kevin-liu-01
- 163 skills
- 0 followers
- 1 day ago last updated
- ▌ Hotfix Preview · kevin-liu-01Cherry-pick a commit from dev onto preview without a PR. Use when you need to cherry-pick a fix to preview without a PR, or for urgent fixes that can't wait for a full promote cycle.
- ▌ Rust Neckbeard · kevin-liu-01Dedalus Rust correctness and style rules. Use when writing, reviewing, or refactoring any Rust code in the host-agent, enclave, or packages/rust workspaces. Covers return-value naming, error design, must_use, visibility, RAII, fail-closed, and all hard limits from style.md and rust.mdx.
- ▌ Security Audit · kevin-liu-01CTF-style security and correctness audit. Use when the user asks for a security review, before deploying user-facing services, or when reviewing auth, payments, or anything that touches secrets.
- ▌ Social Content · kevin-liu-01Social media content creation, scheduling, repurposing, and optimization across LinkedIn, X, Instagram, TikTok, and Facebook. Use when creating social posts, repurposing content across platforms, building engagement routines, analyzing social performance, or when the user says "social content", "social media", "repurpose", "schedule posts", "engagement strategy", or "content calendar." Based on coreyhaines31/marketingskills (40K weekly installs). For Kevin-specific positioning and quality gates, also read content-strategy and social-draft skills.
- ▌ Brandkit · kevin-liu-01Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts. Use when the user says "brand kit", "brand guidelines", "logo system", "identity deck", "visual world", "brand board", or wants to generate brand identity images.
- ▌ Redesign Existing Projects · kevin-liu-01Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS. Use when the user says "redesign", "upgrade design", "improve existing UI", "make this look better", "fix generic design", or wants to elevate an existing project's visual quality.
- ▌ Reticle Aesthetic · kevin-liu-01Build landing page sections, hero blocks, and marketing surfaces in the Reticle/Sigil engineering-instrument-grid aesthetic. Use when creating new landing sections, hero components, marketing pages, or when the user says "reticle", "hero", "landing page", "new section", "instrument panel", "grid cell", or wants to match the existing Agent Machines visual language.
- ▌ Automation Cron · kevin-liu-01Schedule recurring agent tasks with the cronjob tool. Use when the user wants something to run on a schedule, when you finish a task that should recur, or when planning daily/weekly automations.
- ▌ Commit And Push · kevin-liu-01Stage, commit, and push changes without opening a PR. Use when the user says "commit and push", "commit these to a new branch", "push this branch", or wants a branch + commit summary but does not want PR creation. Distinct from `yeet`, which owns the commit + push + PR flow.
- ▌ Frontend Design · kevin-liu-01Distinctive, production-grade frontend interfaces that reject generic AI aesthetics. Use when creating UI components, landing pages, design systems, or any frontend work. Triggers on "make it look good", "design direction", "avoid generic", "art direction", "design taste", "landing page", "UI design", or any frontend creation task. Based on anthropics/skills (259K weekly installs).
- ▌ Loading Screens · kevin-liu-01Implement loading states using braille Unicode spinners and skeleton placeholders. Use when adding loading indicators, replacing spinners, or building new loading screens. Covers component API, sizing, spinner selection, and anti-patterns.
- ▌ Read And Review · kevin-liu-01Read external reference material (RFDs, papers, blog posts, docs), extract actionable rules, then dispatch subagents to audit the codebase against those rules and fix violations. Use when the user shares a technical reference and wants it applied to the codebase.
- ▌ Industrial Brutalist UI · kevin-liu-01Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints. Use when the user says "brutalist", "mechanical UI", "terminal aesthetic", "declassified", "industrial UI", "tactical", or wants raw, utilitarian interface design.
- ▌ Content Strategy · kevin-liu-01Comprehensive self-promotion and content strategy covering positioning arcs, content calendars, weekly rhythms, and quality gates for X and LinkedIn. Use when planning content, discussing personal brand, building a content calendar, or when the user says "content strategy", "what should I post", "content plan", or "social strategy."
