wuxinbo-bo/math-model-skills/evidence-visualization

Claude Code and agent skill by wuxinbo-bo/math-model-skills

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Meta-model-agent 将计算成果转换为可发表的数据图形、表格和排版引用。适用于证据图谱构建。

Install

npx vskill@latest install wuxinbo-bo/math-model-skills/evidence-visualization

SKILL.md

证据图谱构建

稳定执行契约

  • 执行目标：把已冻结的计算结果转换为可核验、可复用、可直接入文的图形与表格证据。
  • 调用参数：[visual-plan-or-data-path]。
  • 权威输入：计算结果.md、图表/全部结果.json、逐问结果文件与用户图表要求。
  • 允许交付：图表/中的数据图、表格和图表引用.tex；不得改写上游数值。
  • 禁止写入：不得越权修改已冻结的上游事实、用户原始文件或本协议未授权的目录。
  • 可用工具边界：Bash(*), Read, Write, Edit, Grep, Glob, Agent。
  • 最小交付：每项核心结论至少有匹配的图或表、可追溯数据源、中文标注与论文引用入口。
  • 恢复入口：优先读取当前工作、状态记录和已有产物，从最近一次通过门禁的位置继续。
  • 失败回退：缺少结果或口径冲突时停止绘图并回退计算实现；不得臆造数据补齐视觉效果。
  • 收口顺序：先核对输入，再完成产物，再运行本环节门禁，最后登记状态；门禁未通过不得宣告完成。

Produce visuals and tables from data: $ARGUMENTS

运行参数

  • FIG_DIR = `图表/`
  • FORMAT = `pdf` (vector, suitable for LaTeX)
  • DPI = 300
  • CUSTOM_REQUIREMENTS — User-specified requirements, highest priority.

<tools_and_style>

工具与表达规范

shared-scripts/plot_utils.py 提供学术绘图的基础样式。Meta-model-agent 可按任务需要选用其中的辅助函数、仅调用 setup_style() 后直接使用 matplotlib，或完全采用自定义实现。

Quality floor: 300 DPI PDF, no in-visual title (plt.title), font ≥9pt, grayscale-distinguishable.

Color palette and recipes: read 工具/figure_style_guide.md (color schemes) and 工具/figure_recipes_*.md (implementation examples).

plot_utils functions: setup_style, save_fig, heatmap, forest_plot, trend_plot, bar_compare, distribution_plot, scatter_plot, residual_diagnostic, multi_line_plot, box_plot, radar_plot, subplot_grid

Stats tables: stats_utils.py supplies regression_table, descriptive_table, correlation_table.

</tools_and_style>

⛔⛔⛔ 交付契约（最高优先级）

除 图表/图表引用.tex 外，必须生成 图表/figure_manifest.json。figures 与 tables 均登记 path、question、visual_role、claim、source、result_keys、reader_task、publish 和 placement，表格可另登记 label。visual_role 取 mechanism/result/validation/decision/diagnostic；只有 publish=true 的图表必须嵌入正文，诊断、调试、完整长表和被替代资产登记为 publish=false。

json
{
  "version": 1,
  "figures": [
    {
      "path": "图表/fig_q1_sensitivity.pdf",
      "question": "Q1",
      "visual_role": "validation",
      "claim": "参数扰动不改变最优方案排序",
      "source": "图表/全部结果.json",
      "result_keys": ["Q1.validation.sensitivity"],
      "reader_task": "比较趋势与稳定区间",
      "publish": true,
      "placement": "body"
    }
  ],
  "tables": [
    {
      "path": "图表/TABLE_q1_solution.tex",
      "label": "tab:q1-solution",
      "question": "Q1",
      "visual_role": "result",
      "claim": "最优方案满足全部约束并优于基线",
      "source": "图表/全部结果.json",
      "result_keys": ["Q1.solution", "Q1.validation.residual"],
      "reader_task": "核对关键决策值与约束余量",
      "publish": true,
      "placement": "body"
    }
  ]
}

正文图表按论证需要组织为“机制 -> 结果 -> 验证/决策”，不是每问机械凑齐三张。所有生成的 TABLE_*.tex/md 必须进入 tables 分类，但只有 publish=true 的摘要表进入正文；相同数据和相同结论的重复资产不得通过更换形式伪装成新证据。

Must produce all planned visuals (per 论文规划.md or skill-specific plan) as 图表/fig_*.png/pdf plus 图表/图表引用.tex (or, in docx mode, the same PNGs without 图表引用.tex requirement).

