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 5 of 87
- View details
diffdockSkillProductivity
Lets your agent run and plan DiffDock molecular docking to predict how a drug-like molecule binds to a protein.
Ready to connect★ 9k
- View details
esmfold2SkillProductivity
Lets your agent predict protein structures from amino acid sequences using fast ESMFold-style folding workflows.
Ready to connect★ 9k
- View details
fair-esm2SkillProductivity
Lets your agent run protein language model analysis like embeddings, mutation scoring, and sequence clustering.
Ready to connect★ 9k
- View details
indication-dossierSkillProductivity
Lets your agent build a sourced research report on a disease, drug target, or therapy with ranked evidence.
Ready to connect★ 9k
- View details
jobsSkillProductivity
Lets your agent check the status of running research jobs and scheduled follow-ups.
Ready to connect★ 9k
- View details
openfold3SkillProductivity
Lets your agent run and document protein structure prediction workflows, checking inputs and comparing results for reproducibility.
Ready to connect★ 9k
- View details
paper-narrativeSkillProductivity
Lets your agent strengthen a scientific paper's argument by restructuring sections, figures, and evidence flow.
Ready to connect★ 9k
- View details
remote-compute-modalSkillProductivity
Lets your agent run research notebooks and compute jobs on Modal's cloud, including GPU tasks.
Ready to connect★ 9k
- View details
scgptSkillProductivity
Runs scGPT-style single-cell analysis like cell annotation, embeddings, and perturbation prediction on gene datasets.
Ready to connect★ 9k
- View details
scvi-toolsSkillProductivity
Lets your agent run single-cell RNA analysis with scvi-tools, including batch correction, embeddings, and cell annotation.
Ready to connect★ 9k
- View details
using-model-endpointSkillProductivity
Lets your agent send requests to a configured model endpoint and interpret the predictions it gets back.
Ready to connect★ 9k
- View details
gsd-fastSkillProductivity
Lets your agent handle small quick tasks directly without spawning helpers or extra planning.
Ready to connect★ 9k
- View details
gsd-quickSkillProductivity
Lets your agent run a quick task with atomic commits and state tracking while skipping optional agents.
Ready to connect★ 9k
- View details
gsd-quick-batchSkillProductivity
Lets your agent plan, run, and merge several small tasks together as a single batch.
Ready to connect★ 9k
- View details
electron-profileSkillProductivity
Lets your agent analyze Chrome performance traces to find slow renders, long tasks, and where CPU time goes.
Ready to connect★ 9k
- View details
gamified-appSkillProductivity
Lets your agent build a three-screen gamified task app with XP points, a dark stage look, and task detail views.
Ready to connect★ 9k
- View details
hr-onboardingSkillProductivity
Lets your agent generate first-week onboarding plans with buddy pairing, learning paths, equipment lists, and completion criteria.
Ready to connect★ 9k
- View details
no-mistakesSkillProductivity
Validate your code changes through the no-mistakes pipeline - automated code review, tests, lint, docs, push, PR, and CI - before they reach the configured push target. Use when the user asks to run no-mistakes, gate or ship or validate their changes, push safely, asks you to do a task and then vali
Ready to connect★ 8k
- View details
gog-calendarSkillProductivity
Lets your agent view and manage Google Calendar events.
Ready to connect★ 8k
- View details
gog-tasksSkillProductivity
Lets your agent create, update, and manage tasks on your Google Tasks lists.
Ready to connect★ 8k
- View details
ccpmSkillProductivity
Lets your agent turn feature plans into PRDs, GitHub issues, and parallel work, then track status and standups.
Ready to connect★ 8k
- View details
orchardcore-workflow-activitySkillProductivity
Lets your agent create custom OrchardCore workflow tasks and events with their editor UI and data handling.
Ready to connect★ 8k
- View details
subagent-driven-developmentSkillProductivity
Lets your agent break an implementation plan into independent tasks and run each one via subagents.
Ready to connect★ 8k
- View details
writing-plansSkillProductivity
Guides your agent to write a step-by-step implementation plan from a spec before coding.
Ready to connect★ 8k
- View details
skill-doli-test-interactiveSkillProductivity
Create interactive PHP test case scripts for Dolibarr ERP/CRM that allow users to setup test data, view results via direct links, and tear down (clean up) the data. Use when asked to create test data for Dolibarr issues or when users need to verify bug fixes in the web interface.
Ready to connect★ 8k
- View details
skill-doli-test-phpunitSkillProductivity
Creates or modify PHP unit tests for Dolibarr ERP/CRM functions and methods. Use when the user asks to add, write, create, or complete a PHPUnit test for Dolibarr, or mentions testing a specific function, method, or class in the Dolibarr codebase.
Ready to connect★ 8k
- View details
reflySkillProductivity
Lets your agent create, find, and run task-specific skills and multi-step workflows for you.
Ready to connect★ 8k
- View details
goal-promptSkillProductivity
Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex.
Ready to connect★ 7k
- View details
slicing-code-contextSkillProductivity
Lets your agent extract focused slices of code and hand small analysis or patch tasks to a lighter subagent.
Ready to connect★ 7k
- View details
user-story-mappingSkillProductivity
Lets your agent build a user story map organizing activities, steps, and tasks into release slices.
Ready to connect★ 7k
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.