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
54,680 results · page 571 of 1,823
- View details
genomilabSkillProductivity
Lets your agent run or continue genome-informed health investigations based on a patient's authorized genome data.
Ready to connect★ 482
- View details
gwas-catalogSkillDev tools
Lets your agent check genetic variants (rsIDs) against GWAS Catalog disease and trait associations.
Ready to connect★ 482
- View details
journalSkillDocs & knowledge
Lets your agent keep a running research journal of findings, decisions, contradictions, and open questions.
Ready to connect★ 482
- View details
journal-source-researchSkillDev tools
Lets your agent review public and source evidence and write back reviewed findings before drawing conclusions.
Ready to connect★ 482
- View details
nutrigenomicsSkillDev tools
Lets your agent look up research evidence linking gene variants to nutrient metabolism, food tolerance, and taste.
Ready to connect★ 482
- View details
pharmacogenomicsSkillDev tools
Lets your agent answer questions about how genes affect drug response using public pharmacogenomics data.
Ready to connect★ 482
- View details
prsSkillDev tools
Lets your agent compute a polygenic risk score from approved local DNA data and check overlap quality.
Ready to connect★ 482
- View details
rare-disease-cancerSkillDev tools
Lets your agent plan research into rare diseases, hereditary conditions, and cancer risk from genetic data.
Ready to connect★ 482
- View details
sequenceSkillDev tools
Lets your agent analyze DNA sequences for translations, ORFs, restriction sites, primers, and FASTA matches.
Ready to connect★ 482
- View details
variant-evidenceSkillDev tools
Lets your agent answer questions about genetic variants like rsIDs, alleles, genes, and genotypes.
Ready to connect★ 482
- View details
abductive-hypothesis-generationSkillAI & models
Lets your agent form best-guess explanations for surprising or conflicting findings.
Ready to connect★ 481
- View details
ablation-brainstormSkillDev tools
Guides your agent to remove system components one by one and observe what changes to find hidden effects.
Ready to connect★ 481
- View details
ablation-component-mappingSkillDev tools
Lets your agent map a system's architecture into units that can be removed one at a time for ablation studies.
Ready to connect★ 481
- View details
ablation-designSkillMedia
Helps your agent design ablation studies that show which parts of an ML system actually matter.
Ready to connect★ 481
- View details
ablation-executionSkillDev tools
Lets your agent remove system components one at a time and record each impact.
Ready to connect★ 481
- View details
abp-vulnerability-classificationSkillSecurity
Lets your agent classify assumptions by how load-bearing they are along two axes.
Ready to connect★ 481
- View details
abstraction-extractionSkillDev tools
Lets your agent pull general principles out of specific real-world examples.
Ready to connect★ 481
- View details
abstraction-ladderSkillDev tools
Lets your agent analyze a problem at multiple levels of abstraction to spark new connections.
Ready to connect★ 481
- View details
abstraction-ladderingSkillDev tools
Lets your agent reframe a problem by stepping up to broader 'why' questions and back down to concrete details.
Ready to connect★ 481
- View details
abstraction-to-designSkillMedia
Lets your agent turn abstract biological principles into practical design principles for research and problem-solving.
Ready to connect★ 481
- View details
action-priority-matrixSkillDev tools
Lets your agent score risks by severity, occurrence, and detection to rank failure modes.
Ready to connect★ 481
- View details
activity-listingSkillMedia
Lets your agent list all implementation activities from an experiment design.
Ready to connect★ 481
- View details
actor-profilingSkillDev tools
Lets your agent build a profile of the user's background, resources, and constraints.
Ready to connect★ 481
- View details
adaptive-pair-selectionSkillDev tools
Lets your agent pick the most informative pairs of items to compare, step by step.
Ready to connect★ 481
- View details
adversarial-debate-protocolSkillCloud & infra
Has your agent debate an idea by building a supporter and a critic to challenge each other.
Ready to connect★ 481
- View details
adversarial-debate-truthseekingSkillDev tools
Runs your agent through adversarial debates to test ideas for truth rather than winning arguments.
Ready to connect★ 481
- View details
adversarial-escalationSkillDev tools
Lets your agent run research that escalates probing pressure step by step to stress-test findings.
Ready to connect★ 481
- View details
adversarial-personaSkillDev tools
Lets your agent critique its own ideas by role-playing attacks from hostile personas like rival researchers.
Ready to connect★ 481
- View details
adversarial-roleplaySkillDev tools
Lets your agent build a hostile persona and attack your work from that viewpoint to find weaknesses.
Ready to connect★ 481
- View details
adversarial-stress-testingSkillDev tools
Lets your agent push an idea to logical extremes to test its boundaries and find flaws.
Ready to connect★ 481
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.
54,249 of the 54,680 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.