- ▌ Dedalus Machines · kevin-liu-01How Agent Machines work -- providers (Dedalus, E2B, Sprites), agent runtimes (Hermes, OpenClaw, Claude Code, Codex), MCP catalog, bootstrap, and closed-loop verification. Use when asked about the runtime, scaling, sleep/wake, destroy, or inspecting this environment.
- ▌ Plan Mode Review · kevin-liu-01Structured review checklist before implementing changes. Use when planning a feature, before opening a PR, or when the user shares code that needs scrutiny across architecture, code quality, tests, and performance.
- ▌ Project Briefing · kevin-liu-01Generate an executive briefing of the last 24 hours of commits for the current project or a specified directory. Use when the user asks for a project update, daily briefing, commit summary, "what changed today," or wants to stay up-to-date with recent work.
- ▌ Minimalist UI · kevin-liu-01Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows. Use when the user says "minimalist", "editorial style", "warm monochrome", "clean flat", "document-style UI", or wants ultra-minimal workspace-style interfaces.
- ▌ Frontend Frontier · kevin-liu-01Use when the user wants a high-signal frontend, distinctive art direction, strong motion design, 3D/parallax, shader effects, landing pages, docs sites, dashboards, or a tokenized design system that avoids generic AI-generated UI.
- ▌ Og Metadata Audit · kevin-liu-01Audit and fix OpenGraph and Twitter card metadata in Next.js App Router projects. Cross-reference metadata exports across pages, identify missing fields, DRY violations, broken middleware, and incorrect canonicals. Use when Twitter cards aren't rendering, OG images are broken, metadata is inconsistent across pages, or when the user says "audit OG", "fix opengraph", "twitter cards broken", "metadata audit", "OG not working", or "social preview broken".
- ▌ Production Safety · kevin-liu-01Production is sacred. Use when any tool call would touch production databases, infrastructure, or SSM parameters -- refuse and route the change through the migration pipeline instead.
- ▌ State Machine Dfa · kevin-liu-01Document state machines with mermaid diagrams and DFA transition files. Use when writing, reviewing, or adding state-driven logic to modules that have sequential phase transitions, lifecycle management, or protocol handshakes.
- ▌ X Bookmark Absorb · kevin-liu-01Deep absorption of X bookmarks into the wiki graph. Goes beyond hub-page entries to create dedicated pages, cross-references, resolver updates, and index entries. Use when Kevin says "absorb bookmarks", "process bookmarks", "bookmark absorption", "sync bookmarks to wiki", or when running the source-compile automation on x-bookmarks data. Also triggers after any `ft sync` / `sync-x-bookmarks.sh` run.
- ▌ Agent Activity Log · kevin-liu-01Bootstrap and maintain a persistent agent memory file (memory.md) in any project. Use when setting up a new project for agent-assisted development, when the user says "add memory", "activity log", "agent memory", "track changes", "memory.md", "set up agent logging", or when starting work on any project that doesn't already have a memory.md. Also triggers on "what did I do last session" or "what's the history of this project."
- ▌ Cross Modal Review · kevin-liu-01Quality gate via a second AI model. Spawn a different model to review work before committing. Grades against the originating skill's Contract. Use when you want a second opinion from a different model, or the user says "second opinion", "cross-modal review", "double check this", or "get another perspective".
- ▌ Daily Bugfix Check · kevin-liu-01Check the current author's commits from the last 24 hours and proactively find and fix any bugs they introduced. Use when the user asks for a daily bugfix check, wants to review today's commits for issues, or asks to "check my recent code for bugs." Combines commit review with the recent-code-bugfix workflow.
- ▌ Doctor Enforcement · kevin-liu-01Auto-run the relevant codebase doctor(s) after large edit sessions or before committing. Detects which subsystems were touched and runs the matching doctor. Use when the agent has completed a significant edit (5+ files), before claiming work is done, or when the user says "run doctors", "health check", "doctor pass", or "check everything."
