Not in the top 1,000 by GitHub stars

heyu-233/engineering-figure-agent

Engineering Figure Banana is a Codex skill for generating publication-style engineering and computer science figures, with support for Chinese academic papers, bilingual labeling, and editable-figure handoff workflows.

Engineering Research

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

a33a553b43f9 → a33a553b43f9

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → a33a553b43f9

No earlier version was observed for comparison.

Compare on GitHub

`adapters/claude-code/skills/engineering-figure-agent/SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

a33a553b43f9 → a33a553b43f9

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → a33a553b43f9

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit a33a553b43f92152fdafcb1c4574d67a4e050cb6

310GitHub stars

-1star in 7 days

2skills in this repository

0commits in 30 days

Heat

0.1

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

engineering-figure-agent /
engineering-figure-agent adapters/claude-code/skills/engineering-figure-agent

How it works

Choose a skill

engineering-figure-agent

When your agent uses it

Use when the user needs engineering or research-paper figures: system architecture diagrams, algorithm workflows, hardware schematics, benchmark charts, ablation plots, figure briefs, redraws, image edits, or exact publication-style plots from numeric data. Covers Gemini, Nano Banana, OpenAI image models, and local plotting workflows.

What it loads into context

Frontmatter

72 tokens

Always available to the agent

SKILL.md

937 tokens

When the skill is activated

Reference documents

19,988 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Boundary
Core Decision
Default Workflow
Reference Loading
Scripts
Quality Rules

Scripts executed separately

scripts/build_engineering_figure_prompt.py
scripts/build_materials_figure_prompt.py
scripts/build_plot_spec.py
scripts/check_docs_links.py
scripts/check_runtime_package.py
scripts/check_setup.ps1
scripts/efa.py
scripts/generate_image.js
scripts/generate_image.py
scripts/install_and_test.ps1
scripts/install_skill.ps1
scripts/load_nanobanana_env.ps1
scripts/plot_publication_figure.py
scripts/sync_codex_skill.py
scripts/validate_prompt_templates.py
scripts/validate_skill.py
scripts/validate_text_encoding.py
scripts/wizard.ps1
tests/test_cli.py
tests/test_plot_workflow.py
tests/test_prompt_builder.py
tests/test_provider_safety.py

