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
54,680 results · page 141 of 1,823
- View details
issue-root-resolutionSkillDev tools
Lets your agent audit issue clusters and resolve them by verifying the root cause.
Ready to connect★ 7k
- View details
judgment-daySkillDev tools
Runs a blind dual review of your work with up to two rounds of scoped fixes and re-judgment.
Ready to connect★ 7k
- View details
rdd-advisory-transportSkillAI & models
Lets your agent enforce a shared contract for how advisory code reviewers send review requests in Go projects.
Ready to connect★ 7k
- View details
rdd-defect-workflowSkillDev tools
Guides your agent through receipt-driven development workflows with review gates, corrections, and delivery checks.
Ready to connect★ 7k
- View details
sdd-archiveSkillDev tools
Lets your agent close out a finished spec-driven change by merging its spec updates into the main specs and moving the work to the archive.
Ready to connect★ 7k
- View details
sdd-designSkillMedia
Lets your agent write a technical design document outlining how a proposed code change will be implemented.
Ready to connect★ 7k
- View details
sdd-exploreSkillDev tools
Lets your agent explore and clarify change ideas before committing to a spec.
Ready to connect★ 7k
- View details
sdd-initSkillDev tools
Lets your agent set up spec-driven development context, testing, and a persistent project registry.
Ready to connect★ 7k
- View details
sdd-onboardSkillDev tools
Guides your agent through a full spec-driven development cycle on your real codebase, teaching each step as it goes.
Ready to connect★ 7k
- View details
sdd-proposeSkillDev tools
Lets your agent write a structured change proposal with intent, scope, approach, and rollback plan.
Ready to connect★ 7k
- View details
sdd-researchSkillDev tools
Lets your agent research questions using authorized external sources and return findings with cited, auditable evidence.
Ready to connect★ 7k
- View details
sdd-specSkillDev tools
Lets your agent write structured spec documents describing requirements and scenarios for a planned code change.
Ready to connect★ 7k
- View details
sdd-tasksSkillProductivity
Lets your agent turn a software design document into a phased checklist of concrete implementation tasks.
Ready to connect★ 7k
- View details
sdd-verifySkillDev tools
Lets your agent run diagnostics on implemented work—tests, builds, checks—and report honest findings without fixing anything.
Ready to connect★ 7k
- View details
skill-registrySkillDev tools
Lets your agent keep an up-to-date index of available skills, their triggers, and file paths.
Ready to connect★ 7k
- View details
systemic-issue-triageSkillDev tools
Lets your agent triage new bug reports and issue floods by grouping them into root-cause classes instead of one-by-one fixes.
Ready to connect★ 7k
- View details
work-unit-commitsSkillDev tools
Lets your agent split code changes into clean, reviewable commits with tests and docs kept together.
Ready to connect★ 7k
- View details
api-and-typingSkillAI & models
Guides your agent in deciding how to type massCode renderer data from generated API clients.
Ready to connect★ 7k
- View details
architecture-standardsSkillDev tools
Lets your agent follow repo-wide architecture rules, naming conventions, and decomposition boundaries in massCode.
Ready to connect★ 7k
- View details
development-workflowSkillDev tools
Lets your agent follow the massCode repo's development workflow rules for linting, testing, and required follow-up steps.
Ready to connect★ 7k
- View details
DiscoverSkillDev tools
Lets your agent run a structured product discovery flow from problem framing to validation planning.
★ 7k
- View details
documentation-workflowSkillWeb & browsing
Lets your agent write and update massCode documentation, including docs pages, assets, and sidebar.
Ready to connect★ 7k
- View details
electron-api-and-ipcSkillFiles & storage
Lets your agent work on massCode's Electron API routes, IPC handlers, and renderer-to-main communication.
Ready to connect★ 7k
- View details
github-workflowSkillDev tools
Lets your agent manage GitHub issues, branches, commits, pull requests, and prepare merges.
Ready to connect★ 7k
- View details
Leadership TransitionSkillDev tools
Lets your agent plan a product leadership career move with role-fit checks and onboarding advice.
★ 7k
- View details
Plan RoadmapSkillDev tools
Lets your agent turn strategy and validated opportunities into a sequenced product roadmap with clear tradeoffs.
★ 7k
- View details
PrioritizeSkillDev tools
Lets your agent pick what task to work on next using a prioritization method that fits your situation.
★ 7k
- View details
spaces-architectureSkillDocs & knowledge
Lets your agent work with massCode spaces, like code, notes, and math, when changing how they behave or sync.
Ready to connect★ 7k
- View details
StrategySkillDev tools
Lets your agent build product strategy, from positioning through opportunity and roadmap decisions.
★ 7k
- View details
ui-foundationsSkillDev tools
Guides your agent to follow massCode UI rules for typography, TailwindCSS v4, and consistent text styling.
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.
54,249 of the 54,680 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.