agentCLAWHUBUnverified
academic-figures
Publication-ready scientific figures from one command — 25 chart types (bar, slope, volcano, grouped bar, scatter, heatmap, forest plot, KM survival curve (Kaplan-Meier, ROC, violin, box, composite panels, PRISMA 2020 flow, funnel, Bland-Altman, PCA, venn 2-4 sets, upset set intersections (5+ sets), clustered heatmap, dual-axis, Cox multi-variable regression forest), 9 themes incl. colorblind-safe Okabe-Ito and NEJM/Lancet/Science journal palettes, 9 journal submission presets, YAML figure pipeline (a whole paper in one command), multi-format export (TIFF/PNG/PDF in one run), Python API, --wizard chart picker, render watchdog with auto-degrade retry, reviewer-style --annotate arrows, PDF text-overlap + font-size gates, 600dpi output. 100% local — data never leaves your machine.
OpenClaw
Rank
62
Safety
84
Downloads
3.0k
Updated
Oct 9, 2026
Version
4.7.0
Source
CLAWHUB
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 3K downloads reported by the source. Last updated 10/9/2026.
Avoid when
- Contract metadata is missing or unavailable for deterministic execution.
Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing
Public facts
Every fact links back to the source it came from.
- Vendor
- Clawhubvendor · observed Oct 9, 2026
- Protocol compatibility
- OpenClawcompatibility · observed Oct 9, 2026
- Adoption signal
- 3K downloadsadoption · observed Oct 9, 2026
- Latest release
- 4.7.0release · observed Oct 8, 2026
- Handshake status
- UNKNOWNsecurity
Install and run
Setup complexity: low.
clawhub skill install s17dagtwyk21qs6vpz98bzcrh1853t29:academic-figures- Install using `clawhub skill install s17dagtwyk21qs6vpz98bzcrh1853t29:academic-figures` in an isolated environment before connecting it to live workloads.
- No published capability contract is available yet, so validate auth and request/response behavior manually.
- Review the upstream CLAWHUB listing at https://clawhub.ai/docsor1212/academic-figures before using production credentials.
Contract: missing
curl -s "https://www.xpersona.co/api/v1/agents/clawhub-docsor1212-academic-figures/snapshot"
Documentation
CLAWHUB
160,000 characters of source documentation, loaded on request.
Extracted files
5 files captured from the source.
SKILL.md
---
name: academic-figures
description: >-
Publication-ready scientific figures from one command — 25 chart types (bar, slope, volcano,
grouped bar, scatter, heatmap, forest plot, KM survival curve (Kaplan-Meier, ROC,
violin, box, composite panels, PRISMA 2020 flow, funnel, Bland-Altman, PCA,
venn 2-4 sets, upset set intersections (5+ sets), clustered heatmap, dual-axis,
Cox multi-variable regression forest), 9 themes incl. colorblind-safe Okabe-Ito and NEJM/Lancet/Science
journal palettes, 9 journal submission presets, YAML figure pipeline (a whole
paper in one command), multi-format export (TIFF/PNG/PDF in one run), Python
API, --wizard chart picker, render watchdog with auto-degrade retry,
reviewer-style --annotate arrows, PDF text-overlap + font-size gates, 600dpi
output. 100% local — data never leaves your machine.
when_to_use: >-
Use when making or generating any figure or chart from data (bar chart,
scatter plot, heatmap, forest plot, Kaplan-Meier / survival curve, ROC curve,
violin / box plot, composite multi-panel figure, flow diagram, PRISMA /
systematic review flow, meta-analysis funnel, venn / Euler diagram, PCA,
Bland-Altman; when exporting publication- or journal-ready figures (600dpi,
colorblind-safe); or when turning a JSON/CSV/Excel data file into an
academic figure.
---
<!--
═══════════ Metadata archive (2026-09-13 frontmatter normalization) ═══════════
ZCode skill auto-discovery only reads the frontmatter whitelist keys:
name / description / when_to_use / license / metadata
and a description over 1024 characters is silently dropped (root cause of the
v2.x auto-discovery failure: v2.4 had 1035 chars, v2.5 initial 1253).
The following keys were moved out of frontmatter (info preserved):
version: 4.7.0
date: 2026-10-09
author: docsor1212
metadata: {clawdbot: {emoji: "📊", category: visualization}}
requires: {python: ">=3.8", pip: [matplotlib, numpy, pymupdf, scipy, openpyxl]}
Runtime deps: requirements.txt and scripts/setup_env.py; history: Version History below.
═════════════════════════════════════════════════════════════════
-->
# Academic Figures — Publication-Quality Chart Generator
Generate figures from JSON/CSV/Excel data. Local execution, no data leaves the machine.