Files

.github/workflows/ci.ymlasset1,097 bytes
.gitignoreasset252 bytes
LICENSEasset1,065 bytes
README.en.mddoc4,424 bytes
README.mddoc7,894 bytes
README.zh-CN.mddoc4,334 bytes
SKILL.mdcore4,586 bytes
SKILL.mdcore4,586 bytes
SKILL.mdcore4,586 bytes
SKILL.mdcore4,586 bytes
SKILL.mdcore4,586 bytes
adapters/README.mddoc463 bytes
adapters/claude-code/README.mddoc1,061 bytes
agents/openai.yamlasset431 bytes
assets/prompt-templates/engineering-figure-templates.jsonasset6,619 bytes
assets/prompt-templates/materials-science-figure-templates.jsonasset9,723 bytes
docs/examples/README.mddoc2,016 bytes
docs/examples/benchmark-plot-request.jsonasset1,466 bytes
docs/examples/benchmark-plot.pngasset167,074 bytes
docs/examples/briefs/benchmark-plot.mddoc560 bytes
docs/examples/briefs/cooperative-object-tracking.mddoc552 bytes
docs/examples/briefs/federated-open-vocab-driving.mddoc558 bytes
docs/examples/briefs/health-monitoring-early-warning.mddoc692 bytes
docs/examples/briefs/linux-kernel-system.mddoc518 bytes
docs/examples/briefs/multi-agent-safety-overview.mddoc540 bytes
docs/examples/cooperative-object-tracking-2k-1.pngasset4,775,119 bytes
docs/examples/cooperative-object-tracking-prompt.txtdoc1,642 bytes
docs/examples/federated-open-vocab-driving-2k-1.pngasset5,677,228 bytes
docs/examples/federated-open-vocab-driving-prompt.txtdoc1,771 bytes
docs/examples/health-monitoring-early-warning-note.txtdoc699 bytes
docs/examples/health-monitoring-early-warning-reference.jpgasset199,633 bytes
docs/examples/linux-kernel-system-1.jpgasset789,267 bytes
docs/examples/linux-kernel-system-diagram-prompt.txtdoc2,597 bytes
docs/examples/multi-agent-safety-overview-2k-1.pngasset5,872,022 bytes
docs/examples/multi-agent-safety-overview-prompt.txtdoc1,553 bytes
docs/platform-adapters.mddoc1,918 bytes
docs/prompt-pack.mddoc2,578 bytes
docs/showcase.mddoc1,546 bytes
examples/figure-briefs/algorithm-workflow-en.mddoc913 bytes
examples/figure-briefs/benchmark-plot-request.mddoc1,806 bytes
examples/figure-briefs/engineering-pipeline-zh.mddoc429 bytes
examples/figure-briefs/system-architecture-en.mddoc1,022 bytes
examples/figure-briefs/system-architecture-zh.mddoc580 bytes
providers.mddoc5,135 bytes
references/api-reference.mddoc3,118 bytes
references/chinese-labels.mddoc1,533 bytes
references/editable-figure-handoff.mddoc1,316 bytes
references/engineering-figure-templates.mddoc1,780 bytes
references/figure-brief-spec.mddoc3,247 bytes
references/highres-policy.mddoc1,033 bytes
references/materials-science-figure-template.mddoc10,089 bytes
references/natural-language-plot-workflow.mddoc4,243 bytes
references/prompt-templates.mddoc2,423 bytes
references/provider-selection.mddoc2,347 bytes
references/publication-chart-patterns.mddoc2,485 bytes
references/publication-figure-design.mddoc2,468 bytes
references/publication-plot-api.mddoc5,773 bytes
requirements.txtdoc81 bytes
schemas/figure-brief.schema.jsonasset1,266 bytes
schemas/plot-request.schema.jsonasset1,138 bytes
scripts/build_engineering_figure_prompt.pyruns2,908 bytes
scripts/build_materials_figure_prompt.pyruns2,927 bytes
scripts/build_plot_spec.pyruns8,346 bytes
scripts/check_docs_links.pyruns1,615 bytes
scripts/check_runtime_package.pyruns2,877 bytes
scripts/check_setup.ps1runs8,729 bytes
scripts/efa.pyruns4,769 bytes
scripts/generate_image.jsruns12,712 bytes
scripts/generate_image.pyruns27,063 bytes
scripts/install_and_test.ps1runs4,069 bytes
scripts/install_skill.ps1runs3,133 bytes
scripts/load_nanobanana_env.ps1runs2,142 bytes
scripts/plot_publication_figure.pyruns15,942 bytes
scripts/sync_codex_skill.pyruns2,525 bytes
scripts/validate_prompt_templates.pyruns4,414 bytes
scripts/validate_skill.pyruns1,160 bytes
scripts/validate_text_encoding.pyruns1,882 bytes
scripts/wizard.ps1runs4,032 bytes
secrets/nanobanana.env.exampleasset1,590 bytes
secrets/nanobanana_api_key.txt.exampleasset51 bytes
secrets/openai_api_key.txt.exampleasset47 bytes
templates/figure-brief/figure-brief.en.mddoc929 bytes
templates/figure-brief/figure-brief.jsonasset633 bytes
templates/figure-brief/figure-brief.zh-CN.mddoc912 bytes
tests/test_cli.pyruns1,200 bytes
tests/test_plot_workflow.pyruns3,657 bytes
tests/test_prompt_builder.pyruns2,212 bytes
tests/test_provider_safety.pyruns3,080 bytes

Read SKILL.md


# Engineering Figure Agent

Use this skill after the figure goal is already reasonably clear.

## Boundary

Good fit:

- Turn a figure brief into a conceptual diagram, workflow figure, schematic, or exact publication plot.
- Choose between `image`, `plot`, and `mixed` mode.
- Build prompts, render plots, and refine existing briefs.

Not the main tool for:

View the complete source on GitHub

When your agent uses it

Create engineering and CS paper figures from local paper context, method notes, code, data tables, or existing drafts. Use for figure briefs, conceptual diagrams, architecture figures, algorithm workflows, exact publication plots, prompt refinement, and light figure critique.

