Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Manage screenshots and other visual assets for GitHub pull requests. Use when a PR body needs real screenshots, when local /tmp paths must be replaced with durable links, when deciding whether GitHub web drag-and-drop uploads can be reproduced with gh api, or when updating a PR without disturbing the user's browser tabs.
Maintain the canonical LangWatch feature map (/feature-map.json). Use when adding features, APIs, MCP tools, CLI commands, or skills — to update the central registry and keep surfaces in sync.
Record an architecture decision as an ADR in docs/adr/. Use when choosing between frameworks, libraries, databases, or architectural patterns; stating a decision with reasoning ("we decided X instead of Y because..."); or querying past decisions ("why did we choose X?").
Align Rspress heading anchor IDs between English and Chinese docs. Use for MDX `\{#...}` anchors, shortened hashes, redundant anchors, or dead links.
Sync uncommitted docs between `website/docs/zh` and `website/docs/en`. Use when authors update docs in one language and need to align the mirrored `.md`/`.mdx` file in the other language.
为说书模式剧本逐段生成旁白配音（TTS）。当用户说"生成旁白"、"配音"、"生成全集旁白"、想重新生成某段配音、或批量配音中断需要补齐时使用。
为剧本场景生成视频片段。当用户说"生成视频"、"把分镜图变成视频"、想重新生成某个场景的视频、或视频生成中断需要续传时使用。支持整集批量、单场景、断点续传等模式。
调用项目配置的文本模型生成 JSON 剧本（同时产出每个分镜的 image_prompt 与 video_prompt）。由 create-episode-script subagent 调用。读取 step1 中间文件和 project.json，输出符合 Pydantic schema 的剧本。
Use this skill to run a holistic regrounding pass on the entire microsoft/apm documentation corpus against current source code, page-by-page, and emit surgical fixes for stale claims. Activate when the maintainer wants a WHOLE-CORPUS audit (not per-PR review) -- typical triggers include "audit the docs", "reground the corpus", "check every page against code", "pre-release docs sweep", "the docs have drifted everywhere", or "we just reshaped the TOC, find dead links". Wave-batched and S7-verified; scales to the full ~112-page corpus in ~10 minutes wall-time. This is a SIBLING to docs-sync, not a replacement: docs-sync is per-PR (triggered by a diff); this skill is per-corpus (triggered by a maintainer ask). They share agent personas, schemas, and the docs index, but their triggers MUST NOT collide. Does NOT auto-merge, does NOT push without maintainer review, and does NOT replace per-PR drift detection.
Process audio recordings, meeting transcripts, podcasts, or lectures. Runs an intake interview (date, mode, speakers, language) then processes into structured notes with action items, decisions, and glossary. Triggers: EN: "transcribe", "I have a recording", "process this audio", "meeting notes from recording", "summarize the call", "lecture notes", "podcast summary". IT: "trascrivi", "ho una registrazione", "processa questo audio", "note della riunione", "riassumi la call". FR: "transcrire", "j'ai un enregistrement", "résumer l'appel". ES: "transcribir", "tengo una grabación", "resumir la llamada". DE: "transkribieren", "Aufnahme verarbeiten". PT: "transcrever", "tenho uma gravação".