Total 59,125 skills
Showing 12 of 59125 skills
Designs original, compact mini-games — rules, controls, scoring, hazards, and difficulty curves — for any input scheme, including one-button (tap / hold / release) games. Use when defining a new mini-game concept, converting creative constraints or seeds into mechanics, choosing an input scheme, checking state-variable necessity, or preventing idle, hold-only, or mashing play from becoming optimal.
Design and create Busabase-backed App-in-Skill packages with a canonical app project, Busabase-native setup and product onboarding, review/execution workflows, a standardized responsive UI, and AirApp-first delivery. Use when a user wants a Busabase research desk, review queue, planner, action console, operating dashboard, control panel, collaboration workspace, onboarding/readiness flow, or an existing Kelly App-based skill updated. Every generated skill contains a complete app/ project, deploys that source to Busabase AirApp by default, runs pnpm dev only when local preview is explicitly requested, follows the Kelly desktop and phone UI contract, delegates AirApp runtime, SDK, security, scaffolding, and deployment constraints to busabase-app-creator, and delegates repository-level conformance testing to kelly-app-skill-creator-tests.
This skill should be used when the user asks to "generate arbitrary values", "generate sample data from a schema", "use Effect Arbitrary", "Schema.toArbitrary", or to produce Effect Schema test data, fixtures, or FastCheck samples.
This skill should be used when the user asks to "write Effect code", "debug Effect code", "use Effect.gen", "create an Effect service", "define Effect Schema models", "compose Layers", "test Effect programs", "build an HttpApi", "look up an Effect API", or works in code importing effect or @effect/*.
Create or decompose workflow skills, dry-run workflows as callstack traces, and model workflows as state machines. Use when asked to design, document, improve, split, trace, simulate, visualize, or diagram a workflow, procedure, algorithm, function, or skill.
Create and improve plans as testable forecasts with explicit outcomes, probabilities, assumptions, evidence checkpoints, trigger rules, and calibration. Use when creating, reviewing, stress-testing, or updating a plan, estimate, roadmap, project proposal, or strategy.
Set up the Better TypeScript linter in Node.js/npm or Bun TypeScript projects, including single-package repositories and monorepos. Use when asked to add, install, configure, or create a lint script for @better-typescript/better-typescript.
Plan the smallest complete happy-path change or implement an approved happy-path plan. Use when asked to plan or implement a feature, change, or bug fix for only the normal valid path.
Build and operate a persistent, Git-backed Markdown wiki that an LLM maintains from immutable source documents. Use when creating, ingesting into, querying, linting, or compacting an LLM-maintained wiki or knowledge base.
Apply established software laws as context-aware guidance for planning, architecture, implementation, delivery, and review. Use when making software tradeoffs, assessing project risks, choosing designs, reviewing code or APIs, estimating work, or evaluating engineering practices.
Turn user stories into @effect/vitest Arbitrary tests plus exact proposed Effect Schemas, Errors, Services, and function signatures. Use when a human wants to review, run, edit, and agree on those contracts before implementation.
Manage an AI-agent project from request through decomposition, preparation, routing, execution, monitoring, review, and closure using durable task records. Use when asked to manage, coordinate, run, or track a multi-task project.