What it loads into context

Frontmatter

58 tokens

Always available to the agent

SKILL.md

533 tokens

When the skill is activated

Reference documents

156 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Core Decision
Workflow
Output Files
Quality Rules

Files

SKILL.mdcore2,679 bytes
templates/figure-brief.mddoc600 bytes

Read SKILL.md


# Engineering Figure Agent For Claude Code

Use this skill for the figure-production layer after the figure goal is reasonably clear.

If the figure claim, panel logic, or caption argument is still unclear, first use a research-writing or paper-analysis workflow to settle the scientific message.

## Core Decision

- Use `image mode` for conceptual figures: system architecture, algorithm workflow, graphical abstract, hardware block diagram, or reference-inspired redraw.
- Use `plot mode` for exact values: benchmark bars, ablation plots, trend curves, heatmaps, scatter plots, or multi-panel quantitative figures.
- Use `mixed` when exact plot panels should be rendered locally and conceptual panels should be generated or described separately.

## Workflow

View the complete source on GitHub

Skills included

engineering-figure-agent

Repository facts

License: MIT
Created: Apr 10, 2026
Last pushed: May 25, 2026
Forks: 14
Open issues: 0
Project activity: Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 5, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 4 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
No dangerous shell commands
69 network referencesin 13 files: providers.md:19 scripts/generate_image.py:20 tests/test_provider_safety.py:9 and 10 more
2 obfuscation signalsin 1 file: scripts/generate_image.py:627
No instruction overrides
22 executable scriptsin 22 files: scripts/build_engineering_figure_prompt.py:1 scripts/build_materials_figure_prompt.py:1 scripts/build_plot_spec.py:1 and 19 more
63 references to secretsin 17 files: scripts/generate_image.py:112 scripts/install_and_test.ps1:13 scripts/check_setup.ps1:73 and 14 more
No requests to vote in Hot

Show all 156 signals by file

`.gitignore`

Access to secretsline 11
```
[Credential-related source omitted]
```

`README.en.md`

Network accessline 5

![Codex Skill](https://img.shields.io/badge/Codex-skill-111827)

Network accessline 6

![Claude Code](https://img.shields.io/badge/Claude%20Code-adapter-8b5cf6)

Network accessline 7

![Modes](https://img.shields.io/badge/modes-image%20%7C%20plot-f59e0b)

Network accessline 8

![Backends](https://img.shields.io/badge/backends-Gemini%20%7C%20OpenAI%20%7C%20local%20plots-16a34a)

`README.md`

Network accessline 5

![License](https://img.shields.io/badge/license-MIT-2563eb)

Network accessline 6

![Codex Skill](https://img.shields.io/badge/Codex-skill-111827)

Network accessline 7

![Figure Modes](https://img.shields.io/badge/modes-image%20%7C%20plot-f59e0b)

Network accessline 8

![Backends](https://img.shields.io/badge/backends-Gemini%20%7C%20OpenAI%20%7C%20local%20plots-16a34a)

Network accessline 9

![Focus](https://img.shields.io/badge/focus-engineering%20papers-7c3aed)

Network accessline 11

[![Try Engineering Figure Agent on Socialistic](https://socialistic.ai/api/embed/engineering-figure-agent-407b80)](https://socialistic.ai/zh/skill/engineering-figure-agent-407b80?utm_source=github&utm_medium=readme&utm_campaign=20260519-stu

Access to secretsline 95
```
[Credential-related source omitted]
```

`README.zh-CN.md`

Network accessline 5

![Codex Skill](https://img.shields.io/badge/Codex-skill-111827)

Network accessline 6

![Claude Code](https://img.shields.io/badge/Claude%20Code-adapter-8b5cf6)

Network accessline 7

![Modes](https://img.shields.io/badge/modes-image%20%7C%20plot-f59e0b)

Network accessline 8

![Backends](https://img.shields.io/badge/backends-Gemini%20%7C%20OpenAI%20%7C%20local%20plots-16a34a)

