AI Agent Skills — what each costs to run

Estimated input cost per 1,000 loads of SKILL.md only (characters ÷ 4). Bundled files, output tokens and execution are excluded.

244 curated skills · Verified 2026-10-28

30 skills

  • supabase-postgres-best-practices
    data

    supabase/agent-skills

    Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing or changing anything that lives in a Postgres database: creating or altering tables and columns (including choosing column types),

    SKILL.md tokens
    807
    Sonnet 5 / 1k loads
    $1.61
    Network access
  • trl-training
    data

    huggingface/skills

    Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging training code with the TRL Python API or the trl CLI.

    SKILL.md tokens
    1,077
    Sonnet 5 / 1k loads
    $2.15
    Network access
  • snowflake-semanticview
    data

    github/awesome-copilot

    Create, alter, and validate Snowflake semantic views using Snowflake CLI (snow). Use when asked to build or troubleshoot semantic views/semantic layer definitions with CREATE/ALTER SEMANTIC VIEW, to validate semantic-view DDL against Snowfl

    SKILL.md tokens
    1,102
    Sonnet 5 / 1k loads
    $2.20
    Network access
    Shell commands
  • analyze
    data

    anthropics/knowledge-work-plugins

    Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.

    SKILL.md tokens
    1,108
    Sonnet 5 / 1k loads
    $2.22
    No flags detected
  • huggingface-datasets
    data

    huggingface/skills

    Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.

    SKILL.md tokens
    1,167
    Sonnet 5 / 1k loads
    $2.33
    Network access
    Shell commands
  • write-query
    data

    anthropics/knowledge-work-plugins

    Write optimized SQL for your dialect with best practices. Use when translating a natural-language data need into SQL, building a multi-CTE query with joins and aggregations, optimizing a query against a large partitioned table, or getting d

    SKILL.md tokens
    1,188
    Sonnet 5 / 1k loads
    $2.38
    No flags detected
  • bigquery-pipeline-audit
    data

    github/awesome-copilot

    Audits Python + BigQuery pipelines for cost safety, idempotency, and production readiness. Returns a structured report with exact patch locations.

    SKILL.md tokens
    1,250
    Sonnet 5 / 1k loads
    $2.50
    No flags detected
  • huggingface-trackio
    data

    huggingface/skills

    Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualizatio

    SKILL.md tokens
    1,271
    Sonnet 5 / 1k loads
    $2.54
    Shell commands
  • power-bi-dax-optimization
    data

    github/awesome-copilot

    Comprehensive Power BI DAX formula optimization prompt for improving performance, readability, and maintainability of DAX calculations.

    SKILL.md tokens
    1,389
    Sonnet 5 / 1k loads
    $2.78
    No flags detected
  • powerbi-modeling
    data

    github/awesome-copilot

    Power BI semantic modeling assistant for building optimized data models. Use when working with Power BI semantic models, creating measures, designing star schemas, configuring relationships, implementing RLS, or optimizing model performance

    SKILL.md tokens
    1,494
    Sonnet 5 / 1k loads
    $2.99
    No flags detected
  • fabric-lakehouse
    data

    github/awesome-copilot

    Use this skill to get context about Fabric Lakehouse and its features for software systems and AI-powered functions. It offers descriptions of Lakehouse data components, organization with schemas and shortcuts, access control, and code exam

    SKILL.md tokens
    1,524
    Sonnet 5 / 1k loads
    $3.05
    No flags detected
  • datanalysis-credit-risk
    data

    github/awesome-copilot

    Credit risk data cleaning and variable screening pipeline for pre-loan modeling. Use when working with raw credit data that needs quality assessment, missing value analysis, or variable selection before modeling. it covers data loading and

    SKILL.md tokens
    1,545
    Sonnet 5 / 1k loads
    $3.09
    Runs scripts
    Shell commands
  • huggingface-community-evals
    data

    huggingface/skills

    Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs,

    SKILL.md tokens
    1,638
    Sonnet 5 / 1k loads
    $3.28
    Runs scripts
    Shell commands
  • xlsx
    data

    anthropics/skills

    Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas,

    SKILL.md tokens
    2,135
    Sonnet 5 / 1k loads
    $4.27
    Runs scripts
    Shell commands
  • sql-code-review
    data

    github/awesome-copilot

    Universal SQL code review assistant that performs comprehensive security, maintainability, and code quality analysis across all SQL databases (MySQL, PostgreSQL, SQL Server, Oracle). Focuses on SQL injection prevention, access control, code

