Ask Hermes | Agent Skills Atlas

About this skill

Consult Hermes (the user's multi-provider LLM CLI, currently routing to GPT-5.5 / codex-class) as a strategic advisor (军师) via a hermes chat -q shell-out, then synthesize Hermes's response into Claude's own answer with explicit attribution. Use when the user explicitly asks for Hermes's view ("问 hermes", "ask hermes", "军师怎么说", "second opinion", "另一个 AI 怎么看", "让 hermes 也说一下"), or proactively when Claude faces a judgment / recommendation / architecture / trade-off / tool-selection decision and a second-AI cross-check materially reduces risk — including areas Claude tends to over-hedge. Claude stays in the lead and synthesizes; it is never a relay. Replaces ask-grok as the default 军师 (Grok sanctioned 2026-05); Grok remains an optional fallback.

Quick start

Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.

Installation guide →

Review, license & listing details

Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Partial

Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.

0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1

Content SHA-256: 98656a3bb404e7ad47e2749b25c2a5ed64226b5a78c3d343c51551f576cf67ec

About scan coverage and limitations

Original listing metadata

Original name

ask-hermes

Original description

Consult Hermes (the user's multi-provider LLM CLI, currently routing to GPT-5.5 / codex-class) as a strategic advisor (军师) via a `hermes chat -q` shell-out, then synthesize Hermes's response into Claude's own answer with explicit attribution. Use when the user explicitly asks for Hermes's view ("问 hermes", "ask hermes", "军师怎么说", "second opinion", "另一个 AI 怎么看", "让 hermes 也说一下"), or proactively when Claude faces a judgment / recommendation / architecture / trade-off / tool-selection decision and a second-AI cross-check materially reduces risk — including areas Claude tends to over-hedge. Claude stays in the lead and synthesizes; it is never a relay. Replaces ask-grok as the default 军师 (Grok sanctioned 2026-05); Grok remains an optional fallback.

About this listing

Category: Developer tools
Reported license: MIT
Listing language (estimated): English
Review status: Not individually reviewed
Agent compatibility: Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.