⛔ 特殊豁免：若 论文规划.md 清晰标明写"无图形与表格"或图形与表格清单为空（纯文字综述/思辨论文），准许 图表/ 为空，但务必写一个空的 图表/图表引用.tex (touch 图表/图表引用.tex; mkdir -p 图表) 让下游知道这步跑过了。

⛔ MUST run output verification prior to ending:

bash
 
PASS=true
 
mkdir -p 图表
 
FIG_PNG=$(ls 图表/fig_*.png 2>/dev/null | wc -l)
 
FIG_PDF=$(ls 图表/fig_*.pdf 2>/dev/null | wc -l)
 
TOTAL=$((FIG_PNG + FIG_PDF))
 
# 检查规划是否要求图表
 
PLAN_HAS_FIG=$(grep -E '^\s*-?\s*fig_|图表清单|图表/fig_' 论文规划.md 2>/dev/null | wc -l)
 
if [ "$TOTAL" -ge 1 ]; then
 
    echo "✅ 图表/fig_*.png/pdf ($TOTAL)"
 
elif [ "$PLAN_HAS_FIG" -eq 0 ]; then
 
    echo "✓ 规划无图表, 创建占位 图表引用.tex"
 
    touch 图表/图表引用.tex
 
else
 
    echo "❌ 规划要求图表但未生成"
 
    PASS=false
 
fi
 
MODE=$(grep -q "Word（.docx）\|docx mode" META_MODEL_AGENT.md 2>/dev/null && echo docx || echo pdf)
 
if [ "$MODE" = "pdf" ] && [ ! -f 图表/图表引用.tex ]; then
 
    touch 图表/图表引用.tex
 
fi
 
[ "$PASS" != true ] && echo "⛔ Output verification FAILED — must complete before ending"

执行流程

工作节点 0：恢复核验（断线重跑必读）

⛔ 当前环节可能由于断线/人工重跑被多次启动。每一次启动前务必先扫描已有产物：

bash
 
echo "=== 工作区扫描 ==="
 
HAS_PNG=$(ls 图表/fig_*.png 2>/dev/null | wc -l)
 
HAS_PDF=$(ls 图表/fig_*.pdf 2>/dev/null | wc -l)
 
HAS_TIKZ=$(ls 图表/tikz_*.pdf 2>/dev/null | wc -l)
 
HAS_INCLUDES=$([ -f 图表/图表引用.tex ] && wc -c < 图表/图表引用.tex || echo 0)
 
echo "  fig_*.png: $HAS_PNG, fig_*.pdf: $HAS_PDF, tikz_*.pdf: $HAS_TIKZ"
 
echo "  图表引用.tex: $HAS_INCLUDES bytes"

依据扫描结果决定行动：

⛔ 铁律：

  • 已有 `图表/fig_*.png/pdf` 避免重画（覆盖会让审稿人看到的图变了）
  • 已有的 `图表/TABLE_*.md/tex` 避免重写（数据已固化）
  • 只补缺失的图 / 表
工作节点 1：Read manuscript structure + data discovery
  1. Consult the full style guide (color schemes + visual selection decision table + anti-patterns + DrawIO/TikZ color schemes — all in one file):
bash
 
cat 工具/figure_style_guide.md 2>/dev/null || cat skills/shared-scripts/figure_style_guide.md
  1. Scan recipe file headings to know what templates are available:
bash
 
echo "=== Advanced ==="
 
(cat 工具/figure_recipes_advanced.md 2>/dev/null || cat skills/shared-scripts/figure_recipes_advanced.md 2>/dev/null) | grep '^## '
 
echo "=== Basic ==="
 
(cat 工具/figure_recipes_basic.md 2>/dev/null || cat skills/shared-scripts/figure_recipes_basic.md 2>/dev/null) | grep '^## '
 
echo "=== Academic ==="
 
(cat 工具/figure_recipes_academic.md 2>/dev/null || cat skills/shared-scripts/figure_recipes_academic.md 2>/dev/null) | grep '^## '
 
echo "=== Competition ==="
 
(cat 工具/figure_recipes_competition.md 2>/dev/null || cat skills/shared-scripts/figure_recipes_competition.md 2>/dev/null) | grep '^## '
 
echo "=== Empirical ==="
 