- ▌ Generate Interface · kevin-liu-01Define or refactor subsystem interfaces into small, explicit contracts with clear ownership, narrow scope, stable semantics, and README-first documentation. Use when designing a new API, collapsing ad hoc module boundaries into a few coherent interfaces, hardening internal contracts, or rewriting subsystem docs so engineers can understand the system by reading README.md files, docstrings, and code only.
- ▌ Recent Code Bugfix · kevin-liu-01Find and fix a bug introduced by the current author within the last week in the current working directory. Use when a user wants a proactive bugfix from their recent changes, when the prompt is empty, or when asked to triage/fix issues caused by their recent commits. Root cause must map directly to the author's own changes.
- ▌ Imagegen Frontend Web · kevin-liu-01Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate. Use when the user says "web design image", "section reference image", "landing page mockup image", "website comp", or wants to generate per-section website design reference images.
- ▌ Image To Code · kevin-liu-01Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop. Use when the user says "image to code", "design to code", "screenshot to code", "implement from image", "match this design", or wants to generate a design image and then implement it as frontend code.
- ▌ CI CD Best Practices · kevin-liu-01Apply Dedalus CI/CD workflow rules for runner placement, Docker build verification, artifact publication, and self-hosted runner orchestration. Use when editing GitHub Actions workflows, Docker build pipelines, deploy jobs, Terraform/ECS/Flux workflows, or self-hosted runner automation.
- ▌ Gstack Design Review · kevin-liu-01Design audit with UX usability tests. 6-phase audit with 80-item checklist and letter grades. Use when the user says "design review", "UX audit", "visual audit", "audit the UI", "how does this site look", or wants a comprehensive design audit with usability testing.
- ▌ SEO Geo Optimization · kevin-liu-01Optimize websites for AI search engines (ChatGPT, Perplexity, Gemini, Copilot, Claude) and traditional search. Covers GEO methods, schema markup, entity engineering, and platform-specific strategies. Use when optimizing for AI citations, implementing schema, running GEO audits, or when the user says "GEO", "AI search", "optimize for ChatGPT", "schema markup", "AI citability", "generative engine optimization", or "optimize for Perplexity." Based on resciencelab/opc-skills.
- ▌ Column Aligned Fields · kevin-liu-01Enforce column-aligned inline comments on dataclass and enum fields. Use when writing or reviewing Python dataclasses, enums, TypedDicts, or any structured type with inline field comments.
- ▌ Frontend Design Taste · kevin-liu-01Build distinctive frontends that avoid generic AI aesthetics. Provides anti-slop enforcement, variance dials, art direction archetypes, creative arsenal, and performance guardrails. Use when creating new landing pages, UI components, design systems, or when the user says "make it look good", "design direction", "avoid generic", "art direction", or "design taste."
- ▌ Reticle Design System · kevin-liu-01Reticle/Sigil design system reference. Use when generating UI for a project that uses this design system -- provides token names, layout primitives (margins, gutters, crosses), typography, and component patterns. Drop in your own design-system skill to replace it.
- ▌ Imagegen Frontend Mobile · kevin-liu-01Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured surfaces, image-led composition, tasteful custom iconography, and clean phone mockup framing. By default, screens should be shown inside a subtle premium iPhone or similar phone mockup with a visible frame, while the main focus stays on the app content itself. This skill generates images only. It does not write code. Use when the user says "mobile app mockup", "app screen concept", "mobile design image", "phone mockup", "app flow image", or wants to generate mobile app screen images without code.
- ▌ Taste Skills Playbook · kevin-liu-01Routing layer for the 13 taste-* design skills. Determines which visual-style skill fires for a given task and which workflow modifiers layer on top. Use when the user asks "which taste skill", "taste routing", "design skill selection", or when you need to decide between taste-soft, taste-minimalist, taste-brutalist, taste-gpt, or any other taste-* variant.