`providers.md`

Network accessline 19

| Provider type | Typical base URL | Typical auth mode | Third-party flag | High-res model handling | | --- | --- | --- | --- | --- | | Official Google Gemini | `https://generativelanguage.googleapis.com` | `google` | not needed | optional

Network accessline 20

| --- | --- | --- | --- | --- | | Official Google Gemini | `https://generativelanguage.googleapis.com` | `google` | not needed | optional `NANOBANANA_HIGHRES_MODEL` | | OpenAI Image API | `https://api.openai.com/v1` | `bearer` | not needed

Network accessline 21

| Official Google Gemini | `https://generativelanguage.googleapis.com` | `google` | not needed | optional `NANOBANANA_HIGHRES_MODEL` |

Network accessline 22

| OpenAI Image API | `https://api.openai.com/v1` | `bearer` | not needed | optional `OPENAI_IMAGE_HIGHRES_MODEL` |

Network accessline 26

| Provider 类型 | 常见 base URL | 常见认证方式 | 是否需要第三方标记 | 高分模型处理 | | --- | --- | --- | --- | --- | | 官方 Google Gemini | `https://generativelanguage.googleapis.com` | `google` | 通常不需要 | 可选 `NANOBANANA_HIGHRES_MODEL` |

Network accessline 27

| --- | --- | --- | --- | --- | | 官方 Google Gemini | `https://generativelanguage.googleapis.com` | `google` | 通常不需要 | 可选 `NANOBANANA_HIGHRES_MODEL` | | OpenAI Image API | `https://api.openai.com/v1` | `bearer` | 通常不需要 | 可选 `OPENAI_IMAGE_HIG

Network accessline 28

| 官方 Google Gemini | `https://generativelanguage.googleapis.com` | `google` | 通常不需要 | 可选 `NANOBANANA_HIGHRES_MODEL` |

Network accessline 29

| OpenAI Image API | `https://api.openai.com/v1` | `bearer` | 通常不需要 | 可选 `OPENAI_IMAGE_HIGHRES_MODEL` |

Network accessline 52

NANOBANANA_BASE_URL=https://generativelanguage.googleapis.com

Network accessline 61

NANOBANANA_BASE_URL=https://your-relay.example.com

Access to secretsline 76
```
[Credential-related source omitted]
```

`references/api-reference.md`

Network accessline 7

- Official base URL: `https://generativelanguage.googleapis.com`

Access to secretsline 10
```
[Credential-related source omitted]
```

Network accessline 15

- Zhizengzeng base URL: `https://api.zhizengzeng.com/google`

Network accessline 21

- The generation scripts are designed to fail closed when `NANOBANANA_BASE_URL` or `--base-url` is missing. - Official Google endpoint is the recommended default: `https://generativelanguage.googleapis.com`

Network accessline 22

- Official Google endpoint is the recommended default: `https://generativelanguage.googleapis.com`

Access to secretsline 30
```
[Credential-related source omitted]
```

`references/provider-selection.md`

Network accessline 14

| Provider | Base URL | Auth | Third-party flag | High-res handling | |---|---|---|---|---| | Official Google Gemini | `https://generativelanguage.googleapis.com` | `google` | not needed | optional `NANOBANANA_HIGHRES_MODEL` |

Network accessline 15

|---|---|---|---|---| | Official Google Gemini | `https://generativelanguage.googleapis.com` | `google` | not needed | optional `NANOBANANA_HIGHRES_MODEL` | | OpenAI Image API | `https://api.openai.com/v1` | bearer | not needed | optional `

Network accessline 16

| Official Google Gemini | `https://generativelanguage.googleapis.com` | `google` | not needed | optional `NANOBANANA_HIGHRES_MODEL` |

Network accessline 17

| OpenAI Image API | `https://api.openai.com/v1` | bearer | not needed | optional `OPENAI_IMAGE_HIGHRES_MODEL` |

