liustack
UserThe first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。
Categories
Indexed Skills (10)
modlens
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).
modsearch
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.
pptwise
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.
pptfast
Generate a native, editable PPTX deck from an outline, notes, or a document using the pptfast CLI (semantic IR → validate → render). Use when the user asks to create a PPT, deck, presentation, or slides (做PPT/生成PPT/制作演示文稿/幻灯片) and wants a stable, editable, brand-consistent result rather than freeform drawn slides.
ncwriting
Write restrained Chinese long-form in New Concept Writing Style (NCW, 新概念作文风格): 白描, numbered weights, empty systems that keep running, emotion held in objects not adjectives. Use when the user says 新概念作文 / 新概念作文风格 / 白描 / 克制着写 / 孙宇晨那种 / 用 ncwriting 写 / New Concept Writing / write like a New Concept winner / 写一篇像《我的女友景甜》 / 陈奕迅的歌那种克制, or wants literary Chinese without hot-take energy. Do not trigger for tutorials, tech blogs, marketing copy, or coding.
style-audit
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.
coding
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.
dig
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��� / 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).
shaping
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. 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.
snapshot
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).
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.