菜单
Manual-only opposite-model request. Use only when the user explicitly invokes ask-peer: Codex asks Fable through `claude -p`; Claude asks Codex through `codex exec`. For one focused second opinion, review, or scoped work pass without a live Herdr pair.
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
Make an existing PR merge-ready through the complete feedback loop: inventory every bot and human review surface, apply valid same-PR fixes, reply, sync the live target branch, resolve conflicts, push, and recheck until the latest head is stably clean. Use for a full review sweep or merge-ready result, not one selected comment. For the whole commit-to-PR lifecycle use ship-it.
Ship a branch through the full PR lifecycle: intentional commits, local quality gate, push, PR creation/update, CI, target-branch sync, and the shared review-clean loop. Use when the user asks to ship end to end or get a branch fully review-ready. For review feedback on an existing PR without the commit/PR lifecycle, use review-pr-comments.
Manual-only long design-exploration loop. Use only when the user explicitly invokes art-director: direct Codex image batches, curate and wipe between axes, and converge on a winning direction before handing it to impeccable or image-to-code.
Fable-led multi-slice orchestration across Codex and Claude subagents: freeze specs, route work, verify, and synthesize. Use when the user explicitly asks Claude to lead, orchestrate, or delegate a non-trivial task across models or subagents. For one opposite-model request use ask-peer; for a live equal pairing use herdr-pair.
Manual-only long improvement campaign run by Claude + Codex as a pair. Use only when the user explicitly invokes goal-loop and supplies one target plus what 'better' means; the agents repeatedly test, improve, ship PRs, and require current evidence plus peer acceptance to stop.
Evidence debugging for unresolved bugs. Use when the user says 'diagnose' or 'debug this', or when behavior is broken, flaky, environment-specific, or unexplained and the root cause is not proven. Build a feedback loop, collect runtime evidence, and fix only after evidence identifies the cause.
| name | ask-peer |
| description | Manual-only opposite-model request. Use only when the user explicitly invokes ask-peer: Codex asks Fable through `claude -p`; Claude asks Codex through `codex exec`. For one focused second opinion, review, or scoped work pass without a live Herdr pair. |
| user-invocable | true |
| disable-model-invocation | true |
| argument-hint | <question, review, or scoped task for the other agent> |
One request, one opposite-model reply. This is the phone-friendly headless path:
use it for a focused second opinion, review, or bounded work pass. Use
herdr-pair for a visible multi-turn dialogue and delegate for Fable-led
multi-slice orchestration.
Detect the current harness, then read the matching reference in full:
| Current harness | Peer | Reference |
|---|---|---|
| Codex | Fable | references/ask-fable.md |
| Claude Code | Codex | references/ask-codex.md |
If the harness is ambiguous, inspect the environment and available CLI before choosing. Never ask the same model through its own CLI.
~/.codex/config.toml or the CLI default owns it.