tyler-skills

Plugin tyler-skills in tylergibbs1/tyler-skills. Commands read from the repo's manifest — 2 days ago.

Skills (13)

• creating-aws-architecture-diagrams

  Creates precise, modern AWS architecture diagrams as PNGs or Mermaid, grounded in source code, infrastructure code, and current AWS guidance. Use when a user asks for an AWS architecture diagram, cloud topology, runtime or deployment view, failure or recovery flow, AWS service visualization, impleme

• linear-design-principles

  Applies Linear's UI/UX and product philosophy (design as product judgment, not decoration) when designing, building, or reviewing interfaces and making product decisions. Use when framing a product problem, planning a redesign, deciding scope, reducing visual noise, designing AI/agent interfaces, de

• mirroring-layout-in-loading-states

  Make every loading state structurally match its own route's real content so there is zero perceived layout shift. Use when building or reviewing any loading.tsx, skeleton, Suspense fallback, or first-sync/import progress UI. Covers per-route fidelity, accessibility, and never showing "done" or stale

• grounding-with-context7

  Ground any work with a library, framework, or SDK in current docs via Context7 MCP instead of training data. Use when writing or changing code that touches a package, when verifying existing usage is correct, when auditing whether a tool is being fully leveraged, and when the user says "use context7

• learning-from-exemplar-repos

  Ground implementation work in a high-quality reference repo instead of inventing patterns from scratch. Use when starting work in a framework (TanStack Start, Effect-TS, Next.js) or going for a specific design/style, when the user says "look at how X does it", "use Y as a reference", "match this rep

• researching-latent-demand

  Decide what to build from real pain and market research, not guesses. Use when the user asks for feature ideas, "what to build next", "wow factor", latent demand, a roadmap, or a competitive gap analysis. Covers researching real pain, the painkiller-not-vitamin test, competitor gap-mapping, and fili

• scientific-literature-discovery

  Find hidden connections, conflicting findings, and falsifiable hypotheses across scientific papers. Use when asked to discover research ideas from literature, connect different scientific fields, investigate inconsistent studies, identify unexplored mechanisms, or design experiments to test literatu

• wcml

  Runs machine-learning work the way world-class ML research teams do - a trusted evaluation, error review by eye, ceilings before methods, one variable per experiment with a control and a pre-written kill line, fast proxies, few deep bets, and a ledger of every result. Use when the user says "wcml",

• orchestrating-subagents

  Orchestrate a multi-agent implementation: decompose a task, fan out subagents to implement each piece in parallel, and brief each one with the context it needs plus a mandate to pull fresh docs via Context7. Use when the user wants to "use subagents", "fan out", "parallelize implementation", "orches

• shipping-pr-reviews

  Push the current changes to a pull request, then launch a dynamic workflow that reviews the PR diff, adversarially verifies each finding, and fixes the confirmed ones, pushing the fixes back to the PR. Use when the user wants to "push to a PR and review", "open a PR then review and fix findings", "s

• cold-emailing

  Writes cold emails and DMs a stranger will read and answer. Short, opened on the reader, one proof, one small question, in the sender's own voice. Use when writing, editing, sending, or following up on any cold outreach (job search, sales, partnerships, fundraising, press), or when deciding who to r

• human-sounding-copy

  Makes writing read as a specific human wrote it, not a model. Cuts AI verbosity, strips lexical and formatting tells, and rebuilds with the craft techniques (cohesion, rhythm, concreteness, stakes, idiolect) that AI text most reliably lacks. Use when writing or editing any prose, UI copy, headings,

• lulu-comms

  Applies Lulu Cheng Meservey's communications operating system (go direct, narrative alpha) to copywriting, mission, branding, and PR. Use when writing launch or fundraising announcements, media pitches, founder posts, crisis comms, apologies, mission statements, or positioning, or when deciding comm