跳到正文
cccskills
免费在 GitHub 公开

model-onboarding

Onboard a new model generation or sibling into oh-my-hermes: probe router recognition, research the official contract, write trait-to-counter calibration, place routing in both lanes, price from documented list only, gate machine config on a served route, prove with the gates, close with a benchmark pair. Use when a model family ships a new generation (for example "Fable 5.1 is out", "GLM 5.4 shipped", "onboard new model", "add model to chains").

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md3.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Model onboarding

The procedure lives in docs/MODEL-ONBOARDING.md. Read that file and follow it in order.

It is kept there rather than here because Codex, Hermes handoffs, and generic executor profiles run the same loop, and AGENTS.md requires that no single executor own a shared surface. This file exists so the loop is reachable as /model-onboarding; it holds no rules of its own.

Start by reading, in this order:

cat docs/MODEL-ONBOARDING.md
cat MODEL_OPTI.md

Nine things the loop gets wrong most often:

  • Recognition before research. Probe every served id and every bare chat name with omh coding model-route first; a model_family of unknown means the calibration never attaches. Probe the dated snapshot form too (<id>-YYYY-MM-DD): some providers serve only that spelling, and it must resolve the base's contract, chain position, price, and HUD label through dated_snapshot_base() rather than falling to generic.
  • The chain names the id the vendor's API serves, not the model card's spelling. Read the Hermes provider profile for the family before choosing the alias — DeepSeek serves deepseek-flash and 400s deepseek-v4.1-flash; the versioned contract sits behind the pointer as a declared projection and in EXACT_CONTRACT_POINTER_ALIASES.
  • Research runs as four parallel read-only lanes (official docs, Hermes runtime source, the vendor's own harness, community harnesses), each a labeled dossier under .omc/research/; the Hermes lane is the one that shows what the wire carries (id folding, effort overrides, passback).
  • Chains move as a set. The Hermes-lane table, its plugin mirror, the Maestro-lane table, the model-setup skill text, seven public doc surfaces, the release budget note, and the pinned-chain tests all name the old id; grep src/ tests/ docs/ README* site/ for it and move every site in the same commit. Superseded generations leave the shipped chains (owner decision, 2026-09-11) and join the recognition-only list; pins hide in fixtures, so start the full suite in the background at the chain edit.
  • Machine config stays provider-neutral. Chains name aliases; the provider row is a separate concern in model-providers.json. Place the id with omh model-chains set, never by hand-editing the JSON; an operator may keep an older generation behind it there, the shipped table does not.
  • Served is not released. Prove the route with one hermes --oneshot call and read the usage file (model, provider, cost_status) before any measurement or placement; gateways want the vendor-prefixed id.
  • The override is measured against the block it replaced, on cost. Run the family arm next to baseline and optimized; expect pass rate to tie and read the paired token delta, tool calls, and turns. Same pass with more tokens on the tasks it fails is a sentence that pushes — cut it.
  • A routing signal is only as good as the tier's chain head. Measure the head on the request class it will receive before shipping the signal, and name the head in every routing claim.
  • A separate reviewer lane reads the diff before the commit. The DeepSeek round's reviewer caught a reverse projection that let -pro / -fast / -flex aliases label their base id; self-review did not.

Arguments pass through verbatim: the model ids as served (for example claude-fable-5-1 claude-mythos-5-1).

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

dag-ulw

免费

[omh] Large multi-part job to run on its own: plan it as a graph of small nodes, run the ready ones in parallel through Hermes' delegate_task, verify the goal with a separate node, and repair failed nodes before reporting. Use when the user says: dag-ulw, dag ulw, ulw dag, dag ultrawork, ultrawork dag.

中文简介正在准备中。当前显示原文说明。

rlaope/oh-my-hermes35492026年10月21日 更新

[omh] Screen-reader or keyboard accessibility gaps: prepare WCAG, keyboard, focus, screen-reader, target-size, and reflow evidence gates for UI surfaces. Use when the user says: accessibility-audit, accessibility audit, a11y audit, a11y architect, wcag audit, wcag 2.2, wcag 2.2 aa, accessibility pass.

中文简介正在准备中。当前显示原文说明。

rlaope/oh-my-hermes35492026年10月21日 更新

[omh] Hermes badges unlocked and achievement progress: achievements observation: summarize hermes-achievements badges, tiers, recent unlocks, and progress from local plugin artifacts. Use when the user says: achievements, achievement, badges, badge, my badges, show achievements, achievement summary, unlocked badges.

中文简介正在准备中。当前显示原文说明。

rlaope/oh-my-hermes35492026年10月21日 更新

[omh] Technical proposal facing adversarial scrutiny: independent perspectives attack a proposal, then distill into a bundle a separate planner consumes. Use when the user says: adversarial-consensus, adversarial planning, adversarial plan review, red team this plan, red-team this plan, red team the proposal, multi-perspective review, multiple perspectives.

中文简介正在准备中。当前显示原文说明。

rlaope/oh-my-hermes35492026年10月21日 更新

[omh] Coordinating several agents or profiles: coordinate multiple Hermes profiles or agents with task, handoff, heartbeat, blocker, and completion states. Use when the user says: agent-board, agent board, kanban, multi-agent, multi agent, multi agent board, multiple hermes agents, multiple hermes profiles.

中文简介正在准备中。当前显示原文说明。

rlaope/oh-my-hermes35492026年10月21日 更新

[omh] Agent is stuck, looping, or drifting: capture a stuck, looping, drifting, or repeatedly failing agent run, diagnose the likely failure pattern, and prepare the smallest safe recovery action. Use when the user says: agent-debug, agent debug, agent debugging, agent introspection, agent self-debug, self-debug, self debugging, looping agent.

中文简介正在准备中。当前显示原文说明。

rlaope/oh-my-hermes35492026年10月21日 更新

查看 rlaope 的全部技能

报告此技能的问题