lcpmarvel

@lcpmarvel source repo

10 skills
0 followers
7 hours ago last updated

▌
Feishu Whiteboard Pro 2 · lcpmarvel bundle
创建、修改、换肤和评审真正经过设计的可编辑飞书白板。适用于信息图、流程图、系统图、时间线、决策板、海报和可视化讲解：先锁定内容事实与设计简报，再按白板媒介构图，机械检查 SVG，查看真实渲染，并在重要交付前做独立终审；避免等大卡片网格和凭空补造关系。飞书写入使用扣子平台授权，授权暂不可用时仍交付本地 SVG + PNG。

0
installs
▌
Refine Regression 2 · lcpmarvel bundle
整体跑一遍真实测试用例（refine_real，真 LLM），并对比前后产物——content_list.json、refine_report.json、full.md——输出回归报告。当用户想"整体跑一下测试用例并对比前后数据"、验证清洗效果有没有回归时使用。

0
installs
▌
Test Ask Experts · lcpmarvel
Validates that the project-level ask-experts MCP server is correctly registered and that each enabled expert produces a coherent answer to a canonical domain question. Use this whenever the user wants to verify the MCP wiring after a config change, env-var update, or rebuild.

0
installs
▌
Bottleneck Migration · lcpmarvel bundle
用"最短板/瓶颈迁移"框架分析一个**投入之间强互补、缺一不可的串联系统**(产业链或技术系统):拆解资源链、定位当前约束、推演下一堵墙会出现在哪、画出"收费站"地图,并用过滤器判断哪些受益环节真能赚到钱、并给出可被事后裁决对错的记分卡。当用户分析这类**互补串联系统**的产业链、问"下一个瓶颈/卡点在哪""谁是受益者/卖铲子的""这轮涨价能不能买""哪个环节是咽喉"、做技术驱动的投资推演时使用。注意:系统若为可替代/并联结构,本 skill 在 GATE A 会主动退出;本 skill 产出的是分析框架与可记分的预测,不是投资建议。

0
installs
▌
Coze Docs Sync · lcpmarvel bundle
Mirror the official Coze docs (docs.coze.cn) to local Markdown, preserving the site's exact directory tree. Use whenever the user wants to sync / update / pull / archive Coze (扣子) docs, grab every page of a docs space (cozespace, guides, tutorial, …), or needs an offline copy of the Coze documentation. Works without a browser or login: it calls the same arcosite API the site uses — GetBusStructureById for the nav tree, then /api/open/docs/{business_id}/{_id} for each page's raw Markdown (the "open markdown" button) — and writes a numbered directory mirror. Idempotent: a manifest tracks output so each run reconciles local with live (stale files removed).

0
installs
▌
Macos App Icon Designer · lcpmarvel bundle
Design, critique, refine, validate, integrate, and package production-ready macOS application and menu bar icons. Use for macOS App Icon concepts, 1024px masters, layered Icon Composer artwork, Liquid Glass variants, Xcode AppIcon catalogs, Tauri or Electron desktop apps, legacy .iconset/.icns export, Finder/Dock previews, status item or tray template images, small-size legibility checks, or reviews against Apple guidance.

0
installs
▌
Feishu Whiteboard Pro · lcpmarvel bundle
Builds, revises, restyles, and critiques deliberate, editable Feishu / Lark whiteboards from content, references, existing SVGs, or live boards. Use for whiteboards, infographics, diagrams, system maps, timelines, decision boards, posters, and visual explainers that need factual fidelity, strong hierarchy, intentional composition, and evidence-based review rather than a generic grid of equal cards. Routes creation, revision, and critique through separate playbooks; commits to a content-and-design contract before drawing; validates deterministic SVG defects; renders and inspects the actual artifact; and uses an independent final reviewer for material deliveries.

0
installs
▌
Release · lcpmarvel
发布新版本：根据上一个 tag 以来的提交自动推导下一个版本号（feat→minor，否则 patch），bump 三端版本、体检、commit、打 tag 推到 GitHub，由 CI 自动发布 crates.io/PyPI/npm。当用户说"发布一个版本"、"发版"、"release"时使用。不监听 CI 结果。

0
installs
▌
Mineru Prime · lcpmarvel
PDF/DOC/PPT/图片进、干净 Markdown 出——比原生 MinerU 产物更可用。先用 MinerU 官方 API 解析成 content_list，再用 mineru-refine 后处理清洗（伪标题、跨页断句、跨页拆表、乱码表、OCR 形近字、页面家具…），全程机器校验保真、fail-open 不搞崩。当用户说"清洗这个 PDF"、"把这份文档转成干净 markdown"、"解析并清洗"、"用 mineru-prime/mineru-refine 处理"时使用。需要三个 key：MINERU_API_TOKEN / DEEPSEEK_APIKEY / QWEN_APIKEY。

0
installs
▌
Refine Regression · lcpmarvel bundle
整体跑一遍真实测试用例（refine_real，真 LLM），并对比前后产物——content_list.json、refine_report.json、full.md——输出回归报告。当用户想"整体跑一下测试用例并对比前后数据"、验证清洗效果有没有回归时使用。

0
installs

10 published skills