Nsfc Schematic

What it does

When your agent uses it

• Tasks that involve Diagrams
• Tasks that involve Image generation
• Tasks that involve PDF

Example prompts

• “生成 NSFC 原理图/机制图/schematic diagram/mechanism diagram”
• “可编辑 + 可嵌入文档”
• “原理图/机制图”
• “/nsfc-schematic”

Requirements

• Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1再次运行规划脚本进行合法性校验（脚本将校验 spec 结构，并给出 P0/WARN 提示）
2. 2审阅 schematic_plan/schematic-plan.md 与 schematic_plan/spec_draft.yaml：确认模块划分、节点清单、连接关系与布局建议是否合理。
3. 3用 generate_schematic.py 进入多轮生成与优化

What it can do on your machine

Read from SKILL.md and the folder at commit 4f96df0. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/, which the agent can run.

  Shell commands in SKILL.md call:

  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • generativelanguage.googleapis.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nsfc Schematic loads about 3.7k tokens when it runs, and up to ~311k if it reads all its reference files. Until then it costs about 72 tokens; SKILL.md has 673 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~72

When it runs · the whole SKILL.md, loaded when a task matches

~3.7k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~311k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:225

  前置条件：在项目根目录 `.env`（或系统环境变量）配置并可连通：

• NoteMentions a .env fileSKILL.md:237

  如你不是在项目根目录执行，可显式指定 `.env`：

• NoteMentions a .env fileSKILL.md:240

  s/nano_banana_check.py --dotenv /path/to/.env

• NoteMentions a .env fileSKILL.md:248

  --dotenv /path/to/.env \

• NoteMentions a .env fileSKILL.md:365

  - `scripts/env_utils.py`：`.env` 解析与向上查找（用于 Nano Banana/Gemini 模式读取 GEMINI_* 配置）。

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 673 words (~3,664 tokens).

name

nsfc-schematic

metadata.author

Bensz Conan

metadata.short-description

生成 NSFC 原理图（默认 drawio + PDF/SVG/PNG；可选 Nano Banana PNG-only）

metadata.keywords

nsfc-schematic, nsfc, schematic, mechanism diagram, drawio, architecture diagram

Read the full SKILL.md on GitHub

Files

SKILL.md and 46 other files (scripts, references, assets) in drclaw/local_skill_hub/proposal_writing/nsfc-schematic of InternScience/DrClaw.

• SKILL.md
• README.md
• assets/color_schemes.yaml
• config.yaml
• references/design_principles.md
• references/models/model-01.jpg
• references/models/model-01.simple.jpg
• references/models/model-02.jpg
• references/models/model-02.simple.jpg
• references/models/model-06.png
• references/models/model-07.png
• references/models/model-08.png
• references/models/model-09.png
• references/models/model-10.png
• references/models/model-11.png
• references/models/model-12.png
• references/models/model-13.png
• references/models/templates.yaml
• … and 29 more

Open the folder on GitHubat commit 4f96df0