dots

Audit AI-generated, AI-shaped, or AI-looking frontend code, UI screenshots, and design diffs. Use for prompts like "audit AI frontend", "de-slop UI", "componentize this screen", "parameterize this React/Tailwind/shadcn UI", "make it responsive/accessible", or "review design-system drift"; check component APIs, reusable props/data models, modular composition, shared primitives/tokens, responsive resilience, accessibility, copy quality, hard-coded fixture screens, one-off CSS piles, and generic cards/gradients/fonts.

Create and manage simple heartbeat automations attached to the current Codex thread. Use when Jason invokes $loop or asks this thread to keep going, check again, follow up, retry, monitor, or resume on a recurring cadence.

Design, critique, set, create, activate, or run durable Codex goals for persistent or long-running objectives. Use when the user says "set a goal", "start a goal", "activate goal mode", "persistent goal", "long-running objective", "goal tree", or asks for a goal with verifiers, durable state, approval gates, completion proof, bounded delegation, or parent/child subagent goals.

Audit, de-slop, parameterize, modularize, or safely clean up AI-generated or AI-shaped backend/general code. Use for Python, TypeScript, or other implementation diffs that may contain duplicate helpers, fixture hacks, hard-coded test data, over-defensive control flow, broad exception wrappers, config-bag or boolean-mode soup, speculative scaffolding, hallucinated APIs/dependencies, local-idiom drift, brittle tests, or maintainability/safety/performance gaps after a feature, bugfix, prototype, or agent pass.

Audit pasted chatbot output, AI-cleanup diffs, wiki drafts, Markdown/MDX/docs, and source-backed articles for generic AI fluff, LLM writing tells, weak audience model, lack of theory of mind, inflated significance, vague attribution, leaked tokens, placeholders, broken markup, fabricated or mismatched citations, and detector false positives. Use for requests like "AI writing audit", "check for AI slop", "find writing fluff", "does this sound like ChatGPT", "cleanup LLM tells", "make this less generic", "verify these citations", "detector flagged this", or text containing turn0search0, oaicite, oai_citation, contentReference, utm_source=chatgpt.com, malformed references, or wrong target-format markup.

Draft, rewrite, critique, or learn from emails in Jason Liu's personal email voice. Use when Jason asks to write an email, reply, follow-up, escalation, intro, scheduling note, vendor/admin message, investor/networking response, assistant delegation, analyze sent mail, update email personas, or produce any outbound Gmail-style message "as me", "in my voice", "like I write", or with Jason's tone/persona. For another person's voice, do not reuse this skill; prompt them to sample their own sent Gmail/Slack/work messages with permission and create a separate like-me skill.

Organize, audit, rename, archive, or sync Jason Liu's Downloads and Desktop with a plan-first file cleanup workflow. Use for cleanup plans, plan-only file organizer runs, vague filename review, duplicate review, delete/trash candidates, moving durable documents into ~/Documents, mirroring important files to Google Drive, and writing cleanup logs under ~/Downloads/.cleanup_logs after explicit approval.

Write, rewrite, critique, or reply on Twitter/X in Jason Liu's (@jxnlco) personal voice. Trigger for requests like "tweet like me", "write this in my style", "make this sound like Jason", "draft a reply", or when Jason asks for Twitter copy about Codex, product building, feedback, launches, quote-tweets, or operator/value takes. For another person's social voice, do not reuse this skill; prompt them to sample their own tweets plus sent Slack/email with permission and create a separate like-me skill.

Build or refine single-file information-first HTML artifacts, especially index.html or text.html pages, with strong information hierarchy, restrained styling, accessible semantics, and minimal AI-generated frontend tells. Use when creating static HTML reports, research pages, explainers, briefs, dashboards, note indexes, or simple front ends whose goal is comprehension rather than marketing conversion.

Help address review/issue comments on the open GitHub PR for the current branch using `oai_gh` or `gh`; verify auth first and prompt the user to authenticate if not logged in.

Review git changes and split them into semantic commits with clear messages. Use when the user asks to commit work, clean up local history, or group a mixed diff into logical commits. Do not commit on main or master unless the user explicitly asks.

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `oai_gh` or `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).

Create or edit Slidev presentations in the /Users/jasonliu/dev/presentations repo. Use for drafting new decks, editing existing slides, applying repo-specific Slidev conventions, and polishing/animation work. Triggers: Slidev slide requests, layout/components usage, deck setup, or presentation workflow guidance for this repo.

Codex-specific, session-driven self-improvement for Codex behavior and project instructions. Use when the user asks to inspect past Codex sessions, run a "dream" pass over prior interactions, mine repeated user corrections/preferences, improve or draft skills, update repo/project `AGENTS.md` guidance, or propose durable edits to global `~/.codex/AGENTS.md`.