Network accessline 24

NANOBANANA_BASE_URL=https://generativelanguage.googleapis.com

Access to secretsline 28
```
[Credential-related source omitted]
```

Network accessline 34

NANOBANANA_BASE_URL=https://your-relay.example.com

Access to secretsline 45
```
[Credential-related source omitted]
```

`schemas/figure-brief.schema.json`

Network accessline 1

{   "$schema": "https://json-schema.org/draft/2020-12/schema",

Network accessline 2

"$schema": "https://json-schema.org/draft/2020-12/schema",

`schemas/plot-request.schema.json`

Network accessline 1

{   "$schema": "https://json-schema.org/draft/2020-12/schema",

Network accessline 2

"$schema": "https://json-schema.org/draft/2020-12/schema",

`scripts/build_engineering_figure_prompt.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/build_materials_figure_prompt.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/build_plot_spec.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/check_docs_links.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/check_runtime_package.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/check_setup.ps1`

Executable scriptline 1
```
Executable file
```
Access to secretsline 73
```
[Credential-related source omitted]
```
Access to secretsline 74
```
[Credential-related source omitted]
```

Network accessline 97

if ($envMap.ContainsKey("NANOBANANA_BASE_URL") -and $envMap["NANOBANANA_BASE_URL"]) {         $baseUrl = $envMap["NANOBANANA_BASE_URL"]         if ($baseUrl -eq "https://generativelanguage.googleapis.com") {

Network accessline 98

$baseUrl = $envMap["NANOBANANA_BASE_URL"]         if ($baseUrl -eq "https://generativelanguage.googleapis.com") {             Add-Result "PASS" "Official Google endpoint configured" $null

Network accessline 99

if ($baseUrl -eq "https://generativelanguage.googleapis.com") {

Access to secretsline 126
```
[Credential-related source omitted]
```
Access to secretsline 128
```
[Credential-related source omitted]
```
Access to secretsline 129
```
[Credential-related source omitted]
```
Access to secretsline 135
```
[Credential-related source omitted]
```
Access to secretsline 151
```
[Credential-related source omitted]
```

`scripts/efa.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/generate_image.js`

Executable scriptline 1
```
#!/usr/bin/env node
```

Network accessline 7

const OFFICIAL_BASE_URL = "https://generativelanguage.googleapis.com";

Access to secretsline 53
```
[Credential-related source omitted]
```
Access to secretsline 253
```
[Credential-related source omitted]
```
Network accessline 318
```
try {     const response = await fetch(
```
Network accessline 319
```
const response = await fetch(
```

`scripts/generate_image.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Network accessline 20

GEMINI_OFFICIAL_BASE_URL = "https://generativelanguage.googleapis.com"

Network accessline 21

GEMINI_OFFICIAL_HOSTNAME = "generativelanguage.googleapis.com" GEMINI_DEFAULT_MODEL = "gemini-3.1-flash-image-preview" OPENAI_DEFAULT_BASE_URL = "https://api.openai.com/v1"

Network accessline 22

GEMINI_DEFAULT_MODEL = "gemini-3.1-flash-image-preview" OPENAI_DEFAULT_BASE_URL = "https://api.openai.com/v1" OPENAI_OFFICIAL_HOSTNAME = "api.openai.com"

Network accessline 23

OPENAI_DEFAULT_BASE_URL = "https://api.openai.com/v1"

Access to secretsline 112
```
[Credential-related source omitted]
```
Access to secretsline 124
```
[Credential-related source omitted]
```
Access to secretsline 342
```
[Credential-related source omitted]
```
Access to secretsline 343
```
[Credential-related source omitted]
```
Access to secretsline 344
```
[Credential-related source omitted]
```
Access to secretsline 345
```
[Credential-related source omitted]
```
Access to secretsline 354
```
[Credential-related source omitted]
```
Access to secretsline 381
```
[Credential-related source omitted]
```
Access to secretsline 382
```
[Credential-related source omitted]
```
Access to secretsline 383
```
[Credential-related source omitted]
```
Access to secretsline 384
```
[Credential-related source omitted]
```
Access to secretsline 385
```
[Credential-related source omitted]
```
Access to secretsline 392
```
[Credential-related source omitted]
```
Access to secretsline 435
```
[Credential-related source omitted]
```
Access to secretsline 446
```
[Credential-related source omitted]
```
Access to secretsline 448
```
[Credential-related source omitted]
```
Network accessline 450
```
request = urllib.request.Request(
```

