming-lab/AutoResearchClaw

Optimize data loading pipeline to prevent GPU starvation. An agent skill from aiming-lab/AutoResearchClaw.

aiming-lab/AutoResearchClaw

Multi-GPU and distributed training patterns with PyTorch DDP.

aiming-lab/AutoResearchClaw

Use FP16/BF16 mixed precision to accelerate training and reduce memory.

aiming-lab/AutoResearchClaw