Skip to content

joshua-zyy/academic-paper-writer / skills/academic-figure

academic-figure

Verified

Create, revise, or audit academic data/result figures for CS/AI/ML papers. Data/result plots default to Python-generated editable SVG with CS/AI/ML-specific design rules for benchmarks, ablations, training dynamics, robustness, diagnostics, distributions, confusion matrices, and efficiency tradeoffs. Use when: generating plots from experiment results or numeric data, auditing publication figures, suggesting data-driven figure types, revising chart colors/layouts/labels, or preparing figure QA reports. Model framework diagrams, architecture diagrams, overview diagrams, and complex mechanism schematics are outside this skill's automatic drawing scope; provide only manual figure requirements or caption/blueprint notes when needed. Triggers on: 绘图, figure, chart, 画图, 实验图, 训练曲线, 消融实验, 对比图, 混淆矩阵, 结果图, 性能图, 鲁棒性图, 效率图, plot, publication figure, 数据可视化, generate plot, figure blueprint, 建议图表类型, figure audit, 审查图表, figure revision, 修改图表.

manifest.yaml

View on GitHub
name: academic-figure
description: >
  Declarative routing manifest for academic data/result figure work. Data plots
  use Python-generated editable SVG with CS/AI/ML chart design gates. Model
  framework diagrams, architecture diagrams, overview diagrams, and complex
  mechanism schematics are outside automatic drawing scope. Deeper references
  load only when needed.

always_load:
  - static/core/stance.md
  - static/core/red-lines.md
  - static/core/output-contract.md
  - static/core/anti-patterns.md
  - ../shared/core/non-invention-rules.md

axes:
  mode:
    detect: |
      Select the smallest mode that satisfies the request. Use an explicit user
      mode if provided. Data files or numeric results imply chart-from-data.
      Existing figure files plus critique language imply figure-audit; existing
      figures plus requested edits imply figure-revision. Section-level figure
      planning implies figure-blueprint. Requests to draw model framework,
      architecture, overview, or complex mechanism diagrams route to
      figure-blueprint only for manual_figure_needed notes; never render images,
      SVG, or prompts.
    values:
      chart-from-data: references/workflow-chart-from-data.md
      figure-blueprint: references/figure-contract.md
      figure-audit: references/qa-contract.md
      figure-revision: references/qa-contract.md
    multi: false

references:
  on_demand:
    - condition: build a Figure Contract
      path: references/figure-contract.md
    - condition: execute Python data plotting workflow
      path: references/workflow-chart-from-data.md
    - condition: write Python plotting code
      path: references/api.md
    - condition: select chart type
      path: references/chart-types.md
    - condition: final delivery, audit, or revision QA
      path: references/qa-contract.md
    - condition: color, typography, layout, and export rationale
      path: references/design-theory.md
    - condition: CS/AI/ML chart design pattern, dense multi-panel layout, benchmark, ablation, training, robustness, or efficiency figure
      path: references/cs-ai-chart-design-patterns.md
    - condition: user needs an end-to-end example
      path: references/tutorials.md
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 196kUpdated Claude CodeCodexVerifiedInstall