Loading...
Loading...
Found 2,804 Skills
Adopt multiple expert personas sequentially for complex problem analysis from diverse perspectives. Single-agent only — do NOT spawn sub-agents.
Deploys a Next.js or Vite project to Vercel, pushes all environment variables from .env.local to production, adds a SPA rewrite rule for Vite, and updates the Supabase site_url to the live domain. Called by the vibe-ship orchestrator.
Use this for SQL queries, database schema design, ETL pipelines, data transformations (pandas/Spark), and data validation.
Use for deep design discovery and problem understanding before planning or implementation. Trigger when the user wants to think deeply, build knowledge, surface edge-cases, ask many questions, or explore the problem space without producing plans or code.
Build native macOS/iOS apps with Apple's Liquid Glass design language and Human Interface Guidelines. Use when creating SwiftUI interfaces, implementing translucent materials, designing cards/rows/badges, applying SF Symbols, following Apple HIG spacing/typography/color systems, or building any app that should feel native to Apple platforms. Triggers on macOS apps, iOS apps, SwiftUI UI, Apple-style design, glass effects, material backgrounds, native app design.
Technical safeguards and architectural patterns for building HIPAA-compliant software on AWS. Use when building healthcare SaaS, handling PHI (Protected Health Information), designing patient data systems, implementing healthcare APIs, setting up HIPAA-eligible AWS infrastructure, reviewing code for PHI exposure, designing audit logging, or when the user mentions patients, medical records, EHR/EMR, health data, HL7, FHIR, or covered entities. Essential for founders and developers building in healthcare or digital health space.
A micro-prompt that reminds the agent that it is an interactive programmer. Works great in Clojure when Copilot has access to the REPL (probably via Backseat Driver). Will work with any system that has a live REPL that the agent can use. Adapt the prompt with any specific reminders in your workflow and/or workspace.
Generate financial analytics and insights from ~/Documents/finances/ data. Terminal report shows: net worth trends (30d/90d/1y), asset allocation, liability table with APR and monthly interest, cash flow (last 30 days), Bitcoin detail with sparkline. HTML dashboard: interactive plotly charts for all of the above over time. Use when: reviewing finances, answering questions about net worth, spending patterns, debt paydown progress, Bitcoin holdings, asset allocation. Keywords: financial report, net worth, spending, cash flow, debt, liabilities, bitcoin, how am I doing financially, finances summary, show me my finances, portfolio.
Progressive context refinement pattern for subagents. Solves the problem of agents not knowing what context they need until they start working. Uses a 4-phase loop: DISPATCH, EVALUATE, REFINE, LOOP.
Inline adversarial plan review — 3 sequential checks (Feasibility, Completeness, Scope & Alignment) performed by the calling LLM in its own context. No subagents spawned. Call after saving a plan. Returns GATE_PASS or GATE_FAIL with blocking issues.
Manage world permissions, namespaces, resource registration, and access control. Use when configuring world ownership, setting up authorization policies, or managing resource permissions.
When the user wants to set up, optimize, or manage TikTok Ads. Also use when the user mentions "TikTok Ads," "TikTok for Business," "TikTok Pixel," "Events API," "TikTok Spark Ads," or "TikTok video ads."