A deliberately small collection of personal Agent Skills.
Stop coding agents from shipping generic UI. Use UIZZE's 800,000+ real web and iOS screens to build product-specific interfaces, define a design contract, cover required states, and run a hard finish gate. Use for web or iOS UI design, implementation, redesign, critique, and pre-ship review in Codex, Claude Code, Cursor, Copilot, and other coding agents.
Build or update an interactive isometric map of a repository's architecture — buildings sized by real measurements, neighborhoods by subsystem, animated flows tracing actual call paths, and a drift counter that fails CI when the map falls behind the code. Use when someone wants to see, explain, or onboard people to how a codebase fits together, or asks for an architecture diagram, system map, codebase overview, or "show me how this repo works". Adapts to the repo's design system; re-run to refresh.
Get a second opinion from Gemini 3.8 Flash High through Antigravity CLI. Use when the user asks for an Antigravity review, asks to consult Flash through Antigravity, or invokes $ask-antigravity.
Get a second opinion from Grok 4.6 at xhigh reasoning through Grok CLI. Use when the user asks for a Grok review, asks to consult Grok, or invokes $ask-grok.
Get a second opinion from Opus with claude -p. Use when the user asks Codex to ask Opus, get Opus's second opinion, consult Opus, or explicitly invokes $ask-opus.
Collect full independent reviews from Opus, Antigravity Flash, and Grok through one Codex coordinator sub-agent. Use when the user asks to ask others, requests these reviewers together, or invokes $ask-others.
Trigger this skill when the user asks to monitor, watch, or babysit an existing pull request, or to handle CI checks, auto-rebasing, and PR review comments.
Run a ChatGPT Pro review on a pull request, wait for the completed review, then verify and address valid findings locally. Use when the user asks for a ChatGPT Pro review of a PR. Do not trigger for an ordinary local or GitHub PR review.
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Remove AI-generated code slop and clean up code style
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
Trigger this skill when the user asks to file, open, or create a new pull request. Do NOT use this skill for monitoring or updating an existing PR.
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Apply a rigorous, evidence-first engineering workflow distilled from pstack. Use when the user invokes $pstack or asks for pstack, poteto-mode, a deep engineering pass, root-cause debugging, verified architecture or refactoring, or a strict evidence-backed judgment of good and bad code.
Turn a completed review or supplied finding list into repository-native problem reports, with one subagent investigating each finding and the parent checking every verdict and file. Use only when explicitly invoked.
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
Comprehensive security and correctness audit of a branch's changes. Use for thermo nuclear, thermonuclear, or deep review requests, or branch/PR diff audits focused on bugs, breaking changes, security issues, devex regressions, and feature-gate leaks.
Launch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug/security and code-quality branch audits.
Cut AI tells from any writing. Must always apply.
Use this skill whenever the requested result depends on a command, job, process, file, service, or external state becoming ready later. Load it before monitoring or checking for completion, including background work, unknown timing, and requests that never explicitly mention waiting.
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.