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
54,221 results · page 329 of 1,808
- View details
atmos-terraformSkillCloud & infra
Lets your agent run Terraform plans and applies, manage workspaces, and set up backend and variable configs.
Ready to connect★ 1k
- View details
atmos-terraform-state-migrationsSkillCloud & infra
Lets your agent plan and apply Terraform state migrations safely using tfmigrate workflows in Atmos.
Ready to connect★ 1k
- View details
atmos-validationSkillFiles & storage
Lets your agent check Atmos project configs, JSON Schema inputs, EditorConfig, and GitHub Actions for errors.
Ready to connect★ 1k
- View details
atmos-vendoringSkillFiles & storage
Lets your agent manage vendored infrastructure components by pulling, updating, and diffing copies from Git, S3, and other sources.
Ready to connect★ 1k
- View details
atmos-versionSkillFiles & storage
Lets your agent track, pin, and verify versions of external dependencies in Atmos configurations.
Ready to connect★ 1k
- View details
atmos-workflowsSkillDev tools
Lets your agent run multi-step cloud infrastructure workflows with conditions, retries, and parallel steps.
Ready to connect★ 1k
- View details
atmos-yaml-functionsSkillCloud & infra
Lets your agent pull Terraform outputs, secrets, and env values into Atmos YAML config files using functions.
Ready to connect★ 1k
- View details
code-hygieneSkillDev tools
Reviews your code changes for structural design problems that linting and tests can't catch.
Ready to connect★ 1k
- View details
component-developmentSkillDev tools
Lets your agent develop and modify Atmos components, including registry providers, commands, schema, tests, and docs.
Ready to connect★ 1k
- View details
field-testSkillDev tools
Runs a hands-on usability test of a feature or CLI command by executing it against real state and reporting findings.
Ready to connect★ 1k
- View details
fix-allSkillAI & models
Lets your agent run a full readiness pass on your branch's PR: sync main, check CI, resolve review threads, fix lint and coverage issues.
Ready to connect★ 1k
- View details
fix-logSkillMonitoring & ops
Has your agent write a durable record of each bug fix or repair it completes under docs/fixes.
Ready to connect★ 1k
- View details
homebrewSkillAI & models
Guides your agent through creating or fixing a Homebrew formula pull request for atmos.
Ready to connect★ 1k
- View details
pr-maintenance-loopSkillDev tools
Runs an hourly background loop that keeps your PR rebased, CI green, tests passing, and code-review threads resolved.
Ready to connect★ 1k
- View details
roadmapSkillWeb & browsing
Lets your agent update a project roadmap file with milestones, initiatives, and quarterly progress.
Ready to connect★ 1k
- View details
saySkillProductivity
Lets your agent speak task updates out loud on a Mac when work finishes or needs your input.
Ready to connect★ 1k
- View details
security-remediateSkillMonitoring & ops
Lets your agent fix reported code vulnerability alerts by committing fixes directly to the current git branch.
Ready to connect★ 1k
- View details
speckit-analyzeSkillProductivity
Lets your agent check that spec, plan, and task documents stay consistent with each other.
Ready to connect★ 1k
- View details
speckit-checklistSkillDev tools
Lets your agent generate a custom checklist for the feature you're building based on your requirements.
Ready to connect★ 1k
- View details
speckit-clarifySkillDev tools
Lets your agent spot vague parts of a feature spec and ask up to 5 targeted questions, then record the answers in the spec.
Ready to connect★ 1k
- View details
speckit-constitutionSkillDev tools
Lets your agent create or update a project constitution file and keep related templates in sync.
Ready to connect★ 1k
- View details
speckit-git-featureSkillDev tools
Lets your agent create a git feature branch with sequential or timestamp numbering.
Ready to connect★ 1k
- View details
speckit-implementSkillProductivity
Lets your agent execute all coding tasks listed in a tasks.md implementation plan.
Ready to connect★ 1k
- View details
speckit-planSkillMedia
Lets your agent run a planning workflow that turns a spec into design artifacts from a template.
Ready to connect★ 1k
- View details
speckit-specifySkillDev tools
Lets your agent create or update a feature specification from a plain-language description of the feature.
Ready to connect★ 1k
- View details
speckit-tasksSkillMedia
Lets your agent turn a feature's design documents into a step-by-step, dependency-ordered task list.
Ready to connect★ 1k
- View details
speckit-taskstoissuesSkillMedia
Lets your agent turn existing tasks into ordered GitHub issues with dependencies for a feature.
Ready to connect★ 1k
- View details
creative-thinking-for-researchSkillDev tools
Guides your agent through cognitive-science-based frameworks to generate novel research ideas for CS and AI.
Ready to connect★ 1k
- View details
ml-training-recipesSkillProductivity
Lets your agent follow proven PyTorch training recipes for models like LLMs, vision, and biomedical networks.
Ready to connect★ 1k
- View details
nanoresearch-experimentSkillDev tools
Lets your agent generate a Python code skeleton from an experiment blueprint.
Ready to connect★ 1k
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.
53,789 of the 54,221 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.