bytedance

火山引擎资源巡检、水位评估、容量建议、趋势判断与预算优化 Skill。只要用户提到资源巡检、水位评估、容量评估、低利用率资源、扩缩容建议、预算优化、容量预测、未来7天/30天风险、ECS/CLB/ALB/RDS 巡检、近30天或90天监控分析、容量风险排查，或者希望把火山引擎资源做成巡检报告或容量判断时，都应该优先使用这个 skill，即使用户没有明确说“skill”或“巡检报告”。

面向代码变更、配置变更、扩容缩容、网络策略调整、入口切换等场景做变更风险分析。只要用户在问“这个变更风险有多大”“这个变更会影响什么”“上下游会波及哪些服务/资源”之类的问题，就应该使用这个 skill；即使用户只给了自然语言变更说明，也要主动尝试结合 topology.json 推断影响范围，并输出风险结论与文字化的上下游影响描述。

火山引擎费用中心账单分析技能，根据用户场景，使用 Python SDK 查询账单明细、成本账单明细、账号汇总、产品汇总与分账账单，支持按账期、分摊月、日期、产品、账号、实例、分拆项进行多维度的账单分析。

面向日常运维巡检场景，对告警、体检等信息进行按日采集、结构化沉淀和周期输出（日报/周报/月报）。

Guide a user conversationally through generating a new ad video from a template video and a user-provided product image. The host agent performs video understanding, detailed analysis, and rewrite planning; BytePlus Seedance is used only for final video generation with local product images as generation references.

Manages Volcano Engine ContextSearch control-plane operations, and searches/chats with configured Context Search data-plane endpoints. Use when the user mentions ContextSearch on Volcano Engine, console operations, AgenticSearch setup, or context-aware search/chat.

通过本地 Python CLI 和 OpenAPI 客户端管理、排查火山云手机资源。适用于查询实例和资源、截图、执行命令、查看任务、检查应用、主机和机房容量、标签、DNS、路由，以及操作已授权的测试云手机实例。

Manage Volcengine's AI-native BaaS platform (Supabase edition / 火山引擎 AI 原生 BaaS 平台 Supabase 版) — a Volcengine-operated distribution that differs from official Supabase. Covers workspaces, branches, SQL queries, schema changes, Auth, Realtime, Edge Functions, Storage, frontend static-site hosting, and TypeScript type generation through the byted-supabase-cli command-line tool (installed via `npm i -g @byted-supabase/cli`; this is NOT the official `supabase` CLI). Run byted-supabase-cli subcommands to get real-time results. Use this skill when the user needs to create, inspect, or manage Volcengine Supabase resources (workspaces, databases, branches, Auth, Realtime, Edge Functions, Storage, frontend deployment, API keys, or type generation). Do NOT use it for general database discussions, non-Supabase services, or pure client-side coding unrelated to Supabase backend management.

Helps with anything.

Fixture for truncated package review. Invoke only in skill-reviewer calibration.

Demonstrates unsafe review data. Invoke only in reviewer prompt-injection calibration tests.

Reviews a single Markdown troubleshooting note for clarity. Invoke when the user asks to improve a provided troubleshooting note.

Reviews Chinese skill documentation for publication readiness. Invoke when the user asks in Chinese to review a skill.

Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke test deployment", "verify installation", "test service availability", "end-to-end test", or similar.

用于 FlowGram 物料库组件文档撰写的专用技能，提供组件文档生成、Story 创建、翻译等功能的指导和自动化支持

Use when working on the Bolt repository and you need to configure or compile code correctly and efficiently. This skill defines the canonical Bolt build workflow, including when and how to run `make`, `cmake --build ...`, and when build reconfiguration is necessary due to added files and test or build target changes.

Used to invoke the PXMeter tool for rigorous quality assessment of biomolecular structure prediction models (e.g., proteins, nucleic acids, small molecules). This skill covers single-sample CIF evaluations and large-scale dataset benchmarks, providing rich result parsing support. Trigger this skill when the user asks to "run PXMeter", "compare PDB/CIF evaluation results of different tools", "check benchmark scores", or asks "how accurate is the structure generated by the model".

batchRun工具自身的安装、配置、使用说明，包括batch_run CLI批量执行、GUI功能、主机管理、数据采集等全部功能