Multi-platform article publisher and content distribution tool. Sync and cross-post Markdown/HTML articles to 29+ platforms including Zhihu (知乎), Juejin (掘金), CSDN, Toutiao (头条), Weibo (微博), Xiaohongshu (小红书), Bilibili (B站), WordPress, Typecho, WeChat (微信公众号), and more. Use when the user wants to publish, sync, cross-post, or distribute articles (文章同步/多平台发布/一键发布) to Chinese content platforms, tech communities, blogging sites, or self-hosted blogs. Also use when checking platform login status or extracting articles from web pages. Keywords: content syndication, blog distribution, multi-platform publishing, self-media (自媒体), content creator tools.

Extract and archive Discord images, attachments, links, and conversation files. Use when asked to "extract Discord images", "download Discord attachments", "harvest a Discord channel", "archive a DM", or when scraping or preserving content from a Discord conversation.

Secret management expert. ALWAYS invoke this skill when you need to read API keys, tokens, or other secrets configured by the user. Never hardcode credentials — use this skill to retrieve them securely.

Diagnose gRPC connection issues between the Bindu core and a language SDK. Use when an SDK fails to register, HandleMessages calls time out, "connection refused" on :3774, heartbeats stop arriving, or the core logs "agent silently died".

输入某个产品的文档、URL 或简要描述，自动抓取关键信息，分别扮演「用户、投资人、产品经理、市场运营、品牌运营、友商、合作伙伴」7 个角色对该产品进行深度分析，中间结果分角色保存，最终整合为一篇图文并茂（SVG/Mermaid/ASCII）的综合分析报告，结论明确、有权威数据支撑、逻辑清晰、小白可读，并附有结论边界、前提假设及假设变动时的结论调整说明。 触发条件：用户提到"产品分析"、"多角色分析"、"7个角色"、"投资人视角"、"用户视角"、"产品竞争分析"、"全面分析这个产品"、"帮我分析一下 XX 产品"、"从多个角度看这个产品"、"product analysis"、"multi-role analysis"，或提供产品文档/链接并希望获得深度产品分析报告时，必须使用本 skill。即使用户只说"帮我全面分析一下这个产品"，也应立即使用本 skill。

将 PRD 翻译成「可独立测试」的功能设计文档。文档的下游使用者包括开发者、评审者、测试者,且三方互相隔离(测试者看不到开发者写的代码),所以必须把行为、状态、接口、数据、权限、异常、验收标准全部显式化,让测试者能独立从文档推导用例。输入是一份已写好的 PRD 文档,输出是一份完整的 Markdown 功能设计文档,保存到当前项目的 `markdown/` 目录。适用于:写功能设计文档、技术设计文档、Tech Design、详细设计说明书、FDD、Functional Design Doc、Detailed Design、模块设计文档、把 PRD 翻译成开发设计、把需求拆成可开发/可测试/可评审的规格。

分析一段内容或一个文件的"人味"（即像不像人类自然写出来的，AI 生成痕迹有多重），给出 0-100 量化打分，并在低于目标线（默认 80 分，用户可指定其他数值如90分）时在不改变原意的前提下改写到目标分数以上。触发条件：用户提到"人味"、"AI味"、"AI感"、"降AI率"、"去AI化"、"人性化改写"、"像人写的"、"过人工检测"、"过AI检测"、"让文章更自然"、"这段话是不是AI写的"、"帮我把这篇文章改得不像AI写的"，或者给出一段文字/文件并希望知道"读起来自然不自然"、"会不会被认出是AI写的"。即使用户只说"这段话感觉很机器，帮我改一下"或"帮我看看这篇稿子像不像真人写的"，也应使用本 skill。输出为 Markdown 报告，保存到当前项目 markdown/ 目录。

Author good Ginkgo specs — container nodes (Describe/Context/When), subject nodes (It/Specify), setup/cleanup nodes (BeforeEach, JustBeforeEach, AfterEach, DeferCleanup, BeforeSuite/AfterSuite), the "declare in container, initialize in BeforeEach" rule, separating creation from configuration, reusable test helpers with GinkgoHelper()/GinkgoHelperGo(), and By/GinkgoWriter output. Use when writing or reviewing specs or extracting a test helper. Covers the tree-construction-time pitfalls (no assertions/init/loop-capture in container bodies).

Make Ginkgo specs interruptible and test asynchronous behavior — SpecContext/context.Context cancellable nodes, NodeTimeout/SpecTimeout/GracePeriod, the --timeout flag, Abort and SIGINT behavior, Gomega Eventually/Consistently (the func(g Gomega) form, .WithContext), and the defer GinkgoRecover() rule for goroutines. Use when a spec hangs or times out, polls for eventual consistency, tests channels/streams/processes, launches goroutines, or needs a deadline.

Run Ginkgo suites with the ginkgo CLI — run, -r, -p, --dry-run, watch, build (precompiled .test binaries), generate, outline, unfocus, labels, version; spec randomization (--randomize-all/--randomize-suites/--seed); running multiple suites (--keep-going/--skip-package/--compilers); previewing (--dry-run, PreviewSpecs); and parameterizing a suite via env vars or init()-registered flags after -- plus GinkgoConfiguration() overrides. Use when running suites locally, precompiling, watching for changes, or parameterizing a run from the command line. For a CI configuration see ginkgo:ci.

Diagnose a failing Ginkgo suite as an agent — always run with --json-report into a predictable temp/gitignored location, read the terminal verdict line, then use jq to extract structured failure details (name, message, file:line, panic value, captured logs). Covers the panicked-vs-failed trap, panic locations pointing into the Go runtime, parallel output interleaving, reproducing with --seed, and progress reports for hangs. Use when a suite failed and you need to know why. Also invokable as /ginkgo:debugging-failures.

Build or redesign polished browser-rendered visual artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use for visual front-end creation, design-system exploration, design critique, or explicit browser acceptance / QA of a web artifact. Not for back-end, CLI, non-visual coding, source-to-longform article conversion, or narration-driven click-through video presentations.

Use when the user wants to play/pause/skip music, control volume, seek, search songs/playlists, query NetEase Music data, or operate NetEase MusicBox. Drives MusicBox through the `musicbox` CLI + daemon; never simulates terminal keypresses to the curses TUI.

Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit the fold.

Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find everything about, research and file, go research, build a wiki on.

Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a paper or codebase into a structured, machine-executable knowledge package, building an ARA from scratch, or converting research outputs into a falsifiable, agent-traversable form.

Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.

Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn. Use when creating any figure for a conference paper.

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

Official GSAP skill for gsap.utils — clamp, mapRange, normalize, interpolate, random, snap, toArray, wrap, pipe. Use when the user asks about gsap.utils, clamp, mapRange, random, snap, toArray, wrap, or helper utilities in GSAP.