Skip to content

Instruction-only agent skills

2,929 instruction-only agent skills, out of 3,419 agent skills listed. Popular ones include Rea analysis optimization, Rea changelog update and Rea ci tests audit. These skills contain instructions and reference files but no scripts, so they run no code of their own. Each one lists the tools it asks for and how to install it in Claude Code, Codex, Cursor and other agents.
  1. Lets your agent write BigQuery SQL for forecasting, anomaly detection and GenAI functions

    • Open source
    • 24.4K GitHub stars
    • Databases
  2. Lets your agent manage BigQuery datasets, tables and jobs and run SQL queries

    • Open source
    • 24.4K GitHub stars
    • Databases
  3. Guides agents to write Python data code on BigQuery DataFrames instead of local pandas

    • Open source
    • 24.4K GitHub stars
    • Databases
  4. Guides agents in pulling BigQuery job, slot and billing telemetry for diagnosis and audits

    • Open source
    • 24.4K GitHub stars
    • Databases
  5. Guides an agent through BigQuery cost, storage layout, and SQL query optimization

    • Open source
    • 24.4K GitHub stars
    • Databases
  6. Guides an agent through root-cause analysis of slow, failing or costly BigQuery workloads

    • Open source
    • 24.4K GitHub stars
    • Databases
  7. Guides an agent to build, deploy and debug BigQuery UDFs and Remote Functions

    • Open source
    • 24.4K GitHub stars
    • Databases
  8. Guides an agent through Bigtable provisioning, row key schema design, and querying

    • Open source
    • 24.4K GitHub stars
    • Databases
  9. Walks an agent through Cloud Build basics: APIs, build history, and running triggers

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  10. Guides an agent through configuring single-project Google Cloud Logging buckets, views

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  11. Builds and publishes a private Gradio Space that runs inference with a LoRA

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  12. Reads Hugging Face and arXiv paper pages and metadata so the agent can analyze AI papers

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  13. Guides an agent to build, deploy and debug apps on Hugging Face Spaces

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  14. Lets an agent log, alert on and query ML training experiment metrics with Trackio

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  15. Guides agents writing Gradio code for ZeroGPU Spaces, covering @spaces.GPU limits

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  16. Run Hugging Face machine learning models directly in JavaScript and TypeScript apps

    • Open source
    • 11.4K GitHub stars
    • Design and media
  17. Guides an agent through post-training LLMs with TRL: SFT, DPO, GRPO, KTO and reward models

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  18. Runs a Trailmark structural summary to report languages, entry points and dependencies

    • Open source
    • 8.2K GitHub stars
    • Developer tools
  19. Expands one known vulnerability into ranked graph-based variant candidates for review

    • Open source
    • 8.2K GitHub stars
    • Security
  20. Generates crypto test vectors that target mutants surviving existing test suites

    • Open source
    • 8.2K GitHub stars
    • Knowledge and memory
  21. Finds other instances of a known bug's root cause across a codebase

    • Open source
    • 8.2K GitHub stars
    • Security
  22. Guides an agent to write, review and structure Lean 4 proofs in Mathlib style

    • Open source
    • 8.2K GitHub stars
    • Developer tools
  23. Audits GitHub Actions workflows that run AI coding agents for prompt injection risks

    • Open source
    • 8.2K GitHub stars
    • AI models and LLM tooling
  24. Builds a verified map of an unfamiliar codebase before any bug hunting begins

    • Open source
    • 8.2K GitHub stars
    • Security
  25. Audits Algorand TEAL and PyTeal contracts against 11 platform-specific vulnerability

    • Open source
    • 8.2K GitHub stars
    • Security