技能创建器
skill-creator
创建、改进和评估自定义技能,把专业流程转化为可重复使用的 AI 能力。
mistral-incident-runbook【数据与研究】Analyze, contain, and recover Mistral credential, outage, throttling, data, spend, and state-reconciliation incidents. Use when responding to provider-related impact. Trigger with "Mistral incident", "Mistral outage", or "rotate a leaked Mistral key".
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
Restore safety before throughput. Classify, stop amplification, protect evidence, reconcile ambiguous work, and use the smallest reversible containment action.
Provider, account, app, and data incidents differ. Workspace caps can suspend access; Files, Batch, Conversations, Agents, and Workflows may outlive a failed request and need reconciliation.
Never paste keys into incident channels. On exposure, revoke through approved admin, rotate consumers, and verify old-key denial without displaying values.
Use Read, Glob, and Grep to inspect code, locks, configuration, tests, and evidence. Use Write and Edit only for approved repository changes. Invocation alone does not authorize network calls, paid usage, uploads, stateful resources, admin mutations, deployments, or deletion.
The commander must approve revocation, traffic, queue or job changes, deletion, limits or spend changes, rollback, and customer communication. Record the approver and exact containment scope.
Return scope and timeline, classification, containment approvals, affected state, reconciliation, recovery, residual risk, communications, and follow-ups. Keep unresolved ambiguity visible with a named owner.
Tabletop key exposure, 429, outage, cap reached, content leak, stuck stream, and ambiguous state; verify rollback/comms.