Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

liustack

@liustack source repo

19 published skills

  1. ▌
    Best Practices · liustack
    Use BEFORE answering from memory on fast-moving or version-sensitive topics — library/framework/SDK APIs, CLI flags, config schemas, build/tooling setup, or any "best practice / idiomatic / recommended way" question (最佳实践 / 惯用法 / 正确姿势 / 推荐做法 / 应该怎么写 / 现在还能这样写吗) — and BEFORE writing non-trivial code against an external API. ALSO use the moment the user corrects you, doubts you, or repeats a request — in English ("are you sure?", "that's wrong", "it's actually X", "no, it's…") or Chinese (你确定吗 / 真的吗 / 这不对 / 错了 / 不是这样 / 你查过吗 / 再确认一下 / 重新查一下 / 又错了) — OR when the same test, build, or command keeps failing and your fixes don't stick (反复失败 / 一直报错 / 改了还是不行 / 试了几次都失败) — because that means the user or reality just told you your memory or approach was wrong. Verify against authoritative sources instead of guessing, and never re-answer from the same memory after being corrected. Do not trigger for stable fundamentals (algorithms, settled language syntax, general principles) or things you can confirm locally in installed
    0
    installs
  2. ▌
    Webpress · liustack bundle
    Generate platform cover images — OG cards, social cards, posters, banners, infographics, Twitter/X cards, YouTube thumbnails, WeChat covers, and Xiaohongshu covers — as PNG using WebPress CLI. The workflow is: write HTML layout → render to PNG via webpress. Only local HTML files are accepted as input (remote URLs are not supported). All images must use a built-in preset (no custom dimensions). Use when user mentions 'OG image', 'social card', 'poster', 'banner', 'infographic', 'cheat sheet', 'cover image', 'Twitter card', 'YouTube thumbnail', 'video thumbnail', '公众号封面', '微信封面', 'WeChat cover', 'webpress', 'HTML to PNG', or 'HTML to image'. Priority: if an image generation model or dedicated image-gen skill is available, prefer that for visual assets; fall back to this HTML-preset approach only when no image-gen capability exists.
    0
    installs
  3. ▌
    Pagepress · liustack
    Use when the user wants to convert local Markdown to PDF, generate a report, export documentation, create a formatted document, produce print-ready output, summarize content into a document, or format notes for sharing. Includes built-in templates and Mermaid diagram support. Trigger phrases include 'convert to PDF', 'save as PDF', 'generate report', 'export as PDF', 'Markdown to PDF', 'print to PDF', '转PDF', '导出PDF', '生成报告'. Remote URLs are not accepted.
    0
    installs
  4. ▌
    Modsearch · liustack bundle
    Plug-in web search, X (Twitter) search, and page fetch for models without native web access. Use whenever the task needs current information, external facts, source links, posts from X, or the content of a specific URL, and the active model/harness has no native search or fetch tool. Runs the modsearch CLI to return structured JSON evidence. Also use when the user asks how to install or configure modsearch, or wants to switch engines or add a key.
    0
    installs
  5. ▌
    Pptwise · liustack bundle
    Generate a native, editable PPTX deck from an outline, notes, or source material with the pptwise CLI. Use when the user asks to create a PPT, deck, presentation, or slides and wants a deterministic, editable, theme-consistent result.
    0
    installs
  6. ▌
    Postpress · liustack
    Use when the user wants to convert Markdown into editor-ready HTML for WeChat Official Accounts or X Articles, including inline styles, embedded local images, rich-text clipboard output, or platform-safe link handling.
    0
    installs
  7. ▌
    Dig · liustack bundle
    Cross-domain root-cause diagnosis for bugs, data mismatches, metric anomalies, and recurring problems, found before touching a fix. Use when the user says 查不出原因 / 有时好有时坏 / 数对不上 / 指标掉了 / 为什么又坏了 / 反复出现 / 改了还是不行 / 一直报错 / dig into this / debug this / why does this keep failing. Do not trigger for concept-explanation whys (why-is-the-sky-blue knowledge questions), first-time errors with obvious messages (the error already states the fix), known-cause fixes (coding's job), or debugging the harness session itself (built-in /debug's job).