(cat 工具/figure_recipes_empirical.md 2>/dev/null || cat skills/shared-scripts/figure_recipes_empirical.md 2>/dev/null) | grep '^## '
 
echo "=== Basic (fallback only) ==="
 
(cat 工具/figure_recipes_basic.md 2>/dev/null || cat skills/shared-scripts/figure_recipes_basic.md 2>/dev/null) | grep '^## '
  1. ⛔ MANDATORY: Extract the COMPLETE visual plan from planning docs. Read ALL planning docs and extract every planned visual/table into a numbered checklist:
bash
 
echo "=== Extracting figure plan ==="
 
for plan in 论文规划.md 问题分析.md 选题规划.md 建模报告.md; do
 
    [ -f "$plan" ] || continue
 
    echo "--- $plan ---"
 
    cat "$plan"
 
done

Following reading, output a FIGURE PLAN CHECKLIST like this (you MUST produce this prior to proceeding):

 
FIGURE PLAN CHECKLIST (from planning docs):
 
[ ] 1. fig_xxx — Descriptive stats distribution (Rain Cloud) — data: results.json
 
[ ] 2. fig_yyy — Model comparison radar (Radar) — data: results.json
 
[ ] 3. fig_zzz — Regression coefficient forest plot (Forest Plot) — data: results.json
 
[ ] 4. TABLE_desc — Descriptive statistics table — data: results.json
 
[ ] 5. TABLE_reg — Regression results table — data: results.json
 
[ ] 6. drawio_roadmap — Technical roadmap (DrawIO)
 
Total planned: 6 figures + 2 tables + 1 DrawIO

Every item in the plan MUST appear in this checklist. If the plan says "12 visuals", the checklist is expected to include 12 entries.

3.5. ⛔ JSON 数据完整性核验（保证数据能支撑全部图形与表格）：

bash
 
echo "=== JSON 数据完整性检查 ==="
 
if [ -f 图表/全部结果.json ]; then
 
    python3 -c "
 
import json
 
with open('图表/全部结果.json', 'r') as f:
 
    data = json.load(f)
 
# 列出所有顶层 key
 
keys = list(data.keys()) if isinstance(data, dict) else [f'[{i}]' for i in range(min(len(data), 10))]
 
print(f'JSON 顶层 key ({len(keys)} 个): {keys}')
 
# 检查是否有空值
 
def verify_empty(obj, path=''):
 
    issues = []
 
    if isinstance(obj, dict):
 
        for k, v in obj.items():
 
            if v is None or v == '' or v == []:
 
                issues.append(f'{path}.{k} 为空')
 
            else:
 
                issues.extend(verify_empty(v, f'{path}.{k}'))
 
    elif isinstance(obj, list) and len(obj) == 0:
 
        issues.append(f'{path} 为空列表')
 
    return issues
 
issues = verify_empty(data)
 
if issues:
 
    print(f'⚠ 发现 {len(issues)} 个空值:')
 
    for i in issues[:5]:
 
        print(f'  - {i}')
 
else:
 
    print('✅ JSON 数据无空值')
 
" 2>/dev/null
 
else
 
    echo "⚠ 图表/全部结果.json 不存在，图表将缺少数据支撑"
 
fi
 
# 检查各子问题的结果文件
 
for f in 图表/problem_*_结果.json; do
 
    [ -f "$f" ] && echo "✅ $(basename $f) 存在" || true
 
done
  1. Scan data files (用户数据/ > 图表/ > root). ⛔ 避免 `cat` 或 `print()` 全部 JSON 文件——大 JSON 会撑爆上下文。 只用以下方式扫描：
bash
 
ls -la 图表/*.json 2>/dev/null
 
python3 -c "
 
import json, os
 
def summarize(v, depth=0):
 
    if isinstance(v, list):
 
        n = len(v)
 
        nulls = sum(1 for x in v if x is None)
 
        nums = [x for x in v if isinstance(x, (int,float)) and x is not None]
 
        if nums:
 
            return f'list[{n}] nulls={nulls} range=[{min(nums):.4g}, {max(nums):.4g}] sample={v[:3]}'
 
        elif v and isinstance(v[0], dict):
 
            return f'list[{n}] of dict, keys={list(v[0].keys())[:8]}'
 