> ⚡ **Top-3 boundaries**: add `--verify` for submission PDFs (PDF only); `--journal`
> locks the figure width (`--width` is ignored); cluster_heatmap >3000 rows auto-downsamples
> to 2000.
**One command, verified output:**
```bash
python3 scripts/gen_figure.py -t bar -d data.json -o fig.pdf --theme okabe-ito --verify
# 或一键投稿包（自动加 --verify + 色盲安全主题 + pdf,png 多格式，v3.8）
python3 scripts/gen_figure.py -t bar -d data.json -o fig --pub-ready
# exit codes: see "Data Validation & Exit Codes" below; --verify overlap = exit 2 (fix, don't ship)
```
## Quick Start
```bash
# 0️⃣ First run: one-command environment setup (deps/CJK font/font cache/self-check)
python3 scripts/setup_env.py
# 0️⃣ Three ways to get unstuck: wizaexamples/README.md
# Examples — 示例数据与预览 每个 `.json` 都是可直接运行的示例数据，配合 `scripts/gen_figure.py` 使用。 ## 快速体验（推荐） ```bash # 一键环境准备（首次使用） python3 scripts/setup_env.py # 交互演示：选择图表类型，自动用内置数据出图 python3 scripts/gen_figure.py --demo --style glm-hatch --cjk # 查看全部配色（终端内色块预览） python3 scripts/gen_figure.py --list-themes ``` ## 逐图示例 | 文件 | 命令 | 说明 | |------|------|------| | example_bar.json | `python3 scripts/gen_figure.py -t bar -d examples/example_bar.json -o fig.png --cjk` | 分组柱状图（药物疗效） | | example_forest.json | `python3 scripts/gen_figure.py -t forest -d examples/example_forest.json -o fig.pdf --cjk` | Meta 分析森林图 | | example_heatmap.json | `python3 scripts/gen_figure.py -t heatmap -d examples/example_heatmap.json -o fig.png --cjk` | 免疫指标相关热力图 | | example_line.json | `python3 scripts/gen_figure.py -t line -d examples/example_line.json -o fig.png --cjk` | 多组折线图（临床评分） | | example_stacked.json | `python3 scripts/gen_figure.py -t stacked_bar -d examples/example_stacked.json -o fig.png --cjk` | 构成比堆叠柱状图 | ## 真实科研场景示例（realworld/） `examples/realworld/`：贴近论文真实形态的场景数据（含样本量、真实基因名/终点命名惯例）， 可直接作为你论文图 1/2/3 的起点： | 文件 | 命令要点 | 场景 | |------|------|------| | realworld_rct_response.json | `-t grouped_bar --cjk` | RCT 三臂 48 周应答率（n=240） | | realworld_omics_volcano.json | `-t volcano` | RNA-seq 差异表达（干扰素通路） | | realworld_survival_km.json | `-t km --cjk` | IgA 肾病三臂生存曲线（36.5 月随访） | ## GLM 黄蓝斜线风格（招牌风格） ```bash python3 scripts/gen_figure.py -t bar -d examples/example_bar.json -o fig.png --style glm-hatch --cjk ``` `--style glm-hatch` = `--theme glm --hatch`：素雅莫兰迪配色 + 黑色斜纹填充， 打印/黑白场景同样清晰，色盲安全。 ## 配色预览 `previews/swatch_<theme>.png`：7 套配色的色板预览图（glm/classic/okabe-ito/nature/lancet/conservative/cool）。 也可随时用 `--theme-swatch <theme> -o out.png` 重新生成。
mcp/README.md
# academic-figures-mcp
23 种投稿级学术图型的 MCP Server（FastMCP）：bar/line/km（含竞争风险）/forest/roc/slope/composite/prisma…，
本地确定性渲染（同输入同字节）、中文零配置、数据校验+渲染看门狗+退出码语义全继承自
[academic-figures](https://github.com/docsor1212/academic-figures) 引擎。
**边界**：纯本地渲染（零密钥/零遥测/零计费）；600dpi 成品落盘本地路径，MCP 回传仅 ≤150dpi 预览。
## 安装
```bash
# uvx（git 直跑，推荐）
uvx --from "git+https://github.com/docsor1212/academic-figures#subdirectory=mcp" academic-figures-mcp
# 或本地路径
cd academic-figures/mcp && pip install . && academic-figures-mcp
```
## 客户端配置
Claude Code / Claude Desktop（`claude_desktop_config.json`）：
```json
{
"mcpServers": {
"academic-figures": {
"command": "uvx",
"args": ["--from", "git+https://github.com/docsor1212/academic-figures#subdirectory=mcp", "academic-figures-mcp"]
}
}
}
```
Cursor（`~/.cursor/mcp.json`）：同上结构。
Codex：`codex mcp add academic-figures -- uvx --from "git+https://github.com/docsor1212/academic-figures#subdirectory=mcp" academic-figures-mcp`
## Tools
| tool | 说明 |
|---|---|
| `render_chart` | 23 图型渲染：`chart` + `data`（JSON/CSV 文本）+ `options`（title/subtitle/source/xlabel/ylabel/theme/journal/column/verify/peak_label/summary…）+ `dpi`（72–600）+ `fmt`；回预览 base64 + 成品落盘路径；重叠检出返回 `overlap_detected`（修复机制，不交付） |
| `suggest_chart` | 数据驱动图型推荐 |
| `doctor` | 渲染前参数/环境体检（只体检不渲染） |
Resources：`capability://matrix`（23 图型注册表×期刊预设）、`capability://changelog`。
