Grok

xAI Grok second opinion via the grok CLI — three modes. Review: independent diff review with a pass/fail gate. Challenge: adversarial pass that tries to break the code. Consult: ask Grok anything, with session continuity for follow-ups. Use when the user says "grok review", "grok challenge", "ask grok", or wants a second opinion from Grok.

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add bolasblack/claude-skills --skill grok
Manual install
git clone --depth 1 https://github.com/bolasblack/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/grok ~/.claude/skills/grok

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# /grok — Second Opinion (xAI Grok)

Grok is the outside voice: an independent AI system with no stake in the plan, reviewing with fresh eyes. Direct, terse, maximally truth-seeking — no compliments, just problems. Present its output verbatim, never summarized.

## Step 0: Preflight

```bash
command -v grok >/dev/null && echo "FOUND: $(command -v grok)" || echo "NOT_FOUND"
python3 "<this skill folder>/scripts/run-with-timeout.py" 30 grok models 2>&1 | head -3
_ROOT=$(git rev-parse --show-toplevel 2>/dev/null)
if [ -z "$_ROOT" ]; then echo "ROOT: NONE"; echo "BASE: NONE"; else
  _BASE=$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null | sed 's|^origin/||')
  [ -n "$_BASE" ] || _BASE=$(git rev-parse -q --verify origin/main >/dev/null 2>&1 && echo main || echo master)
  case "$_BASE" in *[!A-Za-z0-9./_-]*) _BASE=UNRESOLVED;; esac
  echo "ROOT: $_ROOT"; echo "BASE: $_BASE"
fi
```

- `NOT_FOUND` → stop: "Grok CLI not found. Install it from x.ai, then run `grok login` (`grok login --device-auth` on headless machines)."
- `grok models` output showing a model listing (a `Default model:` line) or "logged in" → authenticated. Output that errors out or asks you to log in → stop: "Not authenticated. Run `grok login`."
- `BASE: NONE` → not a git repo: Review and Challenge are unavailable; say so and offer Consult instead.
Read the full skill on GitHub

Details

Skill name
grok
Path
skills/grok/SKILL.md
Repo updated
18 November 2026

FAQ

What does the Grok skill do?

xAI Grok second opinion via the grok CLI — three modes. Review: independent diff review with a pass/fail gate. Challenge: adversarial pass that tries to break the code. Consult: ask Grok anything, with session continuity for follow-ups. Use when the user says "grok review", "grok challenge", "ask grok", or wants a second opinion from Grok.

How do I install the Grok skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add bolasblack/claude-skills --skill grok. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Grok popular?

It lives in bolasblack/claude-skills, which has 5 GitHub stars and 0 forks.

Related skills

Caveman

5

bolasblack/claude-skills

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

Images, Video & Audio

Agent Centric

5

bolasblack/claude-skills

Track decisions (AGD) with validation and indexing. Use when making design decisions, recording important choices, discussing trade-offs, or when user mentions AGD or decision record.

AI, LLMs & Agents

Codex

5

bolasblack/claude-skills

OpenAI Codex second opinion via the codex CLI — three modes. Review: independent diff review with a pass/fail gate. Challenge: adversarial pass that tries to break the code. Consult: ask Codex anything, with session continuity for follow-ups. Use when the user says "codex review", "codex challenge", "ask codex", or wants a second opinion from Codex.

Software Development

Guardrails

5

bolasblack/claude-skills

Rendered guardrail framework: keep a repo's hard rules in one-rule-per-file GRL sources behind a compact router, and render only the rules a task needs. Use when gathering guardrail context before implementing or reviewing code, when creating, editing, retiring, or reviewing GRL rule files or .agents/guardrails/index.md, when running the guardrails CLI (validate, render, review-metadata, next-id), or when setting up, adopting, or bootstrapping a guardrail framework in a repo that does not have one yet. Do NOT use for ordinary lint rule authoring unless the lint rule backs a guardrail, for runt

Software Development

Fractal Architecture

5

vnovakovits/claude-skills

Apply heuristics from Mark Seemann's "Code That Fits in Your Head" (2021) — fractal architecture, working-memory limits, cyclomatic complexity ceilings, vertical slices, encapsulation through invariants, functional core / imperative shell, checklists, and sustainable software engineering. Use when designing, decomposing, sizing methods/classes, deciding what fits in working memory, or evaluating whether code is sustainable over the long term.

Software Development

Hexagonal Clean Architecture

5

vnovakovits/claude-skills

Apply Alistair Cockburn's Hexagonal Architecture (Ports and Adapters), Jeffrey Palermo's Onion Architecture, and Robert C. Martin's Clean Architecture — the family of architectural styles that put the domain at the center, push frameworks and I/O to the edges, and enforce inward-pointing dependencies. Use when structuring a non-trivial application, separating business logic from delivery and persistence, deciding where ports live and how adapters plug in, or testing domain logic without spinning up infrastructure.

Software Development

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.