Assess integrity of an eval, benchmark, metric, A/B test, holdout, LLM-judge, or user-study claim when the question is whether measurement, comparison, or evidence is independent and trustworthy.

Assess integrity of an eval, benchmark, metric, A/B test, holdout, LLM-judge, or user-study claim when the question is whether measurement, comparison, or evidence is independent and trustworthy.

Ingest GitHub Copilot CLI/session history into Obsidian as distilled knowledge. Use for importing or mining Copilot history; not for general Copilot help, simple session search, or backup.

Launch Code OSS (VS Code from sources) into an isolated throwaway profile with unique debug ports so you can drive it with @playwright/cli AND attach a Node debugger via dap-cli in the same session. Use when working on VS Code itself and you want to interact with the running workbench, automate chat or UI flows, test UI features, take screenshots, set breakpoints in the renderer / extension host / main process, or combine UI driving with debugging.

VS Code CSS conventions, file organization, class naming, standard sizes, SplitView/Grid layout, scrollable content, responsive layout, and text overflow/ellipsis patterns. Use when writing CSS, building layouts, or fixing text truncation issues.

Use when: building or evaluating unstyled Primer React primitives, especially accessibility primitives or low-level behavior that other components should build on. Covers when to create a base component instead of baking behavior into a styled component, the unstyled CSS-reset convention, deciding which parts need a base equivalent, and consolidating ARIA Authoring Practices Guide patterns.

Synchronize CS-Notes Git changes and material projections when the user says 同步笔记, sync笔记, or pull CS-Notes and push. Preserve unpublished intakes and require material-specific human completion evidence before archival.

Expert guide for the Gemini Notebook (formerly Google NotebookLM) CLI (`nlm`) and MCP server - interfaces for Gemini Notebook. Use this skill when users want to interact with Gemini Notebook programmatically, including: creating/managing notebooks, checking plan usage and quota windows, adding sources (URLs, YouTube, text, Google Drive), generating content (podcasts, reports, interactive reports, quizzes, flashcards, mind maps, slides, infographics, videos, data tables), conducting research, chatting with sources, or automating Gemini Notebook workflows. Triggers on mentions of "nlm", "notebooklm", "Gemini Notebook", "plan usage", "quota", "podcast generation", "audio overview", "interactive report", "lesson report", "refactor document", "critique draft", or any Gemini Notebook-related automation task.

Use when auditing or recovering Warp changelog fragments, reviewing or finalizing a generated release changelog, or synchronizing a tagged release back to main.

Monitors .NET runtime CI test pipelines on Azure DevOps. Use this skill when asked to monitor CI pipeline test results, triage CI test failures across ADO pipelines, or generate CI test monitoring reports.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Use when finishing a feature, fixing a bug, before committing React code, or when the user types `/doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.

Commit and push the current work, open a ready PR, babysit it through CI and review, and admin-merge it once it's green and clean, then rotate the worktree to a fresh branch. Use when the user asks to ship, publish, or hand off local changes. Merging to main deploys beta automatically; production promotion is manual.

Framework-level sharing and privacy for user-authored resources (dashboards, documents, forms, decks, etc.). Use when making a resource table ownable, wiring list/read/update access checks, or dropping the standard share dialog into a template.

This skill should be used when the user asks to "create an agent", "write an agent", "build an agent", or wants to add new agent capabilities to Claude Code.

Generate .drawio architecture diagrams with consistent visual style and export to PNG/SVG/PDF/HTML. Use when user asks to "create a diagram", "draw architecture", "make a drawio file", "build a diagram", or mentions "drawio", "architecture diagram", or "system diagram".

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

网文写作工具集基础设施部署与检查。为 Claude Code / OpenCode / Codex / Google Antigravity / ZCode / OpenClaw / Reasonix 提供内置适配；Web AI / 通用 Agent 可走 skills + AGENTS.md 文件模式。触发方式：/story-setup、$story-setup、「准备写书」「帮我搭一下环境」「配置写作项目」「检查写作环境」。

Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them.

Install and configure AutoRAG, register its Lite MCP server for external agents, or repair its single search model, approved roots, indexes, datasources, and health checks without exposing credentials. Use when AutoRAG or MCP is missing, init/refresh/health fails, indexes are stale, or the user wants to add folders or datasources.