菜单
Non-Claude agents only. Get an independent second opinion from Claude CLI on decisions with meaningful trade-offs.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Respond to unreplied review comments on the current GitHub Pull Request. For each comment, either commit a fix, push, and reply with the commit hash, or reply with concrete rationale for keeping the code as-is. Does not approve or request changes.
日本語の技術文書・書籍原稿の文章規範。整形（一文一行、引用ブロック、脚注、コラム記法）、段落と論証の構成（パラグラフライティング）、論証の厳密さ（ツッコミどころの除去）、読み手の負荷の管理、視点と語り、演出の抑制、LLM っぽい空句の禁止、冗長の排除を定める。日本語で技術書の章、草稿、記事、解説文を書くとき、または推敲・リライトするときに使用する。
Non-Antigravity agents only. Get an independent second opinion from Antigravity CLI (agy). agy cannot be driven headlessly from a sandboxed agent Bash, so this skill hands the user a ready-to-run command and folds in their pasted reply.
Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) via bias-free executor + two-sided evaluation (self-report + instruction-side metrics). Meta-skill, invoke ONLY when the user explicitly asks for an "empirical" eval of a prompt or skill, or for the Iter-0 description / body consistency check. Do NOT auto-invoke after every skill edit; this loop is operator-triggered by name.
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".
Draft a commit message from staged changes. Matches the style of recent commits in the repo, emphasizes why over what, and does not run `git commit`.
| name | claude-second-opinion |
| description | Non-Claude agents only. Get an independent second opinion from Claude CLI on decisions with meaningful trade-offs. |
If you are a Claude agent, STOP. Tell the user this skill is for non-Claude agents only.
$ARGUMENTS if provided; otherwise infer the question from the current task context. Keep it focused on decision-relevant information:You are providing a second opinion on a decision.
Context:
<context from the current task>
Question:
<the specific question or decision point>
Provide your independent analysis. If you disagree with the current approach, explain why and suggest alternatives.
--no-sandbox (nested sandbox-exec is prohibited on macOS):If run_in_background and TaskOutput are available:
# Bash tool: run_in_background: true, timeout: 120000
claude --no-sandbox -p "$(cat <<'CLAUDE_PROMPT'
<constructed prompt>
CLAUDE_PROMPT
)" 2>&1
Then retrieve with TaskOutput (block: true, timeout: 120000).
Otherwise (tmpfile + poll):
TMPFILE=$(mktemp /tmp/claude-opinion.XXXXXX.log)
claude --no-sandbox -p "$(cat <<'CLAUDE_PROMPT'
<constructed prompt>
CLAUDE_PROMPT
)" > "$TMPFILE" 2>&1 &
PID=$!
Poll $PID every 10-15s. Hard timeout: 300s. On timeout, kill $PID and clean up $TMPFILE.
Parse output: ignore startup logs, MCP errors, and reasoning traces before the final text. Treat the last plain-text block as the answer.
Present both perspectives (labeled by model), highlight agreements and disagreements. Evaluate Claude's suggestion critically — do not blindly adopt it.
On any failure — claude not found, auth error, network error, or timeout — report the reason to the user and proceed with your own analysis only. Discard partial output on timeout as unreliable.
Use a heredoc (<<'CLAUDE_PROMPT') to build prompt text safely. This avoids shell escaping and quoting issues for multi-line content. Note that prompts passed via -p are still subject to ARG_MAX.