Prompt：`chart_picker`（选图引导）。
## 边界
- 单次调用单图；data ≤ 2MB；dpi 72–600；预览 ≤150dpi；渲染超时 900s
- 需要本地 Python 环境（uvx 自动装依赖；中文字体走系统字体自动探测）
- 不含 Pro 云渲染/计费功能
## 开发
```bash
bash mcp/sync_engine.sh # trunk scripts/ → af_engine/ 镜像（sha 门禁）
python3 -m unittest discover -s mcp/tests -p "test_bounds.py"
python3 mcp/tests/e2e.py # 需 fastmcp + 引擎依赖
```README.md
# Academic Figures [](https://github.com/docsor1212/academic-figures) > **Publication-ready scientific figures from data — one command, verified output.** > 从数据一键生成投稿级论文图表：期刊合规、统计正确、中文零配置、纯本地运行。 [](https://skillhub.cn/skill/academic-figures) [](https://docsor.cn) [](https://opensource.org/licenses/MIT)   **25 chart types** (bar/slope/volcano/upset set-intersections/box/violin/scatter/line/heatmap/ clustered-heatmap/forest/KM/ROC/venn 4-set ellipse/Bland-Altman/PCA/funnel/paired/dual-axis/ stacked/composite/diagram/PRISMA 2020 …) · **9 journal presets** (Nature/Lancet/Science/Cell/NEJM/JAMA/IEEE/CMA/ 中文核心) · **9 color themes** incl. colorblind-safe Okabe-Ito · **600dpi TIFF/PDF/SVG/EPS** · **fully local, zero telemetry**. --- ## Quick Start ```bash # one-command figure (auto-picks the chart type) python3 scripts/gen_figure.py --quick -d data.csv # Nature double-column submission (width/font/DPI per author guidelines) python3 scripts/gen_figure.py -t bar -d data.json -o fig.pdf --journal nature --column double --verify # Cox multi-variable regression forest (raw per-subject data; Efron + PH test) python3 scripts/gen_figure.py -t forest -d patient.csv --stats cox --cox-time time --cox-event event --cox-cols "age,sex,treat" # Chinese zero-config (auto CJK font detection) python3 scripts/gen_figure.py -t km -d survival.json -o km.png --cjk ``` ## Why academic-figures - **Journal compliance built-in**: column widths, font sizes and DPI from official author guidelines; `--verify` pixel-level text-overlap gate; `audit_pdf.py` font-size gate — the hard desk-reject reasons are guarded mechanically. - **Statistical correctness**: Cox (Efron ties + PH test), KM (risk table, log-rank, median survival 95% CI), ROC (DeLong), metafunnel (Egger) — all validated against reference implementations (lifelines) to machine precision. - **Chinese zero-config**: CJK font auto-detection, CMA/中文核心 presets, Chinese diagnostics for every error (graded exit codes 0-6). - **Safe by construction**: fully local rendering, no network requests, no telemetry. See SKILL.md "Safety & Data" statement. ## Docs - Full docs: `SKILL.md` (EN) · 中文文档见 SkillHub 页面 - Getting started: `references/quickstart.md` · One-page cheatsheet: `references/cheatsheet.md` · Limits & flag interactions: `references/limits.md` - Scenario templates: `templates/` (23, each with a ready-to-run command) - Regression suite: `tests/run_tests.py` (297 tests) ## Install ```bash git clone https://github.com/docsor1212/academic-figures.git cd academic-figures python3
templates/README.md
# 模板库（v2.6 全图型覆盖） 25 个端到端模板 = 场景数据 JSON + 推荐命令 + 图注模板，**覆盖全部 25 种图型**（v4.4 增 volcano，v4.7 增 upset）。用法： ```bash cp templates/01-meta-forest.json my_data.json # 编辑 my_data.json，把示例数字换成你的真实数据 python3 scripts/gen_figure.py -t forest -d my_data.json -o forest.pdf --theme okabe-ito --verify ``` ## 场景模板（01–16） | 模板 | 场景 | 图型 | 推荐命令要点 | |---|---|---|---| | 01-meta-forest | 荟萃分析 | forest | enhanced 格式：权重气泡+events 列+异质性脚注 | | 02-rct-baseline-bar | RCT 结局对比 | bar | +journal jama；significance 手工标注 | | 03-survival-km | 生存分析 | km | 风险表+log-rank 自动标注 | | 04-diagnostic-roc | 诊断试验 | roc | 多曲线 AUC 自动标注 | | 05-correlation-heatmap | 变量相关 | heatmap | RdBu_r ±1 | | 06-prisma-review | 系统综述筛选 | prisma | 算术自检，对不上拒绝出图 | | 07-dose-response-line | 剂量-反应 | line | 误差带 | | 08-panel-composite | 期刊主图 | composite | A/B/C 面板；--alt 生成图注描述 | | 09-survey-stacked | 构成比 | stacked_bar | 百分比 + 总数 | | 