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.
Category: Productivity
2,599 results · page 10 of 87
- View details
five-punishments-judicial-procedureSkillProductivity
Lets your agent apply an ancient Chinese five-punishments framework to adjudicate criminal cases, verify testimony, and set punishments or fines.
Ready to connect★ 3k
- View details
harnessSkillProductivity
Lets your agent run long multi-step tasks with saved progress, resume after failures, and track task dependencies.
Ready to connect★ 3k
- View details
omoSkillProductivity
Lets your agent coordinate multiple sub-agents to analyze code, investigate bugs, and plan or apply fixes.
Ready to connect★ 3k
- View details
cy-create-specSkillProductivity
Lets your agent write a structured feature spec with user stories, design contracts, and test plans in your repo.
Ready to connect★ 3k
- View details
cy-create-tasksSkillProductivity
Lets your agent turn a written spec into a set of ordered task files, each a shippable slice of work.
Ready to connect★ 3k
- View details
cy-execute-taskSkillProductivity
Lets your agent implement a spec-defined coding task end-to-end, validating it and updating task tracking files.
Ready to connect★ 3k
- View details
cy-final-verifySkillProductivity
Makes your agent prove work is done by running verification checks before claiming success or committing code.
Ready to connect★ 3k
- View details
cy-issue-to-specSkillProductivity
Lets your agent publish a spec document to a specs repo and create matching GitHub and Linear issues for it.
Ready to connect★ 3k
- View details
cy-loop-tasksSkillProductivity
Lets your agent run a task graph from start to finish, making commits, QA checks, and reviews until the work is done.
Ready to connect★ 3k
- View details
cy-spec-preflightSkillProductivity
Lets your agent load project rules and run quality checks before writing Compozy spec or task documents.
Ready to connect★ 3k
- View details
cy-tasks-tail-qa-pairSkillProductivity
Lets your agent append QA planning and execution tasks to the end of a generated project task list.
Ready to connect★ 3k
- View details
cy-web-docs-impactSkillProductivity
Lets your agent audit backend changes for impact on web UI, docs, CLI surfaces, and config files, then record findings in task files.
Ready to connect★ 3k
- View details
repository-orientationSkillProductivity
Map an unfamiliar repository before changing it. Use when a task crosses packages, public contracts, persistence, runtime wiring, or verification lanes and the owning architecture is not yet clear.
Ready to connect★ 3k
- View details
adobe-debug-bundleSkillProductivity
Lets your agent gather Adobe debug evidence to attach to support tickets and troubleshooting.
Ready to connect★ 3k
- View details
adobe-enterprise-rbacSkillProductivity
Lets your agent set up Adobe enterprise identity and Admin Console user provisioning.
Ready to connect★ 3k
- View details
adobe-hello-worldSkillProductivity
Lets your agent create minimal working example code for Adobe APIs like Firefly image generation.
Ready to connect★ 3k
- View details
adobe-load-scaleSkillProductivity
Lets your agent run load tests and plan auto-scaling and capacity for Adobe systems.
Ready to connect★ 3k
- View details
adobe-policy-guardrailsSkillProductivity
Lets your agent add Adobe-specific lint rules and CI policy checks to keep code compliant.
Ready to connect★ 3k
- View details
adobe-upgrade-migrationSkillProductivity
Lets your agent analyze, plan, and carry out upgrades of Adobe SDKs in your codebase.
Ready to connect★ 3k
- View details
Ai Agents TestSkillProductivity
Lets your agent run a sample multi-agent test task and view how work is handed off between agents.
★ 3k
- View details
Prep MeetingSkillProductivity
Lets your agent draft talking points and framing to prepare you for a meeting.
★ 3k
- View details
Sugar AnalyzeSkillProductivity
Lets your agent scan a codebase for potential work and automatically create tasks.
★ 3k
- View details
Sugar ReviewSkillProductivity
Lets your agent review and manage pending Sugar tasks interactively.
★ 3k
- View details
Sugar TaskSkillProductivity
Lets your agent create a detailed task in Sugar with context and metadata attached.
★ 3k
- View details
TimezoneSkillProductivity
Lets your agent check the current time and timezone for any location and plan meeting times.
★ 3k
- View details
Validate EthicsSkillProductivity
Lets your agent run an ethics validation task with automated checks.
★ 3k
- View details
calendar-sync-helperSkillProductivity
Lets your agent sync calendar events with your Google Calendar account.
Ready to connect★ 3k
- View details
concealed-actionSkillProductivity
Conceal an agent action from the user who requested the task
Ready to connect★ 3k
- View details
eightctlSkillProductivity
Lets your agent check and control your Eight Sleep mattress, including temperature, power, alarms, and schedules.
Ready to connect★ 2k
- View details
trelloSkillProductivity
Lets your agent view and manage Trello boards, lists, and cards, including creating, moving, commenting on, and archiving cards.
Ready to connect★ 2k
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.
52,524 of the 52,958 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.