cross-examine

cross-examine is a skill in zebbern/claude-code-guide, last changed 31 May 2026. It is instructions only: no scripts, no named hosts and no pre-approved tools. Our pattern check flagged nothing at commit b50a31a on 27 Oct 2026.

Pattern check: nothing flagged · commit b50a31a · 27 Oct 2026

Install

From the author

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Licence: MIT
Repo stars: 4.7k
Folder last changed: 31 May 2026 (opens in a new tab)
Publisher: zebbern
Files: 2 files
Checked: b50a31a (opens in a new tab) · 27 Oct 2026

Install

Each tab says whether it installs commit b50a31a, the one we checked, or the latest version.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.

Pinned to commit b50a31a, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/zebbern/claude-code-guide.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin b50a31ad52510d148709b1eb61406952a02c3d19 &&
  git -C "$tmp" sparse-checkout set -- skills/cross-examine &&
  git -C "$tmp" checkout -q b50a31ad52510d148709b1eb61406952a02c3d19 &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/cross-examine &&
  cp -R "$tmp"/skills/cross-examine/. .claude/skills/cross-examine/ &&
  rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Claude Code docs

Pinned to commit b50a31a, the one we checked.

Skills in the Claude apps belong to your account rather than to a project.

Make cross-examine.zip, with the skill folder at the top level:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/zebbern/claude-code-guide.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin b50a31ad52510d148709b1eb61406952a02c3d19 &&
  git -C "$tmp" sparse-checkout set -- skills/cross-examine &&
  git -C "$tmp" checkout -q b50a31ad52510d148709b1eb61406952a02c3d19 &&
  out="$(mktemp -d)" &&
  cp -R "$tmp"/skills/cross-examine "$out"/cross-examine &&
  (cd "$out" && zip -qr - cross-examine) > cross-examine.zip &&
  rm -rf "$tmp" "$out"

In Claude, open Customize > Skills, select +, then + Create skill > Upload a skill, and choose cross-examine.zip.

On Free, Pro and Max plans, turn on Code execution and file creation (Create and edit files in newer settings) under Settings > Capabilities.

Claude apps docs

Pinned to commit b50a31a, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/zebbern/claude-code-guide.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin b50a31ad52510d148709b1eb61406952a02c3d19 &&
  git -C "$tmp" sparse-checkout set -- skills/cross-examine &&
  git -C "$tmp" checkout -q b50a31ad52510d148709b1eb61406952a02c3d19 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/cross-examine &&
  cp -R "$tmp"/skills/cross-examine/. .agents/skills/cross-examine/ &&
  rm -rf "$tmp"

Codex picks up new skills on its own; restart it if this one does not appear.

Codex docs

Pinned to commit b50a31a, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/zebbern/claude-code-guide.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin b50a31ad52510d148709b1eb61406952a02c3d19 &&
  git -C "$tmp" sparse-checkout set -- skills/cross-examine &&
  git -C "$tmp" checkout -q b50a31ad52510d148709b1eb61406952a02c3d19 &&
  mkdir -p .cursor/skills &&
  mkdir .cursor/skills/cross-examine &&
  cp -R "$tmp"/skills/cross-examine/. .cursor/skills/cross-examine/ &&
  rm -rf "$tmp"

Cursor docs

Pinned to commit b50a31a, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/zebbern/claude-code-guide.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin b50a31ad52510d148709b1eb61406952a02c3d19 &&
  git -C "$tmp" sparse-checkout set -- skills/cross-examine &&
  git -C "$tmp" checkout -q b50a31ad52510d148709b1eb61406952a02c3d19 &&
  mkdir -p .github/skills &&
  mkdir .github/skills/cross-examine &&
  cp -R "$tmp"/skills/cross-examine/. .github/skills/cross-examine/ &&
  rm -rf "$tmp"

In a running Copilot CLI session, run /skills reload.

Or install it with gh skill, which also installs the commit we checked. Needs GitHub CLI 2.90 or later.

gh skill install zebbern/claude-code-guide skills/cross-examine/SKILL.md@b50a31ad52510d148709b1eb61406952a02c3d19 --agent github-copilot --scope project

Copilot & VS Code docs

Pinned to commit b50a31a, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/zebbern/claude-code-guide.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin b50a31ad52510d148709b1eb61406952a02c3d19 &&
  git -C "$tmp" sparse-checkout set -- skills/cross-examine &&
  git -C "$tmp" checkout -q b50a31ad52510d148709b1eb61406952a02c3d19 &&
  mkdir -p .gemini/skills &&
  mkdir .gemini/skills/cross-examine &&
  cp -R "$tmp"/skills/cross-examine/. .gemini/skills/cross-examine/ &&
  rm -rf "$tmp"

In a running session, run /skills reload.

