القائمة
Use when the user runs /claudex:setup or asks to install/bootstrap claudex's dependencies (the Codex plugin and superpowers). Installs both plugins, then verifies the Codex CLI via codex:setup.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Turn an approved spec into a merged-ready PR with Codex doing the writing. Claude conducts; Codex writes the plan and the implementation; a Codex reviewer and a Claude reviewer independently attack each artifact; a fresh Codex agent reconciles them into one verdict (go / fix-go / fix-review). Use when the user runs /claudex:build, or asks to build/implement an existing spec with Codex as the builder and an adversarial review loop.
Deep, multi-source, fact-checked research reports — entirely on the Claude subscription, no API keys. Plans a TOC + acceptance criteria, fans out parallel Task subagents that search the live web (native WebSearch/WebFetch), gap-fills weak sections, then synthesizes a long-form report with inline [n] citations and a Sources list whose every URL is DETERMINISTICALLY verified against URLs that actually appeared in search results (fabricated citations are dropped). A subscription-only port of NVIDIA AI-Q's deep-research core. Use when the user wants a thorough researched report, a literature/landscape/market scan, a cited comparison, or "deep research" / "research X for me". BEFORE invoking, if the question is underspecified (e.g. "what car should I buy" with no budget/use/region), ask 2-3 clarifying questions to narrow scope, then research the refined question.
Brainstorm a feature or design with an automatic Codex second opinion on every clarifying question. Use when the user runs /claudex:think, or asks for Claude+Codex collaborative brainstorming. Wraps superpowers:brainstorming.
Dual-model deep research with adversarial cross-audit. Claude and Codex each run their own deep-research skill independently on the same question, then each audits the OTHER's citations (claim-support: PASS/WEAK/FAIL → trust-score + verdict), and Codex synthesizes one trust-weighted final report with a disagreement ledger. All 5 notes (2 reports, 2 audits, 1 final) + an index land in a persistent Obsidian-style vault; the main session returns a concise bullet summary. Use for high-stakes questions, when the user wants dual-model / cross-verified research, or when a prior deep-research run came back mixed / unreliable. For ordinary research, use claudex:deep-research instead.
Broadcast the current brainstorm question plus a short context snapshot to a configured panel by email (SEND-ONLY), so people can read it on their own device during a screen-shared meeting and reply by email or aloud. Use when the user runs /claudex:email, or asks to "email the panel", "send this question to the panel", or "broadcast this to the panel". Reads recipients from ~/.claude/claudex/panel.json. Does not collect replies and does not modify claudex:think.
| name | setup |
| description | Use when the user runs /claudex:setup or asks to install/bootstrap claudex's dependencies (the Codex plugin and superpowers). Installs both plugins, then verifies the Codex CLI via codex:setup. |
claudex's /claudex:think needs two other plugins: the Codex plugin
(openai/codex-plugin-cc, for the Codex
runtime) and superpowers (anthropics/claude-plugins-official,
for the brainstorming flow). This skill installs both, then runs the Codex CLI check.
This skill depends only on the claude CLI and Bash, so it works even before either
dependency exists. Every step is idempotent — re-running /claudex:setup is safe
and resumes cleanly.
Install both plugins first, so the user reloads once — only then is
codex:setup invokable, and you run it last.
1. install codex plugin (CLI, no reload needed yet)
2. install superpowers (CLI, no reload needed yet)
3. ONE reload gate (user runs /reload-plugins → both go live)
4. invoke codex:setup (now available; verifies the Codex CLI)
Check first, then add the marketplace and install only if missing:
claude plugin marketplace list 2>/dev/null | grep -q openai-codex \
|| claude plugin marketplace add openai/codex-plugin-cc
claude plugin list 2>/dev/null | grep -q 'codex@' \
|| claude plugin install codex@openai-codex
claude plugin marketplace list 2>/dev/null | grep -q claude-plugins-official \
|| claude plugin marketplace add anthropics/claude-plugins-official
claude plugin list 2>/dev/null | grep -q 'superpowers@' \
|| claude plugin install superpowers@claude-plugins-official
If a marketplace add fails (e.g. no network), report it and stop — the install
in that step can't succeed. The two plugins are independent, so a failure on one
doesn't invalidate the other.
Plugins installed via the CLI are not live in the running session — their skills
(like codex:setup) aren't invokable until a reload. Check whether codex:setup is
available to you now:
/reload-plugins (or restart Claude Code) once, then re-run /claudex:setup to
finish — it'll skip the already-installed plugins and run the Codex CLI check."
Then stop. The idempotent checks in steps 1–2 make the re-run cheap.Invoke codex:setup (via the Skill tool). It checks the local Codex CLI, offers to
npm install -g @openai/codex if missing, and prints !codex login guidance if the
CLI is installed but not authenticated. Present its output to the user.
Run claude plugin list and confirm claudex, codex, and superpowers are all
enabled. Report the final state. /claudex:think is now ready to use.
user scope. Pass --scope project to the
install commands if the user wants the deps tied to this project instead.~/.claude directly to fake plugin state — let the CLI manage it.