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 574 of 1,823
- View details
benchmark-synthesisSkillDev tools
Lets your agent produce a structured audit report as final output.
Ready to connect★ 481
- View details
best-option-selectionSkillDev tools
Lets your agent pick the single best option from a set of candidates using established scoring methods like WSM or TOPSIS.
Ready to connect★ 481
- View details
bias-detectionSkillDev tools
Lets your agent check a set of research evidence for biases like publication and reporting bias.
Ready to connect★ 481
- View details
biological-function-mappingSkillDev tools
Lets your agent map technical functions to biological systems to reframe problems in biological terms.
Ready to connect★ 481
- View details
biological-strategy-extractionSkillDev tools
Lets your agent extract strategy principles and mechanisms from organisms for research.
Ready to connect★ 481
- View details
biologize-and-discoverSkillMedia
Guides your agent through a step-by-step biomimicry process to solve design problems using nature-inspired ideas.
Ready to connect★ 481
- View details
biomimicrySkillDev tools
Lets your agent find design solutions by studying how nature solves similar problems.
Ready to connect★ 481
- View details
biomimicry-synthesisSkillDev tools
Lets your agent combine biomimicry research outputs into one structured idea report.
Ready to connect★ 481
- View details
biotriz-principle-selectionSkillDev tools
Lets your agent pick applicable BioTRIZ principles for a given contradiction.
Ready to connect★ 481
- View details
biotriz-resolutionSkillDev tools
Lets your agent apply biological analogies and a contradiction matrix to solve engineering design problems.
Ready to connect★ 481
- View details
bisociation-network-constructionSkillDev tools
Lets your agent build a network of concepts that bridge different domains to spark new ideas.
Ready to connect★ 481
- View details
blend-completionSkillDev tools
Lets your agent complete blends by adding background knowledge to them.
Ready to connect★ 481
- View details
blend-compositionSkillDev tools
Lets your agent compose new connections in blended space for de-anthropocentric research.
Ready to connect★ 481
- View details
blend-constructionSkillDev tools
Lets your agent build complete 4-space blends with emergent structure.
Ready to connect★ 481
- View details
blend-elaborationSkillDev tools
Lets your agent reason through a blend as a mental simulation before acting.
Ready to connect★ 481
- View details
boundary-analysisSkillDev tools
Lets your agent probe where methods fail and map the limits of their validity.
Ready to connect★ 481
- View details
boundary-condition-specificationSkillDev tools
Lets your agent define the exact conditions under which a research hypothesis holds true.
Ready to connect★ 481
- View details
boundary-critiqueSkillDev tools
Lets your agent critically examine a system's boundaries, asking what is included, excluded, and who benefits.
Ready to connect★ 481
- View details
boundary-enumerationSkillDev tools
Lets your agent identify parameter boundaries and edge values to build stronger test cases.
Ready to connect★ 481
- View details
boundary-probingSkillSearch
Lets your agent test edge cases by generating extreme values and probing system boundaries.
Ready to connect★ 481
- View details
boundary-synthesisSkillDev tools
Lets your agent compile boundary analysis results into a single coherent validity report.
Ready to connect★ 481
- View details
boundary-unfoldingSkillDev tools
Lets your agent run a 12-question method to uncover hidden system boundaries in a design or analysis.
Ready to connect★ 481
- View details
breakpoint-detectionSkillDev tools
Lets your agent test a claim at extreme parameter values to find the exact point where it breaks.
Ready to connect★ 481
- View details
bridge-validationSkillDev tools
Lets your agent check whether a comparison between two ideas is deep enough to draw conclusions from.
Ready to connect★ 481
- View details
budget-constrained-designSkillMedia
Lets your agent plan experiments that fit within given compute and time budgets.
Ready to connect★ 481
- View details
buffer-sizingSkillDev tools
Lets your agent calculate project, feeding, and resource buffers for planning work.
Ready to connect★ 481
- View details
campaign-selectionSkillDev tools
Lets your agent run a structured question process to decide which campaigns to include and emphasize.
Ready to connect★ 481
- View details
capability-taxonomy-mappingSkillDev tools
Lets your agent build a capability taxonomy and map how well benchmarks cover it.
Ready to connect★ 481
- View details
categorize-papersSkillDev tools
Lets your agent group research papers into natural clusters by theme, method, or timeline.
Ready to connect★ 481
- View details
category-sortingSkillDev tools
Lets your agent sort candidates into predefined categories using structured decision rules.
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.