Network accessline 457

try:         with urllib.request.urlopen(request, timeout=args.timeout) as response:

Network accessline 458

with urllib.request.urlopen(request, timeout=args.timeout) as response:

Access to secretsline 537
```
[Credential-related source omitted]
```
Access to secretsline 540
```
[Credential-related source omitted]
```

Network accessline 569

request = urllib.request.Request(url, data=data, headers=headers, method="POST")

Network accessline 570

try:         with urllib.request.urlopen(request, timeout=args.timeout) as response:             return json.loads(response.read().decode("utf-8"))

Network accessline 571

with urllib.request.urlopen(request, timeout=args.timeout) as response:

Possible obfuscationline 627

path.write_bytes(base64.b64decode(inline_data["data"]))

Possible obfuscationline 647

path.write_bytes(base64.b64decode(image_base64))

`scripts/install_and_test.ps1`

Executable scriptline 1
```
Executable file
```
Access to secretsline 13
```
[Credential-related source omitted]
```
Access to secretsline 14
```
[Credential-related source omitted]
```
Access to secretsline 16
```
[Credential-related source omitted]
```
Access to secretsline 17
```
[Credential-related source omitted]
```
Access to secretsline 65
```
[Credential-related source omitted]
```
Access to secretsline 67
```
[Credential-related source omitted]
```
Access to secretsline 72
```
[Credential-related source omitted]
```
Access to secretsline 74
```
[Credential-related source omitted]
```

`scripts/install_skill.ps1`

Executable scriptline 1
```
Executable file
```
Access to secretsline 12
```
[Credential-related source omitted]
```
Access to secretsline 14
```
[Credential-related source omitted]
```
Access to secretsline 61
```
[Credential-related source omitted]
```
Access to secretsline 63
```
[Credential-related source omitted]
```

`scripts/load_nanobanana_env.ps1`

Executable scriptline 1
```
Executable file
```
Access to secretsline 6
```
[Credential-related source omitted]
```
Access to secretsline 7
```
[Credential-related source omitted]
```
Access to secretsline 34
```
[Credential-related source omitted]
```
Access to secretsline 38
```
[Credential-related source omitted]
```
Access to secretsline 48
```
[Credential-related source omitted]
```
Access to secretsline 49
```
[Credential-related source omitted]
```

`scripts/plot_publication_figure.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 14
```
[Credential-related source omitted]
```
Access to secretsline 15
```
[Credential-related source omitted]
```

`scripts/sync_codex_skill.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/validate_prompt_templates.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/validate_skill.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/validate_text_encoding.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/wizard.ps1`

Executable scriptline 1
```
Executable file
```

`secrets/nanobanana.env.example`

Network accessline 11

# Official Google Gemini example # ------------------------------------------------------------------- # NANOBANANA_BASE_URL=https://generativelanguage.googleapis.com

Network accessline 12

# ------------------------------------------------------------------- # NANOBANANA_BASE_URL=https://generativelanguage.googleapis.com # NANOBANANA_DEFAULT_MODEL=gemini-3.1-flash-image-preview

Network accessline 13

# NANOBANANA_BASE_URL=https://generativelanguage.googleapis.com

Network accessline 20

# Replace with your own endpoint and model names. # ------------------------------------------------------------------- NANOBANANA_BASE_URL=https://your-relay.example.com

Network accessline 21

# ------------------------------------------------------------------- NANOBANANA_BASE_URL=https://your-relay.example.com NANOBANANA_DEFAULT_MODEL=<your-default-image-model>

Network accessline 22

NANOBANANA_BASE_URL=https://your-relay.example.com

Access to secretsline 30
```
[Credential-related source omitted]
```
Access to secretsline 35
```
[Credential-related source omitted]
```

`secrets/nanobanana_api_key.txt.example`

Access to secretsline 1
```
[Credential-related source omitted]
```

`secrets/openai_api_key.txt.example`

Access to secretsline 1
```
[Credential-related source omitted]
```

`tests/test_cli.py`

Executable scriptline 1
```
Executable file
```

`tests/test_plot_workflow.py`

Executable scriptline 1
```
Executable file
```

`tests/test_prompt_builder.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 23
```
[Credential-related source omitted]
```

