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
70,704 results · page 637 of 2,357
- View details
thinking-lindy-effectSkillDev tools
Lets your agent judge how reliable a tool or option is based on how long it has already existed.
Ready to connect★ 2k
- View details
thinking-map-territorySkillMonitoring & ops
Stops your agent from theorizing and makes it verify claims against actual code or data when they conflict.
Ready to connect★ 2k
- View details
thinking-margin-of-safetySkillDev tools
Guides your agent to add safety buffers to estimates and limits based on uncertainty and breach cost.
Ready to connect★ 2k
- View details
thinking-model-combinationSkillAI & models
Lets your agent combine multiple thinking models with assigned roles to solve complex problems.
Ready to connect★ 2k
- View details
thinking-model-routerSkillAI & models
Lets your agent pick the right thinking skill for a problem by matching its domain and problem type.
Ready to connect★ 2k
- View details
thinking-oodaSkillDev tools
Lets your agent make quick decisions under uncertainty using an Observe-Orient-Decide-Act cycle.
Ready to connect★ 2k
- View details
thinking-opportunity-costSkillDev tools
Makes your agent weigh a decision against the best forgone alternative before committing time, people, or money.
Ready to connect★ 2k
- View details
thinking-pre-mortemSkillDev tools
Lets your agent stress-test a plan by assuming it failed and working out what went wrong and how to prevent it.
Ready to connect★ 2k
- View details
thinking-probabilisticSkillDev tools
Lets your agent forecast and estimate more accurately using base rates, probability ranges, and evidence updates.
Ready to connect★ 2k
- View details
thinking-red-teamSkillSecurity
Lets your agent run an authorized security review by modeling attackers and reporting verified, exploitable flaws.
Ready to connect★ 2k
- View details
thinking-reversibilitySkillDev tools
Helps your agent decide whether to act fast or slow by judging if a choice is easy to undo.
Ready to connect★ 2k
- View details
thinking-scientific-methodSkillDev tools
Guides your agent to rank possible causes of a problem and test the cheapest one first.
Ready to connect★ 2k
- View details
thinking-second-orderSkillDev tools
Lets your agent trace the knock-on effects of a change—like incentives and scale—before committing to it.
Ready to connect★ 2k
- View details
thinking-socraticSkillDev tools
Helps your agent ask clarifying questions to uncover hidden requirements before building on vague requests.
Ready to connect★ 2k
- View details
thinking-steel-manningSkillDev tools
Guides your agent to build the strongest case against a proposal before rejecting or agreeing, then update its view.
Ready to connect★ 2k
- View details
thinking-systemsSkillDev tools
Lets your agent analyze complex systems by mapping feedback loops and finding high-leverage points to fix problems.
Ready to connect★ 2k
- View details
thinking-theory-of-constraintsSkillDev tools
Lets your agent find and fix the one bottleneck limiting a pipeline's speed instead of optimizing everything.
Ready to connect★ 2k
- View details
thinking-thought-experimentSkillDev tools
Lets your agent reason through thought experiments when real tests are too rare, large, or irreversible.
Ready to connect★ 2k
- View details
thinking-trizSkillMedia
Lets your agent resolve design conflicts by naming contradictions and finding no-compromise solutions.
Ready to connect★ 2k
- View details
thinking-via-negativaSkillDev tools
Lets your agent solve problems by removing unneeded parts first, guarding against irreversible deletions.
Ready to connect★ 2k
- View details
female-portrait-directorSkillMedia
Lets your agent build and refine detailed image prompts for adult female portrait photos.
Ready to connect★ 2k
- View details
architectSkillMedia
Lets your agent sketch types, signatures, and module structure before any code gets written.
Ready to connect★ 2k
- View details
arenaSkillProductivity
Lets your agent run several parallel attempts at the same task, then combine the best parts into one result.
Ready to connect★ 2k
- View details
automate-meSkillAI & models
Automate me: turns your working preferences into a personalized '-mode' skill your agent follows.
Ready to connect★ 2k
- View details
- View details
create-verification-skillSkillAI & models
Lets your agent create a skill that tests your app by driving it like a real user would.
Ready to connect★ 2k
- View details
figure-it-outSkillMonitoring & ops
Lets your agent build a careful, reviewable plan for big or unclear tasks, logging each decision as it works.
★ 2k
- View details
fix-merge-conflictsSkillAI & models
Lets your agent find and fix git merge conflicts, then run builds and tests to confirm the branch works.
Ready to connect★ 2k
- View details
howSkillAI & models
Lets your agent explain how a codebase works, giving architecture overviews and answers to "how does X work" questions.
Ready to connect★ 2k
- View details
interrogateSkillAI & models
Lets your agent have several AI models review and challenge your code from different angles.
Ready to connect★ 2k
Popular skills lists
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
- Best Claude skills for superpowers
- Best Claude skills for obsidian
- Best Claude skills for frontend design
- All best lists
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.
68,574 of the 70,704 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 workspace 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.