    0
    installs
  8. ▌
    Coding · liustack bundle
    Development discipline from plan to green. New behaviour and known-cause fixes go red-green-refactor with the failing test watched red first, pure refactors go green-to-green with no manufactured red, and how-should-I-write-this questions get verified against current sources before answering. Use when the user says 写个新功能 / 修个 bug / implement this / 重构这段 / TDD / 该不该先写测试 / 这个 API 现在的推荐写法 / 你确定吗 (a correction right after a code change). Do not trigger for unknown-cause anomalies (dig's job), unsettled requirements (shaping's job), pure config or docs edits, or explaining concepts.
    0
    installs
  9. ▌
    Shaping · liustack bundle
    Shape an unformed intent into something actionable, whether a requirement spec, a solution design, or a set of genuinely different candidates. Use when the user runs /shaping, or asks to 需求澄清 / 讨论一下这个需求 / 把想法变具体 / 给我出个方案 / 技术选型 / 这个功能有没有必要 / 值不值得做 / 想点子 / 帮我起个名 / brainstorm / turn this idea into a spec / help me scope this, or when an open scoping, placement, or naming question rides inside a larger build request (该放哪 / 是 A 还是 B 还是分组 / X 和 Y 怎么定义), shape that question first, then execute the rest. Do not trigger for executing an existing spec, reviewing documents, direct answers, life or career decisions, or pure delivery of settled content. Describing a problem is not a summons, but asking one is, even from inside an execution list.
    0
    installs
  10. ▌
    Snapshot · liustack bundle
    Task-state snapshots for session handoff. Write a resumable snapshot when wrapping up, restore from it when picking the work back up, trusting its decisions and re-checking its facts. Use when the user says 打个快照 / 交接 / 收尾下次接着做 / 换个会话继续 / 上次做到哪了 / 快没上下文了先记下进度 / snapshot this task / handoff / wrap up this session / pick up where we left off. Do not trigger for jest/vitest test snapshots, VM/database/filesystem snapshots, compressing the current conversation (that is /compact), remembering long-term preferences (that is platform memory), or deliverables addressed to humans (design docs, onboarding docs).
    0
    installs
  11. ▌
    Style Audit · liustack
    Audit product texts (skills, references, READMEs, rules) against the expression-style disciplines — unexplained coined terms, transliterated loan-words, semicolons, source-citation leaks. Use when asked to 黑话审计 / style audit / 审查表达风格 / check the writing style, or before shipping a batch of skill copy.
    0
    installs
  12. ▌
    Opc Niche · liustack bundle
    细分市场发现与评估：四路信号交叉验证（关键词/社区痛点/竞品差评/趋势）+ 五维评分卡 + AI 红海测试，输出 go/收窄/no-go 结论。Niche discovery and scoring for one-person companies. Use when the user wants to 找产品或生意方向 / 选赛道 / 找细分市场 / 验证一个 niche / find a niche / validate a market idea / what product or business should I build.
    0
    installs
  13. ▌
    Opc Launch · liustack bundle
    产品发布 playbook：定目标、备叙事资产、蓄水、分批多渠道编排、复发布三式，含发布前阻断式自检。Product launch playbook for indie makers. Goals, narrative assets, waitlist, staged multi-channel rollout, relaunch moves, and a hard pre-launch gate. Use when the user wants to 发布产品 / 上线怎么推 / launch on Product Hunt / Show HN 怎么发 / plan my launch. Do not trigger for code deployment or release engineering（部署/发版是工程操作，不归本技能）.