`tests/test_provider_safety.py`

Executable scriptline 1
```
Executable file
```

Network accessline 9

env = {         **os.environ,         "NANOBANANA_BASE_URL": "https://relay.example.com",

Network accessline 10
```
[Credential-related source omitted]
```
Access to secretsline 10
```
[Credential-related source omitted]
```

Network accessline 11

"NANOBANANA_BASE_URL": "https://relay.example.com",

Access to secretsline 37
```
[Credential-related source omitted]
```

Network accessline 47

"openai",             "--openai-base-url",             "https://relay.example.com/v1",

Network accessline 48

"--openai-base-url",             "https://relay.example.com/v1",             "--timeout",

Network accessline 49
```
"https://relay.example.com/v1",
```

Network accessline 66

env = {         **os.environ,         "NANOBANANA_BASE_URL": "https://generativelanguage.googleapis.com",

Network accessline 67
```
[Credential-related source omitted]
```
Access to secretsline 67
```
[Credential-related source omitted]
```

Network accessline 68

"NANOBANANA_BASE_URL": "https://generativelanguage.googleapis.com",

Access to secretsline 93
```
[Credential-related source omitted]
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Declared and executed: 4 facts

Contacts generativelanguage.googleapis.com, which SKILL.md, the README and the plugin manifest do not mentionscripts/check_setup.ps1:99High confidence
Contacts generativelanguage.googleapis.com, which SKILL.md, the README and the plugin manifest do not mentionscripts/generate_image.js:7High confidence
Contacts generativelanguage.googleapis.com, which SKILL.md, the README and the plugin manifest do not mentionscripts/generate_image.py:20High confidence
Contacts api.openai.com, which SKILL.md, the README and the plugin manifest do not mentionscripts/generate_image.py:23High confidence

Signal confidence: 141 facts

Network access in prose of documentationREADME.en.md:5Low confidence
Network access in prose of documentationREADME.en.md:6Low confidence
Network access in prose of documentationREADME.en.md:7Low confidence
Network access in prose of documentationREADME.en.md:8Low confidence
Network access in prose of documentationREADME.md:5Low confidence
Network access in prose of documentationREADME.md:6Low confidence
Network access in prose of documentationREADME.md:7Low confidence
Network access in prose of documentationREADME.md:8Low confidence
Network access in prose of documentationREADME.md:9Low confidence
Network access in prose of documentationREADME.md:11Low confidence
Access to secrets in prose of documentationREADME.md:95Low confidence
Network access in prose of documentationREADME.zh-CN.md:5Low confidence
Network access in prose of documentationREADME.zh-CN.md:6Low confidence
Network access in prose of documentationREADME.zh-CN.md:7Low confidence
Network access in prose of documentationREADME.zh-CN.md:8Low confidence
Network access in prose of documentationproviders.md:19Low confidence
Network access in prose of documentationproviders.md:20Low confidence
Network access in prose of documentationproviders.md:21Low confidence
Network access in prose of documentationproviders.md:22Low confidence
Network access in prose of documentationproviders.md:26Low confidence
Network access in prose of documentationproviders.md:27Low confidence
Network access in prose of documentationproviders.md:28Low confidence
Network access in prose of documentationproviders.md:29Low confidence
Network access in code of documentationproviders.md:52Low confidence
Network access in code of documentationproviders.md:61Low confidence
Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueproviders.md:76Low confidence
Network access in prose of documentationreferences/api-reference.md:7Low confidence
Access to secrets in prose of documentationreferences/api-reference.md:10Low confidence
Network access in prose of documentationreferences/api-reference.md:15Low confidence
Network access in prose of documentationreferences/api-reference.md:21Low confidence
Network access in prose of documentationreferences/api-reference.md:22Low confidence
Access to secrets in code of documentationreferences/api-reference.md:30Low confidence
Network access in prose of documentationreferences/provider-selection.md:14Low confidence
Network access in prose of documentationreferences/provider-selection.md:15Low confidence
