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 573 of 1,823
- View details
argument-visualizationSkillDev tools
Lets your agent turn arguments into visual diagrams of claims and how they connect.
Ready to connect★ 481
- View details
artifact-detectionSkillDev tools
Lets your agent detect annotation artifacts and shortcuts in benchmark datasets.
Ready to connect★ 481
- View details
ask-constraintsSkillDev tools
Lets your agent clarify hard boundaries of a research task, such as target venues and required methodology.
Ready to connect★ 481
- View details
ask-decomposition-validationSkillDev tools
Lets your agent show its breakdown of a research goal to you and check whether the steps seem reasonable before proceeding.
Ready to connect★ 481
- View details
ask-intentionalitySkillSearch
Lets your agent ask deeper follow-up questions to uncover the real reasons behind your requests.
Ready to connect★ 481
- View details
ask-obstacle-acceptanceSkillDev tools
Lets your agent list obstacles with severity ratings and proposed fixes for review.
Ready to connect★ 481
- View details
assess-obstacle-severitySkillDev tools
Lets your agent rate each obstacle's difficulty by how easily it can be overcome and how long it takes.
Ready to connect★ 481
- View details
assignee-normalizationSkillDev tools
Lets your agent standardize assignee names and find which corporate group they belong to.
Ready to connect★ 481
- View details
assumption-cascadeSkillDev tools
Guides your agent to surface hidden assumptions, sort them by dependency, and challenge the root ones.
Ready to connect★ 481
- View details
assumption-cascade-tracerSkillDev tools
Lets your agent map how assumptions depend on each other and trace failures back to their root cause.
Ready to connect★ 481
- View details
assumption-challengingSkillDev tools
Has your agent question and test the validity of assumptions in its research or plans.
Ready to connect★ 481
- View details
assumption-constraintSkillSecurity
Lets your agent rank which assumptions in an analysis are most fragile and assess their potential impact.
Ready to connect★ 481
- View details
assumption-criticalitySkillDev tools
Lets your agent test how conclusions change when each assumption is flipped to its opposite.
Ready to connect★ 481
- View details
assumption-destructionSkillDev tools
Lets your agent challenge its own assumptions by systematically negating them to find new solution spaces.
Ready to connect★ 481
- View details
assumption-excavationSkillDev tools
Lets your agent find, question, and test the hidden assumptions behind an idea or plan.
Ready to connect★ 481
- View details
assumption-negationSkillDev tools
Lets your agent stress-test a claim by assuming the opposite and checking if that leads to a contradiction.
Ready to connect★ 481
- View details
assumption-stress-testSkillSecurity
Lets your agent surface hidden assumptions in a plan or claim and rank which ones are most fragile.
Ready to connect★ 481
- View details
attack-resilience-scoringSkillDev tools
Lets your agent compute an overall resilience score from attack results and coverage.
Ready to connect★ 481
- View details
attack-vector-generationSkillSecurity
Lets your agent generate specific attack strategies for a given threat surface.
Ready to connect★ 481
- View details
axiom-negationSkillDev tools
Lets your agent spot and question hidden assumptions in its reasoning using de Bono's PO technique.
Ready to connect★ 481
- View details
axis-extractionSkillDev tools
Lets your agent systematically pull out axes of variation when analyzing research literature.
Ready to connect★ 481
- View details
axis-validationSkillDev tools
Lets your agent check that candidate axes in an analysis are independent and meaningful using a step-by-step procedure.
Ready to connect★ 481
- View details
ballot-collectionSkillDev tools
Lets your agent gather ranking ballots from multiple judges or perspectives.
Ready to connect★ 481
- View details
baseline-establishmentSkillDev tools
Lets your agent run a structured campaign to measure and record performance baselines.
Ready to connect★ 481
- View details
baseline-selectionSkillDev tools
Lets your agent pick suitable baselines to compare experiments against.
Ready to connect★ 481
- View details
baseline-synthesisSkillDev tools
Lets your agent produce a final structured baseline report combining all analysis results.
Ready to connect★ 481
- View details
benchmark-archaeologySkillDev tools
Lets your agent study and evaluate AI benchmarks using five systematic research strategies.
Ready to connect★ 481
- View details
benchmark-auditSkillDev tools
Lets your agent score a paper or report against 46 benchmark criteria and flag weaknesses.
Ready to connect★ 481
- View details
benchmark-challengeSkillDev tools
Lets your agent identify hidden assumptions in AI benchmarks and challenge common best practices.
Ready to connect★ 481
- View details
benchmark-sweepSkillDev tools
Lets your agent systematically scan known solutions and identify gaps in their coverage.
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.