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.
Filter by category
55,543 results · page 111 of 1,852
- View details
ml-training-recipeSkillDatabases & data
Lets your agent find practical machine learning training recipes from papers, datasets, docs, and code.
Ready to connect★ 10k
- View details
modal-computeSkillCloud & infra
Lets your agent run research benchmark or replication scripts on remote GPU computers by writing a Python script and calling the Modal CLI.
Ready to connect★ 10k
- View details
openfold3SkillProductivity
Lets your agent run and document protein structure prediction workflows, checking inputs and comparing results for reproducibility.
Ready to connect★ 10k
- View details
paper-code-auditSkillDev tools
Lets your agent compare a research paper's claims against its public code to find mismatches.
Ready to connect★ 10k
- View details
paper-narrativeSkillProductivity
Lets your agent strengthen a scientific paper's argument by restructuring sections, figures, and evidence flow.
Ready to connect★ 10k
- View details
pdf-exploreSkillDocs & knowledge
Lets your agent read scientific PDFs and pull out methods, figures, tables, and citations with page references.
Ready to connect★ 10k
- View details
product-self-knowledgeSkillDev tools
Lets your agent answer questions about Feynman's own features and settings by checking its source and docs.
Ready to connect★ 10k
- View details
proteinmpnnSkillMedia
Lets your agent design protein sequences that fit a given 3D backbone structure.
Ready to connect★ 10k
- View details
remote-compute-modalSkillProductivity
Lets your agent run research notebooks and compute jobs on Modal's cloud, including GPU tasks.
Ready to connect★ 10k
- View details
remote-compute-sshSkillMonitoring & ops
Lets your agent run research jobs on remote machines over SSH or Slurm and collect the results.
Ready to connect★ 10k
- View details
replicationSkillDev tools
Lets your agent plan and run replications of papers, claims, or benchmarks to verify results.
Ready to connect★ 10k
- View details
runpod-computeSkillDatabases & data
Lets your agent create and manage rented GPU servers on RunPod to run long research experiments with SSH access.
Ready to connect★ 10k
- View details
scgptSkillProductivity
Runs scGPT-style single-cell analysis like cell annotation, embeddings, and perturbation prediction on gene datasets.
Ready to connect★ 10k
- View details
self-awarenessSkillFiles & storage
Lets your agent look up what happened in its current workbench session, like which files were written and which tools ran.
Ready to connect★ 10k
- View details
session-logSkillDocs & knowledge
Lets your agent write a session log summarizing completed work, findings, questions, and next steps.
Ready to connect★ 10k
- View details
session-searchSkillSearch
Lets your agent search past Feynman session transcripts to recover earlier work.
Ready to connect★ 10k
- View details
solublempnnSkillMedia
Lets your agent design and screen protein sequences for solubility using structured design workflows.
Ready to connect★ 10k
- View details
source-comparisonSkillDev tools
Lets your agent compare several sources on a topic and produce a grounded comparison matrix.
Ready to connect★ 10k
- View details
using-model-endpointSkillProductivity
Lets your agent send requests to a configured model endpoint and interpret the predictions it gets back.
Ready to connect★ 10k
- View details
watchSkillMonitoring & ops
Lets your agent set up a baseline survey of a research field and track new papers or updates over time.
Ready to connect★ 10k
- View details
gsd-add-testsSkillDev tools
Lets your agent generate tests for a completed work phase based on acceptance criteria and what was built.
Ready to connect★ 9k
- View details
gsd-ai-integration-phaseSkillMedia
Lets your agent write an AI-SPEC.md design contract for project phases that build AI systems.
Ready to connect★ 9k
- View details
gsd-audit-fixSkillDev tools
Lets your agent find code issues, classify them, apply fixes, test, and commit the changes.
Ready to connect★ 9k
- View details
gsd-audit-milestoneSkillDev tools
Lets your agent check whether a project milestone was fully completed as originally planned before archiving it.
Ready to connect★ 9k
- View details
gsd-audit-uatSkillDev tools
Lets your agent audit all outstanding UAT and verification items across project phases.
Ready to connect★ 9k
- View details
gsd-autonomousSkillDev tools
Lets your agent work through project phases on its own, discussing, planning, and executing each one.
Ready to connect★ 9k
- View details
gsd-captureSkillDocs & knowledge
Lets your agent save ideas, tasks, and notes to the right place.
Ready to connect★ 9k
- View details
gsd-cleanupSkillDev tools
Lets your agent archive phase directories left over from completed milestones.
Ready to connect★ 9k
- View details
gsd-code-reviewSkillFiles & storage
Lets your agent review recently changed source files for bugs, security issues, and code quality problems.
Ready to connect★ 9k
- View details
gsd-complete-milestoneSkillDev tools
Lets your agent archive a completed milestone and set up the next version.
Ready to connect★ 9k
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.
55,111 of the 55,543 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.