Network access in prose of documentationreferences/provider-selection.md:16Low confidence
Network access in prose of documentationreferences/provider-selection.md:17Low confidence
Network access in code of documentationreferences/provider-selection.md:24Low confidence
Access to secrets in code of documentation: a variable, placeholder or call, not a stored valuereferences/provider-selection.md:28Low confidence
Network access in code of documentationreferences/provider-selection.md:34Low confidence
Access to secrets in code of documentation: a variable, placeholder or call, not a stored valuereferences/provider-selection.md:45Low confidence
Executable script in code of a file that runsscripts/build_engineering_figure_prompt.py:1High confidence
Executable script in code of a file that runsscripts/build_materials_figure_prompt.py:1High confidence
Executable script in code of a file that runsscripts/build_plot_spec.py:1High confidence
Executable script in code of a file that runsscripts/check_docs_links.py:1High confidence
Executable script in code of a file that runsscripts/check_runtime_package.py:1High confidence
Executable script in code of a file that runsscripts/check_setup.ps1:1High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/check_setup.ps1:73Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/check_setup.ps1:74Low confidence
Network access in code of a file that runsscripts/check_setup.ps1:97High confidence
Network access in code of a file that runsscripts/check_setup.ps1:98High confidence

and 91 more

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Compatible	Standard SKILL.md SKILL.md	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

heyu-233/engineering-figure-agent

History

SKILL.md

adapters/claude-code/skills/engineering-figure-agent/SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

engineering-figure-agent

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Frontmatter

SKILL.md

Reference documents

The playbook

Files

Skills included

Repository facts

Before you install

.gitignore

README.en.md

README.md

README.zh-CN.md

providers.md

references/api-reference.md

references/provider-selection.md

schemas/figure-brief.schema.json

schemas/plot-request.schema.json

scripts/build_engineering_figure_prompt.py

scripts/build_materials_figure_prompt.py

scripts/build_plot_spec.py

scripts/check_docs_links.py

scripts/check_runtime_package.py

scripts/check_setup.ps1

scripts/efa.py

scripts/generate_image.js

scripts/generate_image.py

scripts/install_and_test.ps1

scripts/install_skill.ps1

scripts/load_nanobanana_env.ps1

scripts/plot_publication_figure.py

scripts/sync_codex_skill.py

scripts/validate_prompt_templates.py

scripts/validate_skill.py

scripts/validate_text_encoding.py

scripts/wizard.ps1

secrets/nanobanana.env.example

secrets/nanobanana_api_key.txt.example

secrets/openai_api_key.txt.example

tests/test_cli.py

tests/test_plot_workflow.py

tests/test_prompt_builder.py

tests/test_provider_safety.py

How the signals fit together

Works with

You might also use

mattpocock/skills

obra/superpowers

NousResearch/hermes-agent

multica-ai/andrej-karpathy-skills

anthropics/skills

DietrichGebert/ponytail

`SKILL.md`

`adapters/claude-code/skills/engineering-figure-agent/SKILL.md`

`.gitignore`

`README.en.md`

`README.md`

`README.zh-CN.md`

`providers.md`

`references/api-reference.md`

`references/provider-selection.md`

`schemas/figure-brief.schema.json`

`schemas/plot-request.schema.json`

`scripts/build_engineering_figure_prompt.py`

`scripts/build_materials_figure_prompt.py`

`scripts/build_plot_spec.py`

`scripts/check_docs_links.py`

`scripts/check_runtime_package.py`

`scripts/check_setup.ps1`

`scripts/efa.py`

`scripts/generate_image.js`

`scripts/generate_image.py`

`scripts/install_and_test.ps1`

`scripts/install_skill.ps1`

`scripts/load_nanobanana_env.ps1`

`scripts/plot_publication_figure.py`

`scripts/sync_codex_skill.py`

`scripts/validate_prompt_templates.py`

`scripts/validate_skill.py`

`scripts/validate_text_encoding.py`

`scripts/wizard.ps1`

`secrets/nanobanana.env.example`

`secrets/nanobanana_api_key.txt.example`

`secrets/openai_api_key.txt.example`

`tests/test_cli.py`

`tests/test_plot_workflow.py`

`tests/test_prompt_builder.py`

`tests/test_provider_safety.py`