メニュー
Internal guidance for presenting Grok helper output back to the user
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Run a multi-angle Grok analysis in a single call — Grok analyzes the task from several expert angles (security, review, research, tests) and synthesizes one consolidated answer with a section per angle plus a verdict. Use when the user wants a thorough, multi-perspective audit/review/analysis of something ("find everything wrong with…", "review this from all angles", "deep multi-angle look at…") that benefits from more coverage than a single-shot question. Read-only by default.
Ask xAI Grok a one-off question with optional live web search. Use when the user wants Grok's opinion or a quick answer that benefits from Grok's distinct training (recent web/X awareness, code-focused models). Read-only by default. Returns Grok's stdout verbatim.
Deep research with xAI Grok using effort=max, live web search, and Grok's self-verification --check loop. Use when the user wants a thorough investigation of a topic, recent events, or claims that need source-grounding. Returns Grok's research output verbatim.
Delegate a long-form coding task, root-cause investigation, multi-file refactor, or open-ended fix to xAI Grok via the companion's `task` subcommand. Use when the work is too large or specialized to handle inline and benefits from Grok's distinct training (live web search, code-focused models, 512K context).
Generate an image from a text description using xAI Grok's `/imagine` builtin. Use when the user asks for an image, picture, illustration, logo, mockup, or visual artifact. Returns the absolute path to the saved image plus an `open` command to view it.
Internal helper contract for calling the grok-companion runtime from Claude Code
| name | grok-result-handling |
| description | Internal guidance for presenting Grok helper output back to the user |
| user-invocable | false |
Use this skill from inside the slash commands and the grok:grok-rescue subagent when forwarding the companion's stdout to the user.
Almost everything that comes out of node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" <sub> should be passed through to the user unchanged. The reasons:
The verbatim rule applies to:
/grok:ask — answer text from Grok./grok:review and /grok:adversarial-review — review findings, including JSON when --json is set./grok:rescue — the rescue task output./grok:result — the stored output of a finished job.Augment, do not replace, the verbatim output with these structural cues when they appear in stdout or stderr:
[hint: ...] line on stderr means the companion classified an authentication failure. Show the hint and remind the user to run /grok:setup.[grok-plugin] Job <id> ... line gives a follow-up handle. Keep it so the user can run /grok:status <id> or /grok:result <id>.[grok-plugin] Session: <id> (resume: grok -r <id>) line is a resumption handle for the underlying Grok thread. Keep it visible; some users will want to drop down into the raw grok -r <id> flow later.--output-format json payload (the companion already extracts the user-facing text)./grok:cancel or /grok:purge on the user's behalf without explicit instruction.If the companion exits non-zero or prints a Grok error: line:
[hint: ...] line is also present, surface that next.124 specifically means timeout — surface the timeout duration and the --timeout 0 escape hatch the companion already prints, but do not silently retry with a longer timeout.