Chargement du README du dépôt…
Affichage de 6 skills collectés sur 6.
Task-owning worker policy with deterministic acceptance and evidence-driven escalation (model_proctor) — run substantial work through the gated path (runner.py init/dispatch/verify/accept; flash-first with escalation to glm-5p3 then kimi-k3 on recorded…
Langue du texte source : anglais
Use when substantial coding or proctor tasks require runner-governed delegation, or when the user explicitly invokes model-proctor. Do not use for trivial tasks — execute those directly. Requires the model-proctor install.
Langue du texte source : anglais
Multi-model routing policy for Kimi K3 — delegate coding subtasks to fast/cheap models (k2p7 scout, DeepSeek V4 flash/pro, GLM-5.2) via the delegate wrapper and native GLM subagents, with read-only Codex/Claude advisors. Use ONLY for nontrivial coding tasks…
Langue du texte source : anglais
Full multi-model routing policy — delegation to fast/cheap models via the delegate wrapper plus native GLM subagents (eval config C). Use ONLY for nontrivial coding tasks (unfamiliar codebases, multi-file changes, debugging, migrations, security-sensitive…
Langue du texte source : anglais
ds-pro-start routing policy — DeepSeek V4 Pro is the default worker and you adjudicate (eval config D). Use ONLY for nontrivial coding tasks. Do NOT use for trivial tasks (known location, small patch, one edit-test cycle) — execute those directly.
Langue du texte source : anglais
Routing policy for delegating coding work to native GLM secondary subagents only (eval config B). Use ONLY for nontrivial coding tasks (unfamiliar codebases, multi-file changes, debugging). Do NOT use for trivial tasks (known location, small patch, one…
Langue du texte source : anglais
Copiez ce prompt dans l’assistant IA que vous utilisez.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/dachent/model_proctor.Le README n’a pas pu être chargé. Vous pouvez toujours consulter les Skills du dépôt ci-dessous.