Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add SpaceZephyr/cowrite --skill text-logic-diagramgit clone --depth 1 https://github.com/SpaceZephyr/cowriteWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/spacezephyr/cowrite/text-logic-diagram)<a href="https://agentmods.dev/skills/spacezephyr/cowrite/text-logic-diagram"><img src="https://agentmods.dev/badge/skills/spacezephyr/cowrite/text-logic-diagram/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/spacezephyr/cowrite/text-logic-diagram"><img src="https://agentmods.dev/badge/skills/spacezephyr/cowrite/text-logic-diagram.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.02428 |
| Opus 5 | $0.00044 | $0.01214 |
| Sonnet 5 | $0.00018 | $0.00486 |
| Haiku 4.5 | $0.00009 | $0.00243 |
Grade A, and why
text-logic-diagram scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文本逻辑关系图
将文本转换为精准的逻辑关系 SVG 图，输出为独立 HTML 文件。
触发条件
当用户提到以下场景时，主动使用此技能：
- "生成逻辑图" / "画逻辑关系图" / "文本转图"
- "逻辑拆解" / "拆成图" / "可视化"
- 用户粘贴了文章/段落/论述内容并要求分析逻辑
- "递进图" / "流程图" / "循环图" / "层次图" / "对比图" / "矩阵图"
- 用户要求对文本进行结构化可视化
工作流程
第一步：文本分析
- 通读全文，识别文本中的核心论点、关键概念和逻辑链条
- 段落拆解，将文本按自然段落或逻辑段落分割
- 判断关系类型，为每个段落选择最适合的逻辑关系：
| 关系类型 | 适用场景 | 视觉特征 |
|---|---|---|
| 递进关系 | 概念渐进发展、层层深入 | 阶梯式排列，箭头从左到右或从上到下 |
| 流程关系 | 步骤顺序、阶段推进 | 线性/蛇形排列，带编号的节点 |
| 循环关系 | 概念循环往复、闭环反馈 | 环形排列，首尾相连 |
| 层次结构 | 包含、从属、分类关系 | 树形/金字塔/嵌套结构 |
| 对比关系 | 对照、比较、优劣分析 | 左右/上下对称排列 |
| 矩阵关系 | 多维度交叉、复杂关联 | 网格/象限布局 |
第二步：概念抽象
- 提取关键词：从每个段落中提取 2-6 个核心概念
- 精简文字：每个概念节点文字控制在 15 字以内
- 标注关系：概念之间的连接线和箭头标注简要说明
- 分层整理：区分主要概念和次要概念
第三步：生成 SVG 图
根据分析结果，使用本技能的设计规范生成 HTML 文件。
多段拆解规则：
- 当文本包含多个独立逻辑段落时，生成多张 SVG 图
- 每张图使用独立的
<div class="diagram-card">容器 - 每张图上方标注段落标题或逻辑类型
- 所有图按顺序排列在同一 HTML 文件中
设计系统
主题系统
支持深色和浅色主题切换，默认深色。
深色主题（默认）
| 元素 | 颜色 |
|---|---|
| 页面背景 | #0a0a0a |
| 卡片背景 | #141414 |
| 节点填充主色 | #1a2332 → #243447 |
| 节点描边 | #3f72af |
| 主文字 | #ffffff |
| 副文字 | #8899aa |
| 连接线 | #556677 |
| 箭头 | #8899aa |
| 强调色 | #3f72af (蓝), #5dade2 (亮蓝) |
浅色主题
| 元素 | 颜色 |
|---|---|
| 页面背景 | #f5f7fa |
| 卡片背景 | #ffffff |
| 节点填充主色 | #e8edf2 → #dbe2ef |
| 节点描边 | #3f72af |
| 主文字 | #112d4e |
| 副文字 | #4a6785 |
| 连接线 | #aabbcc |
| 箭头 | #8899aa |
| 强调色 | #3f72af (蓝), #112d4e (深蓝) |
字体规范
- 全局使用 JetBrains Mono 等宽字体
- 节点标题：14px，font-weight 600
- 节点子标签：11px，font-weight 400
- 连接线标注：10px
- 段落标题：16px，font-weight 700
- 图例文字：10px
SVG 规范
通用规范
- 画布尺寸：每张图 viewBox
0 0 800 500，按需调整 - 内边距：上下左右各留 40px
- 箭头标记：小巧箭头，线宽 1
- 阴影效果：轻微阴影
dx=1.5, dy=1.5, stdDeviation=2
节点样式
<!-- 带阴影的圆角矩形节点 -->
<rect x="X" y="Y" width="W" height="H" rx="8"
fill="url(#nodeGrad)" stroke="#3f72af" stroke-width="1.5"
filter="url(#shadow)"/>
<text x="CX" y="CY" class="text-primary" font-size="14" font-weight="600"
text-anchor="middle">概念名称</text>
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 235 lines · 88 tokens per session scan A 11efb6675a8a
text-logic-diagram is a skill published in the GitHub repository SpaceZephyr/cowrite (91 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 2,428 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
plan
Use when a request needs shaping before any code is written — a rough or vague prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. One chain-starter that amplifies the prompt, designs the approach, and decomposes it into a batched task file, skipping whichever phases the request…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
dstack-prototyping
Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final…
llm-icon-finder
Finding and accessing AI/LLM model brand icons from lobe-icons library. Use when users need icon URLs, want to download brand logos for AI models/providers/applications (Claude, GPT, Gemini, etc.), or request icons in SVG/PNG/WEBP formats.
ss-dial
Turn ONE design axis up or down as a coordinated, deterministic transform — "denser", "sharper corners", "more muted", "bolder", "flatter", "livelier". Not a vibe the model reinterprets each time; a defined ramp that moves many tokens together, respects the guardrails (8px grid, a11y floors, single accent…
ss-reference
Compile screenshots, URLs, Figma exports, or an existing UI into a project-local StyleSeed output grammar with evidence, tokens, confidence, anti-patterns, and a validation screen. Use when the user supplies a design reference that StyleSeed does not already model.