DevOps e Infra

Shows what changed in dotforge since the project's last sync, to decide whether running /forge sync is worthwhile.

Scan an ops repo's goals, state, and backlog to surface new work items and add them to the backlog. Load when deciding what the project should work on next.

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

Run a full pre-launch quality gate before shipping — chains product review, growth audit, UX audit, security scan, and deployment preflight into a go/no-go launch decision. Stops on critical blockers. Use before v1 launch, beta release, major version rollout, or feature launch.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Emergency fix-and-deploy pipeline — diagnose a bug, apply a minimal fix, verify safety, deploy to production, and confirm the service is healthy. Supports Vercel, AWS, Railway, Fly.io, Heroku, and Kubernetes. Tracks incident timeline and MTTR. Triggered by 'fix and deploy', 'hotfix and ship', 'emergency fix', 'fix this bug and deploy', 'patch and push', 'fix and ship'.

Manage Linear issues, projects, and teams via the GraphQL API. Create, update, search, and organize issues. Uses API key auth (no OAuth needed). All operations via curl — no dependencies.

Configure a CDN with optimized caching, SSL/TLS, security headers, and cache invalidation — auto-detects hosting provider and app type, generates CloudFront, Cloudflare, or Vercel config with per-content-type cache rules, edge functions, and compression. Use when deploying a static site, SPA, SSR app, or adding a CDN layer to an existing API.

Analyze fleet fuel optimization systems including MPG consumption analytics, eco-driving behavior scoring, route fuel cost modeling, idling detection and anti-idle programs, IFTA tax compliance reporting, alternative fuel transition planning, EV charging infrastructure readiness, and EPA SmartWay partnership metrics for commercial vehicle fleets.

Skill de auditoria SEO abrangente para páginas Next.js e HTML, cobrindo otimização on-page, validação de esquema, meta tags, Open Graph, HTML semântico, velocidade do site, responsividade móvel e análise de backlinks. Utilize para auditar, otimizar ou corrigir problemas de SEO em páginas ou sites.

Scan project code to detect patterns, dependencies, and conventions. Propose domain rules based on what the code actually does.

飞书视频会议：搜索历史会议、查询会议纪要产物（总结、待办、章节、逐字稿）、查询会议参会人快照。1. 查询已经结束的会议数量或详情时使用本技能（如历史日期｜昨天｜上周｜今天已经开过的会议等场景），查询未开始的会议日程使用 lark-calendar 技能。2. 支持通过关键词、时间范围、组织者、参与者、会议室等筛选条件搜索会议。3. 获取或整理会议纪要、逐字稿、录制产物时使用本技能。4. 查询“谁参加过某会议”“参会人列表”等参会人快照信息用 vc meeting get --with-participants（任意时点可查，含已结束会议）。注意：**Agent 真实入会/离会、感知正在进行中会议的实时事件**请使用 lark-vc-agent 技能，本技能不覆盖写操作和会中事件流。