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: Dev tools
16,833 results · page 88 of 562
- View details
speckit-constitutionSkillDev tools
Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.
Ready to connect★ 1k
- View details
speckit-git-featureSkillDev tools
Create a feature branch with sequential or timestamp numbering
Ready to connect★ 1k
- View details
speckit-specifySkillDev tools
Create or update the feature specification from a natural language feature description.
Ready to connect★ 1k
- View details
test-skillSkillDev tools
A test skill for unit testing the Atmos skill marketplace functionality
Ready to connect★ 1k
- View details
creative-thinking-for-researchSkillDev tools
Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.
Ready to connect★ 1k
- View details
nanoresearch-experimentSkillDev tools
Generate a Python code skeleton from an experiment blueprint
Ready to connect★ 1k
- View details
nanoresearch-planningSkillDev tools
Produce an experiment blueprint from a research hypothesis
Ready to connect★ 1k
- View details
nanoresearch-writingSkillDev tools
Draft a LaTeX research paper from all previous stage outputs
Ready to connect★ 1k
- View details
react-startSkillDev tools
React bindings for TanStack Start: createStart, StartClient, StartServer, React-specific imports, re-exports from @tanstack/react-router, full project setup with React, useServerFn hook.
Ready to connect★ 1k
- View details
router-core/data-loadingSkillDev tools
Route loader option, loaderDeps for cache keys, staleTime/gcTime/ defaultPreloadStaleTime SWR caching, pendingComponent/pendingMs/ pendingMinMs, errorComponent/onError/onCatch, beforeLoad, router context and createRootRouteWithContext DI pattern, router.invalidate, Await component, deferred data loa
Ready to connect★ 1k
- View details
router-core/not-found-and-errorsSkillDev tools
notFound() function, notFoundComponent, defaultNotFoundComponent, notFoundMode (fuzzy/root), errorComponent, CatchBoundary, CatchNotFound, isNotFound, NotFoundRoute (deprecated), route masking (mask option, createRouteMask, unmaskOnReload).
Ready to connect★ 1k
- View details
router-core/path-paramsSkillDev tools
Dynamic path segments ($paramName), splat routes ($ / _splat), optional params ({-$paramName}), prefix/suffix patterns ({$param}.ext), useParams, params.parse/stringify, pathParamsAllowedCharacters, i18n locale patterns.
Ready to connect★ 1k
- View details
router-core/ssrSkillDev tools
Non-streaming and streaming SSR, RouterClient/RouterServer, renderRouterToString/renderRouterToStream, createRequestHandler, defaultRenderHandler/defaultStreamHandler, HeadContent/Scripts components, head route option (meta/links/styles/scripts), ScriptOnce, automatic loader dehydration/hydration, m
Ready to connect★ 1k
- View details
router-pluginSkillDev tools
TanStack Router bundler plugin for route generation and automatic code splitting. Supports Vite, Webpack, Rspack, and esbuild. Configures autoCodeSplitting, routesDirectory, target framework, and code split groupings.
Ready to connect★ 1k
- View details
start-core/middlewareSkillDev tools
createMiddleware, request middleware (.server only), server function middleware (.client + .server), context passing via next({ context }), sendContext for client-server transfer, global middleware via createStart in src/start.ts, middleware factories, method order enforcement, fetch override preced
Ready to connect★ 1k
- View details
buildSkillDev tools
Build clice. Optional arg = build type (Debug | RelWithDebInfo, default RelWithDebInfo). Runs in a forked context — compile output and mechanical fixes stay out of the main conversation; only the outcome returns.
Ready to connect★ 1k
- View details
resolve-commentsSkillDev tools
Pull unresolved review threads of the current PR, apply the fixes in the worktree, resolve the threads, and return a compact summary. Runs inline; the digest script keeps the bot boilerplate out of the conversation.
Ready to connect★ 1k
- View details
upgrade-llvmSkillDev tools
Complete workflow for upgrading the prebuilt LLVM packages clice depends on — build-llvm CI, API adaptation, release-llvm pruning, changelog. Arg = target version, e.g. 22.1.4.
Ready to connect★ 1k
- View details
thinking-circle-of-competenceSkillDev tools
Use when a specific claim may lack grounding. Check evidence boundary, size wrongness cost, then answer, fetch, or abstain — never confabulate.
Ready to connect★ 1k
- View details
thinking-cynefinSkillDev tools
When the right response mode is unclear, classify the cause-effect domain first; decompose disorder.
Ready to connect★ 1k
- View details
thinking-effectuationSkillDev tools
Under genuine uncertainty with no reliable forecast, inventory means, cap downside at affordable loss, act for commitments, and let goals emerge from controllable moves.
Ready to connect★ 1k
- View details
thinking-first-principlesSkillDev tools
When a constraint is treated as fixed, separate physics from convention, keep only independently supported primitives, and rebuild the simplest solution that satisfies real constraints.
Ready to connect★ 1k
- View details
thinking-five-whys-plusSkillDev tools
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.
Ready to connect★ 1k
- View details
thinking-jobs-to-be-doneSkillDev tools
Deciding what to build or why adoption fails. Recover the progress users hire a solution for under a circumstance, then rank by outcome and competing workarounds.
Ready to connect★ 1k
- View details
thinking-kepner-tregoeSkillDev tools
Use when a selective defect needs IS/IS-NOT difference analysis or a consequential option choice needs must/want weighting and adverse-consequence comparison.
Ready to connect★ 1k
- View details
thinking-lindy-effectSkillDev tools
Use when longevity of a non-perishable option matters. Treat survival duration as a remaining-life prior, then check domain drift before favoring the proven.
Ready to connect★ 1k
- View details
thinking-margin-of-safetySkillDev tools
When provisioning, setting a limit, or committing an estimate under uncertainty, size a buffer to residual error and the cost of breach—not to the optimistic edge.
Ready to connect★ 1k
- View details
thinking-oodaSkillDev tools
Use under time pressure when the situation is still changing and you must act before certainty — cycle Observe→Orient→Decide→Act on ~70% confidence, then re-observe.
Ready to connect★ 1k
- View details
thinking-opportunity-costSkillDev tools
Before committing scarce time, people, or money, name the best forgone use of those resources and the value delta of the chosen path versus that alternative.
Ready to connect★ 1k
- View details
thinking-pre-mortemSkillDev tools
Before committing to a plan or launch, assume it already failed and reason backward through concrete causes — convert failure paths into mitigations, gates, and stop checks.
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.
53,585 of the 54,017 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.