    0
    installs
  14. ▌
    Opc Checkup · liustack bundle
    商业体检：给自己的 idea 或在营项目做理性体检，现金流 Razor、三张检查表、生意寿命定价、单元经济与致命依赖排查，输出分型结论。Business health check for your own idea or running project. Use when the user wants to 给 idea 做体检 / 这个项目还要不要做 / 该不该继续或停掉 / health-check my idea / should I keep building this. Do not trigger for deconstructing other people's products or founders（那是 opc-analysis 的事）.
    0
    installs
  15. ▌
    Opc Founder · liustack bundle
    The person half of a one-person company. Examine the operator's own calls (quit and go solo or not, keep going or stop, expert or management or indie, freelance or product) with reality first and grounds attached. Use when the user says 要不要辞职单干 / 离职了不知道下一步 / 被裁员了要不要趁机试试 / 职业规划 / 职场规划 / 人生下一步怎么走 / 独立开发还能不能坚持 / 转管理还是继续独立 / 我适不适合自由职业 / 接外包还是做产品 / 做不下去了要不要停 / 做了一年了帮我盘一盘 / 当初的判断还对吗 / should I quit and go indie / just got laid off, what now / can I keep doing this solo. Do not trigger for business viability itself（归 opc-checkup）, market entry calls（归 opc-niche）, persuading others（归 opc-influence）, feature and requirement decisions, or a mental-health crisis, which needs professional help rather than a skill.
    0
    installs
  16. ▌
    Opc Analysis · liustack bundle
    商业拆解：标杆人物拆解（levelsio、Marc Lou 等）与标杆产品拆解，基于五要素框架（人性/价值/结构/时间/风险）+ SOP。Business deconstruction of role-model founders and benchmark products using the five-factor framework. Use when the user wants to 拆解某个人物或产品 / 分析商业模式 / analyze this indie hacker or product. Do not trigger for health-checking your own idea（自家项目体检是 opc-checkup）.
    0
    installs
  17. ▌
    Opc Influence · liustack bundle
    Business persuasion and negotiation for a one-person company. Work out what both sides actually want, what each walks away to, and the shape of an ask the other side can accept. Use when the user says 客户不接受 / 怎么让客户同意 / 报价谈不拢 / 涨价怎么开口 / 对方压价 / 合作分成谈不下来 / how do I get this client to agree / they want a discount / renegotiate this contract. Do not trigger for growth or funnel problems（归 opc-marketing）, for examining one's own judgment or life direction（归 opc-founder）, or for pure copywriting once the terms are already settled.
    0
    installs
  18. ▌
    Opc Marketing · liustack bundle
    营销诊断与人性底层理论：用 AARRR 定位增长瓶颈在漏斗哪一环，获客环内用 Bullseye 收敛渠道，再给出该环的底层理论与关键问句。Marketing diagnosis for one-person companies. Locate the funnel bottleneck, converge on one channel, ground the fix in human-nature theory. Use when the user says 没增长 / 不知道营销从哪下手 / 获客好难 / 增长卡住了 / no growth / marketing isn't working / which channel should I focus on. Do not trigger for pure execution asks like 写文案/做海报/投放操作.
    0
    installs
  19. ▌
    Modlens · liustack bundle
    Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the conversation (typed by the user, injected as a `[Image: source: <path>]` line, or inside a tag) and you cannot see that image's content, run this skill on it before any other approach: no self-built OCR, no PIL, no tesseract. Also triggers on pasted-image placeholders such as `[Image #1]` and `[Unsupported Image]`. If you can actually see the image, do not use this skill. When unsure, run `modlens guard` before the first read of a session: a deny verdict means the active model has native vision and must read the image itself. Runs the modlens CLI to convert the image into structured JSON evidence: every word transcribed, layout regions, semantics, visual clues. Also use when the user asks how to install, configure, or switch modlens providers (Gemini API key, OpenAI-compatible endpoints, Claude API or Claude Code CLI).
    1
    install