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
54,514 results · page 505 of 1,818
- View details
nw-persona-jtbd-analysisSkillMonitoring & ops
Lets your agent build user personas and map jobs-to-be-done with templates, pain points, and success metrics.
Ready to connect★ 614
- View details
nw-platform-engineering-foundationsSkillDev tools
Gives your agent background knowledge on platform engineering topics like SRE, continuous delivery, and team topologies.
Ready to connect★ 614
- View details
nw-po-review-dimensionsSkillDev tools
Lets your agent critique requirements documents for bias, completeness, clarity, testability, and priority issues.
Ready to connect★ 614
- View details
nw-por-review-criteriaSkillDev tools
Gives your agent review criteria and common bug patterns to check journey artifacts against.
Ready to connect★ 614
- View details
nw-post-mortem-frameworkSkillMonitoring & ops
Lets your agent write blameless post-mortems, rebuild incident timelines, and evaluate how a response was handled.
Ready to connect★ 614
- View details
nw-production-readinessSkillFiles & storage
Lets your agent check whether software is ready to launch using checklists for monitoring and releases.
Ready to connect★ 614
- View details
nw-production-safetySkillDocs & knowledge
Lets your agent follow safety rules for validating inputs, filtering outputs, and limiting what it changes.
Ready to connect★ 614
- View details
nw-progressive-refactoringSkillDev tools
Guides your agent through step-by-step code refactoring using a catalog of code smells and safe transformations.
Ready to connect★ 614
- View details
nw-property-based-testingSkillDev tools
Guides your agent in writing property-based and mutation tests to check that code is thoroughly tested.
Ready to connect★ 614
- View details
nw-quality-frameworkSkillMonitoring & ops
Lets your agent run quality checks on code commits, builds, and tests before changes are finalized.
Ready to connect★ 614
- View details
nw-quality-validationSkillDocs & knowledge
Lets your agent check documentation against quality checklists and thresholds.
Ready to connect★ 614
- View details
nw-query-optimizationSkillDatabases & data
Teaches your agent how to analyze and speed up slow database queries using indexing and execution plans.
Ready to connect★ 614
- View details
nw-refactorSkillDev tools
Guides your agent through structured, level-based refactoring passes to improve code quality.
Ready to connect★ 614
- View details
nw-researchSkillFiles & storage
Lets your agent gather facts from the web and your files and write a cited research document.
Ready to connect★ 614
- View details
nw-research-methodologySkillDev tools
Gives your agent templates and quality standards for doing evidence-driven research and summarizing findings.
Ready to connect★ 614
- View details
nw-reviewSkillAI & models
Lets your agent send roadmaps or plans to an expert reviewer for a quality critique before proceeding.
Ready to connect★ 614
- View details
nw-review-output-formatSkillMedia
Lets your agent write design review feedback in a standard YAML format with approval criteria.
Ready to connect★ 614
- View details
nw-review-workflowSkillAI & models
Gives your agent a step-by-step checklist and scoring method for reviewing agent definitions.
Ready to connect★ 614
- View details
nw-rigorSkillDev tools
Lets your agent set a quality-vs-effort profile (lean to exhaustive) for its work, saved globally or per project.
Ready to connect★ 614
- View details
nw-roadmapSkillDev tools
Lets your agent create a phased roadmap file with acceptance criteria and test-driven steps for a feature.
Ready to connect★ 614
- View details
nw-roadmap-designSkillMedia
Lets your agent write concise implementation roadmaps with clear steps and acceptance criteria.
Ready to connect★ 614
- View details
nw-roadmap-review-checksSkillDev tools
Lets your agent run validation checks on roadmaps during architecture reviews.
Ready to connect★ 614
- View details
nw-root-whySkillDev tools
Lets your agent investigate bugs and trace them back to their root cause.
Ready to connect★ 614
- View details
nw-rr-critique-dimensionsSkillDocs & knowledge
Gives your agent criteria and scoring rubrics for reviewing research documents.
Ready to connect★ 614
- View details
nw-sa-critique-dimensionsSkillDocs & knowledge
Gives your agent a set of quality dimensions for critiquing software architecture documents during peer review.
Ready to connect★ 614
- View details
nw-sc-review-dimensionsSkillDev tools
Lets your agent critique code changes for bias, test quality, completeness, and priority during peer review.
Ready to connect★ 614
- View details
nw-sd-case-studiesSkillMedia
25 real-world system design case studies condensed from Alex Xu's System Design Interview Vol 1 and 2 - requirements, architecture, deep dive insights, key takeaways
Ready to connect★ 614
- View details
nw-sd-frameworkSkillMedia
Lets your agent tackle system design questions using a 4-step framework with rough estimates and common pitfalls.
Ready to connect★ 614
- View details
nw-sd-patternsSkillCommunication
Lets your agent apply distributed systems design patterns like caching, sharding, and rate limiting.
Ready to connect★ 614
- View details
nw-sd-patterns-advancedSkillMonitoring & ops
Guides your agent in designing systems that record every change and handle failures reliably.
Ready to connect★ 614
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.
54,082 of the 54,514 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.