- ▌ Web Design Guidelines · kevin-liu-01Audit UI code against Vercel's Web Interface Guidelines for design and accessibility compliance. Use when reviewing UI code, checking accessibility, auditing components, or when the user says "check design", "UI review", "accessibility audit", "web guidelines", or "interface compliance." Based on vercel-labs/agent-skills (234K weekly installs).
- ▌ Empirical Verification · kevin-liu-01Scientific method for software. Use when debugging, reviewing surprising behavior, or before claiming code works -- always tether assumptions to reality with a small experiment.
- ▌ Font Switcher Dev Tool · kevin-liu-01Build a floating font selector dev tool for any Next.js app. Copies font files, generates @font-face CSS, creates a FontProvider context with localStorage persistence, and builds a floating selector UI. Use when evaluating candidate typefaces across an app, adding font preview capability, or when the user says "font switcher", "try fonts", "compare fonts", or "add a font selector."
- ▌ Invariant First Coding · kevin-liu-01Reason from proven invariants before coding. Use when reviewing fallback logic, narrowing types, handling conversions, deciding whether an error path is real or impossible, removing overdefensive code, or when the user questions whether code is being too theatrical, too hedged, or not fail-closed enough.
- ▌ Closed Loop Development · kevin-liu-01Use when building, debugging, or verifying software inside an Agent Machine. Teaches the agent to write code, run the service, hit endpoints, inspect logs, drive the browser, and iterate without asking the user to be the test harness.
- ▌ Invariant First Testing · kevin-liu-01Write tests that describe system invariants, not specific bugs. Tests should read like design documentation, not a changelog of failures. Use when writing new tests, reviewing test suites, or refactoring reactive bug-fix tests into invariant-style tests.
- ▌ Stage Refactor Checklist · kevin-liu-01Comprehensive checklist for refactoring a schema_compiler stage folder. Use EVERY TIME you refactor a compiler stage (resolve, unify, codegen, etc.). Read this before writing any code.
- ▌ Stripe Webhook Hardening · kevin-liu-01Harden Stripe webhook handlers against three failure-prone invariants — raw-body signature verification, negative-lifecycle handling, and idempotent side effects. Use when reviewing, implementing, or hardening Stripe webhook routes, or when the user says "stripe webhooks", "webhook hardening", "signature verification", "idempotent webhooks", or "webhook review."
- ▌ Fail Closed Case Matching · kevin-liu-01Dedalus philosophy on conditional logic, error paths, and why we never write fallbacks. Use when writing or reviewing any branching logic that selects between strategies, modes, or error-recovery paths.
- ▌ Vercel React Best Practices · kevin-liu-01React and Next.js performance optimization with 69 prioritized rules across 8 categories. Use when writing React components, implementing data fetching, reviewing code for performance, refactoring React/Next.js code, optimizing bundle size, or when the user says "React performance", "optimize React", "Next.js best practices", "bundle size", or "waterfall." Based on vercel-labs/agent-skills (291K weekly installs).
- ▌ App Onboarding Questionnaire · kevin-liu-01Design and build high-converting questionnaire-style app onboarding flows modelled on proven conversion patterns from top subscription apps (Headspace, Noom, Duolingo). Use when building onboarding flows, sign-up funnels, questionnaire UIs, or conversion-optimized first-run experiences. Triggers on "onboarding flow", "sign-up questionnaire", "first-run experience", "conversion funnel", "paywall flow", "app onboarding", "welcome screen", or "user activation". Based on adamlyttleapps/claude-skill-app-onboarding-questionnaire (374 GitHub stars).
- ▌ Minimal First Implementation · kevin-liu-01Build the smallest correct version first. Name every case, implement only what has a real consumer, return typed errors for the rest. Use when designing new systems, extracting shared packages, or deciding how much to build before shipping.
- ▌ DB · kevin-liu-01Run read-only SQL queries against Supabase databases (local or remote). Use when inspecting schema, debugging data, checking migrations, or answering questions about database state.