    SKILL.md tokens
    2,218
    Sonnet 5 / 1k loads
    $4.44
    No flags detected
  • sql-optimization
    data

    github/awesome-copilot

    Universal SQL performance optimization assistant for comprehensive query tuning, indexing strategies, and database performance analysis across all SQL databases (MySQL, PostgreSQL, SQL Server, Oracle). Provides execution plan analysis, pagi

    SKILL.md tokens
    2,295
    Sonnet 5 / 1k loads
    $4.59
    No flags detected
  • huggingface-papers
    data

    huggingface/skills

    Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an a

    SKILL.md tokens
    2,337
    Sonnet 5 / 1k loads
    $4.67
    Network access
    Shell commands
  • pinecone-rag
    data

    github/awesome-copilot

    Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend. ALWAYS USE THIS SKILL when the user mentions Pinecone, wants to index documents for semantic search, build a retrieval-augmented gener

    SKILL.md tokens
    2,404
    Sonnet 5 / 1k loads
    $4.81
    No flags detected
  • statistical-analysis
    data

    anthropics/knowledge-work-plugins

    Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing. Use when analyzing distributions, testing for significance, detecting anomalies, computing correlations, or interpreting stati

    SKILL.md tokens
    2,608
    Sonnet 5 / 1k loads
    $5.22
    No flags detected
  • data-visualization
    data

    anthropics/knowledge-work-plugins

    Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility an

    SKILL.md tokens
    2,762
    Sonnet 5 / 1k loads
    $5.52
    No flags detected
  • sql-queries
    data

    anthropics/knowledge-work-plugins

    Write correct, performant SQL across all major data warehouse dialects (Snowflake, BigQuery, Databricks, PostgreSQL, etc.). Use when writing queries, optimizing slow SQL, translating between dialects, or building complex analytical queries

    SKILL.md tokens
    2,781
    Sonnet 5 / 1k loads
    $5.56
    No flags detected
  • postgresql-optimization
    data

    github/awesome-copilot

    PostgreSQL-specific development assistant focusing on unique PostgreSQL features, advanced data types, and PostgreSQL-exclusive capabilities. Covers JSONB operations, array types, custom types, range/geometric types, full-text search, windo

    SKILL.md tokens
    2,832
    Sonnet 5 / 1k loads
    $5.66
    No flags detected
  • explore-data
    data

    anthropics/knowledge-work-plugins

    Profile and explore a dataset to understand its shape, quality, and patterns. Use when encountering a new table or file, checking null rates and column distributions, spotting data quality issues like duplicates or suspicious values, or dec

    SKILL.md tokens
    2,879
    Sonnet 5 / 1k loads
    $5.76
    No flags detected
  • supabase
    data

    supabase/agent-skills

    Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, Svelte

    SKILL.md tokens
    3,567
    Sonnet 5 / 1k loads
    $7.13
    Network access
    Shell commands
  • validate-data
    data

    anthropics/knowledge-work-plugins

    QA an analysis before sharing -- methodology, accuracy, and bias checks. Use when reviewing an analysis before a stakeholder presentation, spot-checking calculations and aggregation logic, verifying a SQL query's results look right, or asse

    SKILL.md tokens
    3,728
    Sonnet 5 / 1k loads
    $7.46
    No flags detected
  • build-dashboard
    data

    anthropics/knowledge-work-plugins

    Build an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a shareable self-contained report, building a team monitoring snapshot, or needing mult

    SKILL.md tokens
    6,356
    Sonnet 5 / 1k loads
    $12.71
    Network access
  • huggingface-llm-trainer
    data

    huggingface/skills

    Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deploy

    SKILL.md tokens
    7,165
    Sonnet 5 / 1k loads
    $14.33
    Runs scripts
    Network access
    Shell commands
  • huggingface-vision-trainer
    data

    huggingface/skills

    Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using

    SKILL.md tokens
    7,498
    Sonnet 5 / 1k loads
    $15.00
    Runs scripts
    Network access
    Shell commands
  • hf-cli
    data

    huggingface/skills

    Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Bu

    SKILL.md tokens
    8,459
    Sonnet 5 / 1k loads
    $16.92
    Network access
    Shell commands
  • cosmosdb-datamodeling
    data

    github/awesome-copilot

    Step-by-step guide for capturing key application requirements for NoSQL use-case and produce Azure Cosmos DB Data NoSQL Model design using best practices and common patterns, artifacts_produced: "cosmosdb_requirements.md" file and "cosmosdb

    SKILL.md tokens
    11,862
    Sonnet 5 / 1k loads
    $23.72
    Network access