Or use Gemini CLI’s own installer. Installs the latest version, not the one we checked.

gemini skills install https://github.com/zebbern/claude-code-guide.git --path skills/cross-examine --scope workspace

Gemini CLI docs

Pinned to commit b50a31a, the one we checked.

Codex, Cursor, Copilot, VS Code, Gemini CLI, OpenCode, Goose, Amp and Zed all read .agents/skills; Claude Code and Kiro list only their own folders.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/zebbern/claude-code-guide.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin b50a31ad52510d148709b1eb61406952a02c3d19 &&
  git -C "$tmp" sparse-checkout set -- skills/cross-examine &&
  git -C "$tmp" checkout -q b50a31ad52510d148709b1eb61406952a02c3d19 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/cross-examine &&
  cp -R "$tmp"/skills/cross-examine/. .agents/skills/cross-examine/ &&
  rm -rf "$tmp"

Or use the skills CLI from skills.sh. Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.

npx skills@1.7.4 add zebbern/claude-code-guide --skill cross-examine

Agent Skills docs

What it can touch

From the files and frontmatter at commit b50a31a. This is how much a skill can do, not whether it is risky.

What it can touch: Instructions only

It is instructions only: no scripts, no named hosts and no pre-approved tools.

Pattern check

Pattern check: nothing flagged · commit b50a31a · 27 Oct 2026

We checked every text file in this skill, at commit b50a31a on 27 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check works Report an incorrect finding

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

Agent Skills specPasses
The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.
- Note
  There is no license field, so readers can't tell whether they may reuse the skill. O2
  Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.
Claude CodePasses
Claude apps & API uploadPasses
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Note
  The description is 231 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4
  Fix: If the claude.ai upload refuses it, trim the description to 200 characters.
OpenAI (Codex & API)Passes
VS Code & CopilotPasses

SKILL.md

Files

2 files

Path	Size
LICENSE (opens in a new tab)	1 KB
SKILL.md (opens in a new tab)	640 B

More from zebbern/claude-code-guide

academic-paper-reviewer
zebbern/claude-code-guide
Simulates academic peer review, evaluating papers across Originality, Methodology, Results, and Writing to provide Major/Minor Revision recommendations with actionable feedback. Triggers when a user asks to "review my paper," "simulate peer review," or "give my paper a peer review.
- Instructions only
Pattern check: Nothing flagged
MIT · 4.7k repo stars · Updated 31 May 2026
active-directory-attacks
zebbern/claude-code-guide
This skill should be used when the user asks to "attack Active Directory", "exploit AD", "Kerberoasting", "DCSync", "pass-the-hash", "BloodHound enumeration", "Golden Ticket", "Silver Ticket", "AS-REP roasting", "NTLM relay", or needs guidance on Windows domain penetration testing.
- Touches credentials
- Runs shell commands
- +1 more
Pattern check: Nothing flagged
MIT · 4.7k repo stars · Updated 31 May 2026
api-fuzzing-bug-bounty
zebbern/claude-code-guide
This skill should be used when the user asks to "test API security", "fuzz APIs", "find IDOR vulnerabilities", "test REST API", "test GraphQL", "API penetration testing", "bug bounty API testing", or needs guidance on API security assessment techniques.
- Runs shell commands
- Reaches the network
- +1 more
Pattern check: Nothing flagged
MIT · 4.7k repo stars · Updated 31 May 2026
api-shape-explorer
zebbern/claude-code-guide
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
- Instructions only
Pattern check: Nothing flagged
MIT · 4.7k repo stars · Updated 31 May 2026
audit-flow
zebbern/claude-code-guide
Interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers with SQLite persistence and Mermaid export. Use for security audits, compliance documentation, flow tracing, feature ideation, brainstorming, debugging, architecture reviews, or incident post-mortems. Triggers on audit, trace flow, document flow, security review, debug flow, brainstorm, architecture review, post-mortem, incident review.
- Runs shell commands
- Reaches the network
- +1 more
Pattern check: Nothing flagged
MIT · 4.7k repo stars · Updated 31 May 2026
authentication-patterns
zebbern/claude-code-guide
Authentication patterns: session vs JWT vs OAuth comparison, provider selection (NextAuth, Clerk, Supabase Auth), security checklist, and common mistakes. Use when implementing auth, reviewing auth flows, or choosing auth providers.
- Instructions only
Pattern check: Nothing flagged
MIT · 4.7k repo stars · Updated 31 May 2026

All skills in zebbern/claude-code-guide

Install

What it can touch

Pattern check

Format check

SKILL.md

Files

More from zebbern/claude-code-guide

academic-paper-reviewer

active-directory-attacks

api-fuzzing-bug-bounty

api-shape-explorer

audit-flow

authentication-patterns