Skills.

Give your AI a better way to work.

A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.

Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.

Category: Databases & data

2,391 results · page 8 of 80

  • nber-working-papers-apiSkillDatabases & data

    Lets your agent search NBER working papers and pull economic datasets like business cycle dates.

    Ready to connect★ 4k

    github.com/brycewang-stanford/auto-empirical-research-skills4k stars

    View details
  • google-analyticsSkillDatabases & data

    Lets your agent analyze Google Analytics 4 traffic, conversions, and events, and manage key events or custom dimensions.

    Ready to connect★ 4k

    github.com/nowork-studio/notfair-plugin4k stars

    View details
  • offensive-sqliSkillDatabases & data

    Teaches your agent how to test web apps for SQL injection flaws during security audits.

    Ready to connect★ 3k

    github.com/snailsploit/claude-red4k stars

    View details
  • agent-analyticsSkillDatabases & data

    Lets your agent track analytics, run A/B experiments, and analyze growth data for your projects.

    Ready to connect★ 3k

    github.com/davepoon/buildwithclaude3k stars

    View details
  • cohesivitySkillDatabases & data

    Lets your agent work with backend and infrastructure tasks through Cohesivity when it's already set up.

    Ready to connect★ 3k

    github.com/davepoon/buildwithclaude3k stars

    View details
  • wiki-exportSkillDatabases & data

    Lets your agent export an Obsidian wiki's link graph as JSON, GraphML, SQL, or an interactive HTML visualization.

    Ready to connect★ 3k

    github.com/ar9av/obsidian-wiki3k stars

    View details
  • adrSkillDatabases & data

    Lets your agent record and look up architecture decisions with reasoning in docs/adr/.

    Ready to connect★ 3k

    github.com/linuxfoundation/crowd.dev3k stars

    View details
  • scaffold-snowflake-connectorSkillDatabases & data

    Lets your agent scaffold a new Snowflake data source for crowd.dev, generating queries, transformers, and type registrations.

    Ready to connect★ 3k

    github.com/linuxfoundation/crowd.dev3k stars

    View details
  • accelerated-computing-cudfSkillDatabases & data

    Gives your agent NVIDIA's official guidance for running pandas-style data work on GPUs with cuDF.

    Ready to connect★ 3k

    github.com/nvidia/skills3k stars

    View details
  • amc-run-rtsp-calibrationSkillDatabases & data

    Lets your agent calibrate a new dataset from live RTSP camera streams using the AutoMagicCalib API.

    Ready to connect★ 3k

    github.com/nvidia/skills3k stars

    View details
  • amc-run-sample-calibrationSkillDatabases & data

    Lets your agent run a test calibration on a sample dataset to check that an AMC service is working.

    Ready to connect★ 3k

    github.com/nvidia/skills3k stars

    View details
  • amc-run-video-calibrationSkillDatabases & data

    Lets your agent calibrate camera data from local MP4 video files using an online calibration service.

    Ready to connect★ 3k

    github.com/nvidia/skills3k stars

    View details
  • cupynumeric-hdf5SkillDatabases & data

    Lets your agent save and load large cuPyNumeric arrays as HDF5 files using fast parallel I/O.

    Ready to connect★ 3k

    github.com/nvidia/skills3k stars

    View details
  • cupynumeric-parallel-data-loadSkillDatabases & data

    Lets your agent load large sharded datasets into a distributed array for parallel processing.

    Ready to connect★ 3k

    github.com/nvidia/skills3k stars

    View details
  • data-designerSkillDatabases & data

    Lets your agent create datasets, generate synthetic data, and build data generation pipelines.

    Ready to connect★ 3k

    github.com/nvidia/skills3k stars

    View details
  • deepstream-devSkillDatabases & data

    Helps your agent build video analytics pipelines with NVIDIA DeepStream, including object detection, tracking, and Kafka integration.

    Ready to connect★ 3k

    github.com/nvidia/skills3k stars

    View details
  • deepstream-run-mv3dtSkillDatabases & data

    Lets your agent set up and run NVIDIA's Multi-View 3D Tracking app on sample or custom MP4 video datasets.

    Ready to connect★ 3k

    github.com/nvidia/skills3k stars

    View details
  • i4h-workflow-dataset-annotateSkillDatabases & data

    Lets your agent use a vision model to check whether recorded robot episodes match the task description.

    Ready to connect★ 3k

    github.com/nvidia/skills3k stars

    View details
  • i4h-workflow-dataset-convertSkillDatabases & data

    Lets your agent convert HDF5 recordings of agent tasks into LeRobot datasets with parquet files, metadata, and videos.

    Ready to connect★ 3k

    github.com/nvidia/skills3k stars

    View details
  • i4h-workflow-dataset-mimicSkillDatabases & data

    Lets your agent expand a recorded robotics dataset by cloning trajectories with added action and state noise.

    Ready to connect★ 3k

    github.com/nvidia/skills3k stars

    View details
  • i4h-workflow-dataset-replaySkillDatabases & data

    Lets your agent replay a recorded HDF5 robot episode inside Isaac Sim to visually check what happened.

    Ready to connect★ 3k

    github.com/nvidia/skills3k stars

    View details
  • i4h-workflow-dataset-teleopSkillDatabases & data

    Lets your agent record teleoperation episodes (keyboard, robot arm, or VR) as human demos saved to HDF5 files.

    Ready to connect★ 3k

    github.com/nvidia/skills3k stars

    View details
  • i4h-workflow-finetuneSkillDatabases & data

    Lets your agent fine-tune a robotics policy on a demonstration dataset.

    Ready to connect★ 3k

    github.com/nvidia/skills3k stars

    View details
  • bio-database-evidenceSkillDatabases & data

    Lets your agent pull gene, variant, cancer, and pathway evidence from major biological databases.

    Ready to connect★ 3k

    github.com/foryourhealth111-pixel/vibe-skills3k stars

    View details
  • biopythonSkillDatabases & data

    Lets your agent parse and analyze biological sequence data like FASTA files, run alignments, and query databases like NCBI.

    Ready to connect★ 3k

    github.com/foryourhealth111-pixel/vibe-skills3k stars

    View details
  • datacommons-clientSkillDatabases & data

    Lets your agent query public statistics like demographics, economics, health, and environment data from Data Commons.

    Ready to connect★ 3k

    github.com/foryourhealth111-pixel/vibe-skills3k stars

    View details
  • detecting-data-anomaliesSkillDatabases & data

    Guides your agent through finding outliers, spikes, and suspicious records in a dataset.

    Ready to connect★ 3k

    github.com/foryourhealth111-pixel/vibe-skills3k stars

    View details
  • fda-databaseSkillDatabases & data

    Lets your agent look up FDA data on drugs, medical devices, adverse events, recalls, and regulatory submissions.

    Ready to connect★ 3k

    github.com/foryourhealth111-pixel/vibe-skills3k stars

    View details
  • lamindbSkillDatabases & data

    Lets your agent manage and query biological datasets like scRNA-seq and track reproducible workflows in LaminDB.

    Ready to connect★ 3k

    github.com/foryourhealth111-pixel/vibe-skills3k stars

    View details
  • metabolomics-workbench-databaseSkillDatabases & data

    Lets your agent search NIH Metabolomics Workbench for metabolite data, study metadata, and mass spectrometry results.

    Ready to connect★ 3k

    github.com/foryourhealth111-pixel/vibe-skills3k stars

    View details

What is a skill?

A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.

52,524 of the 52,958 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.

Install one and every AI you use gets it

Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.

Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.

See how to connect your AI