Everything in the catalog

更新官方 dbskill，并保留其他 Skill 与用户存档。用户要求更新、升级、检查 dbskill 版本，或在更新提醒后回复 1 时使用。

从抖音、小红书、微信视频号等平台链接或分享文案查询作品／账号数据并提取语音文字稿，按作者和标题归档为 Markdown。用户要求解析平台视频或取得数据、文字稿时使用；需配置 TikHub 与轻抖凭证，不负责本地成片章节导航或导航视频渲染。

根据本地视频或带时间戳字幕划分章节、话题或步骤，生成可导入剪辑软件的导航条 MP4、动态分段进度和时间表。用户要求视频章节导航、顶部进度条或当前位置提示时使用；不负责平台链接数据提取或标题封面开头文案。

通用手绘风社区发帖与静态页面/资产发布 Skill。打通 handraw-style.com (Discourse) 官方论坛账号系统与静态画廊发布系统。涵盖双重能力：(1) 全板块论坛发帖与管理（创作交流、好用的工具、综合大厅、运营与变现、实战作品与爆款、手绘skill）：支持发布通用长帖、出版级手绘提示词卡片、自…

Review an OpenMetadata connector against golden standards.

dontbesilent 商业工具箱的技能调度台，根据当前问题和反馈选择下一步，在对话中直接执行、澄清、组合或对照尝试 Skill。用户不知道从哪里开始、需要调整处理方法、第一次使用 dbskill、输入三位编号或查询隐藏款目录时使用；仅需推荐或可复制提示词时按请求交付。

Review how the lean-ctx ctx_* MCP tools performed in the current session and file upstream issues for confirmed problems.

Set up, audit, verify, or fix website conversion tracking.

Plan, draft, audit, and publish LinkedIn posts and comments.

Use when writing, reviewing, or refactoring SwiftUI code for iOS or macOS, including state and `@Observable` data flow, view composition, resizable layouts…

Convert existing PyTorch Lightning training code into an NVFLARE federated job using the Lightning Client API patch, local validation, and job export; use…

Convert existing plain or manual PyTorch training code into an NVFLARE federated job using Client API model exchange, local validation, and job export; use…

Compute federated statistics over tabular data (count, sum, mean, stddev, var, histogram, quantile, noise-protected min/max) and image data (count…

Answers BMad questions and recommends the next skill from what is installed.

Push the LLM to reconsider, refine, and improve its recent output.

Work out and record the architecture decisions that keep separately built parts of a system consistent, in a short architecture document.

Facilitate a brainstorming session using diverse creative techniques.

Authors and updates customization overrides for installed BMad skills.

Decision-grade research on a topic or this repository.

Runs the evals of a BMad skill through the agent harness the user works in and reports what they show: baseline against the bare model, variant against a…

Test a half-formed idea in a questioning conversation, with different personas probing its weak points, until the user can act on it or drop it with confidence.

Orchestrates lively group discussions between installed BMAD agents or custom personas, and helps author custom parties.

Runs one or more installed review lenses — adversarial critique, edge cases, verification gaps, structure, prose — and reports triaged findings.

Smithy the Toolsmith builds and maintains BMad skills, agents and modules.