zchee

Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries for plugin ordering and availability metadata, or update an existing local plugin during development with the CLI-driven cachebuster and reinstall flow.

Split the current git worktree into one or more meaningful commits with clean staging boundaries and commit hygiene. Use when the user asks to commit current changes, wants related changes grouped into multiple commits, or needs help preparing commit messages without disturbing unrelated local modifications.

Code context using Exa. Finds real snippets and docs from GitHub, StackOverflow, and technical docs. Use when searching for code examples, API syntax, library documentation, or debugging help.

Search for research papers and academic content using Exa advanced search. Full filter support including date ranges and text filtering. Use when searching for academic papers, arXiv preprints, or scientific research.

Guide for creating effective skills. This skill should be used when users want to create, update, review, and debug native Zsh completion scripts built on the modern completion system (`compsys`). Use when Codex needs to create a new `_command` completion function, extend subcommand, option, or argument completion, fix completion parity against a CLI's current help output, migrate legacy `compctl` behavior to `#compdef` or `compdef`, or diagnose matcher, style, tag, or context issues in existing Zsh completion code.

Code context using Exa. Finds real snippets and docs from GitHub, StackOverflow, and technical docs. Use when searching for code examples, API syntax, library documentation, or debugging help.

[OMX] Run an anti-slop cleanup/refactor/deslop workflow

[OMX] Socratic deep interview with mathematical ambiguity gating before execution

[OMX] Setup and configure oh-my-codex using current CLI behavior

[OMX] Self-referential loop until task completion with architect verification

[OMX] N coordinated agents on shared task list using tmux-based orchestration

[OMX] Create and execute durable repo-native multi-goal plans over Codex goal mode artifacts.

Poll and retrieve Gemini Deep Research runs with the deep_research_result tool of the mcp-gemini-search MCP server. Use this skill whenever a deep_research run has been started and you hold an interaction_id — to check progress, wait for completion, fetch the finished Markdown report with its citations, or re-fetch a report from an earlier session. Also use it when the user asks "is the research done yet?", "get the report", or pastes an interaction_id.

Start an asynchronous Gemini Deep Research run with the deep_research tool of the mcp-gemini-search MCP server — an autonomous agent that searches, reads sources, and writes a long citation-rich Markdown report over several minutes. Use this skill whenever the user wants a comprehensive report, competitive analysis, technology comparison, literature survey, market/landscape overview, or any multi-source investigation — even if they just say "research X thoroughly" or "write me a report on Y". Also read it before ever calling deep_research, because a careless call starts a duplicate billed multi-minute run.

Drive the google_search tool of the mcp-gemini-search MCP server — a Google-Search-grounded Gemini call that returns a Markdown answer with inline [n] citations and a numbered Sources list. Use this skill whenever the user asks to search the web, look up current events, verify a fact against live sources, check the latest version/release/pricing/news of anything, or when any claim needs verifiable citations — even if they never say "search" or "google_search". Also use it to decide when a request should instead go to the deep_research tool.

Add a new LSP server configuration following this repo's patterns. Use when adding support for a new language server.

Add a new lazy.nvim plugin following this repo's patterns. Use when adding a new Neovim plugin.

Regenerate the tree-sitter parser from grammar.js and run corpus tests. Use after editing grammar.js, or whenever src/parser.c may be stale.

Run parser tests across every language binding (node, python, go, rust, zig, swift) and report which passed and failed. Use to verify a grammar change doesn't break any binding's smoke test.

Update the Go pkg/codex SDK in pandaemonium from an upstream OpenAI Codex Rust release tag such as rust-v0.XXX.X. Use when Codex needs to refresh the local codex app-server generated protocol schema, regenerate pkg/llm/codex/protocol_gen.go, preserve generated-code boundaries, port adjacent public API or example changes from upstream Rust/Python Codex releases, and verify package/tests/examples before commit or report.

Use when Codex needs to design, implement, debug, test, or review Language Server Protocol (LSP) clients, servers, middleware, SDK bindings, or editor integrations, including JSON-RPC framing, initialize/shutdown lifecycle, capability negotiation, textDocument/workspace methods, diagnostics, hover, completion, definition, references, formatting, semantic tokens, code actions, file watching, dynamic registration, position/range encoding, URI handling, cancellation, progress, or interoperability with language servers such as gopls, pyright, clangd, rust-analyzer, or TypeScript language services.

Port a source file from the upstream google-antigravity/antigravity-sdk-python SDK into idiomatic Go, then diff the public API surface for parity. Use when adding or updating functionality that mirrors the Python SDK.