10-cn-journal-hbar | 中文期刊横柱 | hbar | --journal cn-core 自动开中文；--alt | | 11-rct-grouped-bar | 两组×多时点对比 | grouped_bar | 误差棒+显著性标注 | | 12-dose-response-scatter | 浓度-反应分组散点 | scatter | groups 分色+趋势线 | | 13-qol-box | 评分分布比较 | box | --stats auto 显著性括号 | | 14-cytokine-violin | 分布形状对比 | violin | --stats multi 全两两 | | 15-lab-trend-dual-axis | 双轴指标趋势 | dual_axis | 左右轴各一系列 | | 16-study-design-diagram | 研究设计/CONSORT | diagram | blocks+arrows 定位 | ## 图型速查模板（按图型命名，覆盖其余 9 种） | 模板 | 图型 | 模板 | 图型 | |---|---|---|---| | bland_altman.json | bland_altman 一致性 | pca.json | pca 得分图 | | cluster_heatmap.json | cluster_heatmap 聚类热图 | paired.json | paired 配对变化 | | funnel.json | funnel 漏斗图 | venn.json | venn 韦恩/欧拉图 | | slope.json | slope 斜率图（两时点） | upset.json | upset 集合交集图（v4.7） | | volcano.json | volcano 火山图 | — | — | > v2.6 起模板与图型一一对应（v4.7 增 upset）；不确定用哪个图型可对数据跑 > `python3 scripts/gen_figure.py --suggest -d 你的数据.json`。 每个 JSON 顶部有 `_scene/_chart_type/_command/_caption_template` 元字段，渲染时会被忽略。 示例数字仅示意，发表前请替换为真实数据。
Github ReposUpdated 6mo agoRank 70
activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
OPENCLAW
Github ReposUpdated 6mo agoRank 70
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants.
MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70
AionUi
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
OPENCLAW
Machine-readable data
The same record, as JSON, for agents and crawlers.
{
"facts": [
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Clawhub",
"href": "https://clawhub.ai/docsor1212/skills/academic-figures",
"sourceUrl": "https://clawhub.ai/docsor1212/skills/academic-figures",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-09T10:16:10.595Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-docsor1212-academic-figures/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-docsor1212-academic-figures/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-09T10:16:10.595Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "3K downloads",
"href": "https://clawhub.ai/docsor1212/academic-figures",
"sourceUrl": "https://clawhub.ai/docsor1212/academic-figures",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-09T10:16:10.595Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "4.7.0",
"href": "https://clawhub.ai/docsor1212/academic-figures",
"sourceUrl": "https://clawhub.ai/docsor1212/academic-figures",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-10-08T19:28:21.897Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-docsor1212-academic-figures/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-docsor1212-academic-figures/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 4.7.0",
"description": "v4.7.0 new chart type + scenario guides: (1) chart #25 upset - the UpSet set-intersection plot for 5+ sets (standard successor to venn 2-4 sets): intersection-size bars aligned above membership dot columns + set-size bars, deterministic size/degree sort, top_n/min_size control, truncated intersections reported on stderr; (2) two reviewer-facing scenario guides - color-guide.md (data semantics to color order to theme to grayscale self-check) and combo-guide.md (composite vs pipeline, multi-figure consistency); (3) FAQ systematically indexed (data/parameter/submission/environment), pitfalls adds rejection-prone color misuse and statistical-method misuse sections; (4) three real-world research examples (RCT n=240, RNA-seq DE, 3-arm KM 36.5-month follow-up); (5) limits.md quick-reference table. Includes all v4.6.0 content. Feel free to Star on GitHub or bookmark the SkillHub page.",
"href": "https://clawhub.ai/docsor1212/academic-figures",
"sourceUrl": "https://clawhub.ai/docsor1212/academic-figures",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-10-08T19:28:21.897Z",
"isPublic": true
}
]
}Record generated Oct 9, 2026.