- ▌ Pr · kevin-liu-01Create a pull request using the Dedalus PR template. Injects git state, commit history, and diff stats automatically.
- ▌ QA · kevin-liu-01QA lead with real browser testing. Adapted from GStack's /qa (Garry Tan, github.com/garrytan/gstack) for Cursor + agent-browser. Tests your app, finds bugs, fixes them with atomic commits, generates regression tests.
- ▌ Sdk · kevin-liu-01Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor TypeScript SDK (`@cursor/sdk`). Use when the user mentions integrating, installing, or writing code against the Cursor SDK; says `Agent.create`, `Agent.prompt`, `Agent.resume`, `agent.send`, `run.stream`, `CursorAgentError`, or `@cursor/sdk`; asks to run Cursor agents programmatically from a script, CI/CD pipeline, GitHub Action, backend service, or other code outside the Cursor IDE; wants to pick between local and cloud runtime, configure MCP servers for an SDK agent, or handle streaming, cancellation, or errors; or is wiring Cursor into an automation, bot, or REST `/v1/agents` migration. Use eagerly rather than answering from memory; the SDK surface evolves and this skill is the source of truth for the external package.
- ▌ Bugs · kevin-liu-01CTF-style security and correctness audit. Dispatches parallel Opus subagents to hunt for day-0 bugs in security-critical files. Each agent must find a real bug or honestly admit failure. Use when you want a thorough adversarial review of a codebase area.
- ▌ Lerp · kevin-liu-01Audit prose (comments, docs, READMEs, commit messages, PR descriptions) for jargon, unexplained acronyms, and assumed context. Rewrites for the least experienced reader. Use after writing docs, READMEs, or any prose that will be read by someone who did not write the code.
- ▌ Perf · kevin-liu-01Discipline for performance investigations. Ramp up from cheap experiments to expensive ones. Profile before patching. Isolate hypotheses with standalone probes before touching production code. Numbers gate every decision. Use when the user says `/perf`, asks to speed up code, or asks why something is slow.
- ▌ Rtfm · kevin-liu-01Verify claims against primary sources before writing code or docs. Read the actual API, run the actual command, check the actual docs. Do not guess. Do not assume. Do not ship until verified.
- ▌ Issue · kevin-liu-01Create a GitHub issue using the Dedalus issue templates (bug, feature, question). Injects branch and commit context automatically, prompts for Linear link. Use when creating a GitHub issue using Dedalus templates, or the user says "file an issue", "create issue", "open a bug", or "report a feature request".
- ▌ Voice · kevin-liu-01Write third-person, credential-forward bio copy in someone's own voice. Modeled on the "Why?" blurbs Sequoia / curated job platforms generate for founders + engineers. Use whenever the agent needs to describe a real person to a reader (recruiter "Why this candidate" blurbs, LinkedIn headlines + About sections, conference bios, intro requests, cold outreach openers, "tell me about yourself" answers, X/site bios, panel descriptions, app submission profiles, founder intros). Triggers on "write a bio", "intro me", "one-liner", "pitch me", "About section", "candidate blurb", "outreach opener", "describe me", or whenever copy is being authored that represents a person in their own voice.
- ▌ Canvas · kevin-liu-01A Cursor Canvas is a live React app that the user can open beside the chat. You MUST use a canvas when the agent produces a standalone analytical artifact — quantitative analyses, billing investigations, security audits, architecture reviews, data-heavy content, timelines, charts, tables, interactive explorations, repeatable tools, or any response that benefits from visual layout. Especially prefer a canvas when presenting results from MCP tools (Datadog, Databricks, Linear, Sentry, Slack, etc.) where the data is the deliverable — render it in a rich canvas rather than dumping it into a markdown table or code block. If you catch yourself about to write a markdown table, stop and use a canvas instead. You MUST also read this skill whenever you create, edit, or debug any .canvas.tsx file.
- ▌ Commit · kevin-liu-01Create a git commit with conventional commit format. Injects current git state automatically.