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 572 of 1,823
- View details
advocate-constructionSkillDev tools
Lets your agent build the strongest possible argument for a rejected candidate or opposing position.
Ready to connect★ 481
- View details
aggregation-methodSkillDev tools
Lets your agent combine several ranking lists into one consensus ranking using a chosen method.
Ready to connect★ 481
- View details
ahp-weightingSkillDev tools
Lets your agent calculate how much each scoring factor should count when judging options.
Ready to connect★ 481
- View details
ahrq-picme-assessmentSkillDev tools
Lets your agent assess a research gap systematically using the AHRQ PiCMe framework across 6 dimensions.
Ready to connect★ 481
- View details
ahrq-reason-classificationSkillDev tools
Lets your agent classify the root causes of gaps using the AHRQ 4-reason framework.
Ready to connect★ 481
- View details
alias-resolutionSkillDev tools
Lets your agent find and merge duplicate pages that use different names for the same concept.
Ready to connect★ 481
- View details
alternative-analysisSkillDev tools
Lets your agent run what-if analysis and explore alternative future scenarios from multiple perspectives.
Ready to connect★ 481
- View details
alternative-futuresSkillDev tools
Lets your agent generate 2-4 divergent future scenarios from one shared evidence base.
Ready to connect★ 481
- View details
alternative-model-generationSkillAI & models
Lets your agent create alternative versions of a model by relaxing, replacing, or generalizing its parts.
Ready to connect★ 481
- View details
alternative-scoringSkillDev tools
Lets your agent score each candidate option against your criteria to compare alternatives.
Ready to connect★ 481
- View details
alternatives-generationSkillDev tools
Lets your agent generate alternative approaches for a problem so no possible solution is overlooked.
Ready to connect★ 481
- View details
analogical-transferSkillDev tools
Lets your agent apply solutions from one domain to another using structured analogy mapping.
Ready to connect★ 481
- View details
analogy-chainSkillDev tools
Lets your agent build multi-layer analogy chains (3-5 levels) to explore an idea more deeply.
Ready to connect★ 481
- View details
analogy-extractionSkillDev tools
Lets your agent pull transferable structural principles from one domain and apply them to another.
Ready to connect★ 481
- View details
analogy-quality-assessmentSkillDev tools
Lets your agent grade how deep an analogy is, from surface resemblance to structural and systemic similarity.
Ready to connect★ 481
- View details
and-or-decomposeSkillDev tools
Lets your agent break a big goal into smaller sub-goals using AND/OR decomposition.
Ready to connect★ 481
- View details
anomaly-characterizationSkillDev tools
Lets your agent describe and classify phenomena that current scientific theories cannot explain.
Ready to connect★ 481
- View details
anomaly-driven-abductionSkillDev tools
Lets your agent reason from anomalous observations to likely explanations using abductive inference.
Ready to connect★ 481
- View details
answering-sequence-designSkillMedia
Lets your agent plan the best order to answer sub-questions when breaking down a complex research task.
Ready to connect★ 481
- View details
anti-benchmarkSkillDev tools
Lets your agent question hidden assumptions in industry best practices and deconstruct benchmarks.
Ready to connect★ 481
- View details
appreciative-discoverySkillSearch
Lets your agent find unusually successful examples and extract lessons that can be applied elsewhere.
Ready to connect★ 481
- View details
appreciative-reframingSkillDev tools
Lets your agent find what already works well and reframe problems from flaws to strengths.
Ready to connect★ 481
- View details
appropriateness-boundingSkillDev tools
Lets your agent set acceptability standards using the RAND/UCLA Appropriateness Method.
Ready to connect★ 481
- View details
ara-compileSkillDev tools
Lets your agent run an external ARA compiler once to build output files from a feeding plan.
Ready to connect★ 481
- View details
ara-from-contextSkillAI & models
Lets your agent turn research notes into a structured research artifact and run an epistemic review.
Ready to connect★ 481
- View details
ara-rigor-reviewSkillDev tools
Lets your agent run a six-dimension rigor review over the ARA project and deliver the resulting report.
Ready to connect★ 481
- View details
argument-crystallizationSkillDev tools
Lets your agent identify and distill the strongest arguments from each perspective in a debate or discussion.
Ready to connect★ 481
- View details
argument-extractionSkillDev tools
Lets your agent extract and strengthen the core arguments behind a set of opinions.
Ready to connect★ 481
- View details
argument-mappingSkillDev tools
Lets your agent extract claims and link evidence to map out argument structures.
Ready to connect★ 481
- View details
argument-synthesisSkillDev tools
Lets your agent combine evidence from multiple sources into balanced argument positions.
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.