        return f'list[{n}] sample={str(v[:3])[:100]}'
 
    elif isinstance(v, dict) and depth < 2:
 
        items = []
 
        for k2, v2 in list(v.items())[:6]:
 
            items.append(f'{k2}: {summarize(v2, depth+1)}')
 
        return 'dict{' + ', '.join(items) + '}'
 
    return f'{type(v).__name__}={str(v)[:60]}'
 
for f in sorted(os.listdir('图表')):
 
    if not f.endswith('.json'): continue
 
    sz = os.path.getsize(f'图表/{f}')
 
    with open(f'图表/{f}') as fh: d = json.load(fh)
 
    print(f'\n=== {f} ({sz//1024}KB) ===')
 
    if isinstance(d, dict):
 
        for k, v in list(d.items())[:10]:
 
            print(f'  {k}: {summarize(v)}')
 
    elif isinstance(d, list):
 
        print(f'  {summarize(d)}')
 
"

Every visual in the plan is expected to be generated — the actual count can exceed the plan but not fall short.

<supplement_mode>

Supplement mode: if 图表/ already has ≥3 PDFs + 图表引用.tex from a previous step (e.g., experiment-bridge):

  1. Compare existing PDFs against the FIGURE PLAN CHECKLIST
  1. Validate quality of each existing PDF (valid chart type, uses PALETTE, valid language labels)
  1. Regenerate any visual that fails quality validate
  1. Produce any planned visual that doesn't exist yet
  1. Always produce DrawIO architecture diagrams
  1. Always regenerate 图表引用.tex to include ALL visuals

Normal mode (no existing PDFs — this is the default for stats modeling since computational-realization only outputs JSON):

Produce all visuals from scratch using JSON data in 图表/*.json.

</supplement_mode>

工作节点 1.5：Produce AI Image visuals (non-data visuals)

AI Image 默认关闭。仅当题目确有无法用数据图、DrawIO 或 TikZ 准确表达的物理场景，并且用户明确需要场景示意时才启用；技术路线图、流程图和模型架构图严禁使用生成式图片。

1. AI Image 不得直接采用，必须进行内容级预核验：

API Key 已通过配置文件 工具/_ai_image_config.json 注入（用户在设定页面配置，后端自动化写入）。

直接调用即可。成功就用，失败 3 次后 DrawIO 兜底。不需检测 Python 或核验环境变量。

bash
 
# Python 路径：MH_PYTHON 由后端注入，fallback 到系统 python
 
PYTHON="${MH_PYTHON:-$(command -v python3 2>/dev/null || command -v python 2>/dev/null || echo python)}"
 
GPT_IMG=1
 
echo "AI_IMAGE: ready (Python=$PYTHON, config=工具/_ai_image_config.json)"

2. Establish language:

bash
 
# Verify paper language from planning docs（注意：comp_apmcm_zh 是中文赛项，必须先排除）
 
if grep -qi 'comp_apmcm_zh' META_MODEL_AGENT.md 2>/dev/null; then
 
    AIIMG_LANG="zh"
 
elif grep -qi 'MCM\|ICM\|APMCM\|comp_mcm\|comp_apmcm\|comp_certcup_en\|comp_shuwei_en' META_MODEL_AGENT.md 2>/dev/null; then
 
    AIIMG_LANG="en"
 
else
 
    AIIMG_LANG="zh"
 
fi
 
echo "AI Image language: $AIIMG_LANG"

3. Read ALL upstream documents to understand the FINAL methods and outcomes:

bash
 
echo "=== Reading upstream docs for AI Image prompt construction ==="
 
cat 问题分析.md 2>/dev/null | head -500
 
cat 建模报告.md 2>/dev/null | head -500
 
cat 计算结果.md 2>/dev/null | head -200

4. Consult the AI Image plan from 问题分析.md:

bash
 
grep -A 30 'AI Image' 问题分析.md 2>/dev/null

5. For every planned AIIMG visual, construct a prompt and call the tool.

This is the start of the file. Read the full SKILL.md on GitHub.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
90
Repository forks
2
7-day trend score
23

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/wuxinbo-bo/math-model-skills/evidence-visualization/badge)](https://verified-skill.com/skills/wuxinbo-bo/math-model-skills/evidence-visualization)

Something wrong with this skill or its page? Tell us.