MCPInstall

nsfc-roadmap

by huangwb8AI & Agents

当用户明确要求"生成 NSFC 技术路线图/技术路线图绘制/roadmap/flowchart"或需要把标书研究内容转成"可打印、A4 可读"的技术路线图时使用。默认输出可编辑源文件（.drawio）与可嵌入文档的渲染结果（.svg/.png/.pdf）；当用户主动提及 Nano Banana 图片模型时，可切换为 PNG-only 模式，并兼容 Gemini 与 OpenAI gpt-image-2。⚠️ 不适用：用户只是想修改某张已有图片的格式/尺寸（应使用图片处理技能）、只是想润色技术路线文字描述（应直接改写正文）。

Installs
88
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/huangwb8/chineseresearchlatex --skill nsfc-roadmap
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads nsfc-roadmap automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

NSFC 技术路线图生成器

与 bensz-collect-bugs 的协作约定

  • 当用户环境中出现因本 skill 设计缺陷导致的 bug 时，优先使用 bensz-collect-bugs 按规范记录到 ~/.bensz-skills/bugs/，严禁直接修改用户本地 Claude Code / Codex 中已安装的 skill 源码。
  • 若 AI 仍可通过 workaround 继续完成用户任务，应先记录 bug，再继续完成当前任务。
  • 当用户明确要求“report bensz skills bugs”等公开上报动作时，调用本地 gh 与 bensz-collect-bugs，仅上传新增 bug 到 huangwb8/bensz-bugs；不要 pull / clone 整个 bug 仓库。

定位

  • 用于把 NSFC 标书中的研究内容、技术路线和风险控制转成可打印、A4 可读的路线图。
  • 默认工作流是确定性的 drawio 渲染；只有用户明确要求 Nano Banana 图片模型时才允许切到 PNG-only。
  • 本技能只服务科研写作与可视化表达，不代表任何官方评审口径或资助结论。

输入

至少提供其一：

  • proposal_path：标书目录，推荐。
  • proposal_file：单个输入文件。
  • spec_file：结构化图规格文件，最可控。

可选：

  • rounds：默认读 config.yaml:evaluation.max_rounds
  • output_dir：默认 roadmap_output/
  • renderer：默认 drawio；仅用户明确要求时才用 nano_banana
  • dotenv：仅 nano_banana 用
  • style_ref_images：仅 nano_banana 用，最多前 4 张
  • layout / template_ref：高级选项，默认不需要

输出

默认交付：

  • roadmap.drawio
  • roadmap.svg
  • roadmap.png
  • roadmap.pdf
  • roadmap-plan.md

隐藏中间产物位于 output_dir/.nsfc-roadmap/：

  • runs/run_*/round_*
  • spec_latest.yaml
  • optimization_report.md
  • config_used_best.yaml
  • evaluation_best.json
  • config_local.yaml
  • ai/：stop_strategy=ai_critic 时的请求/响应协议

Nano Banana 模式仅交付：

  • roadmap.png
  • roadmap_compacted.png

硬规则

  • 先读 config.yaml，以下字段视为单一真相来源：renderer、evaluation、layout、color_scheme、planning、output。
  • 仅处理用户明确提供的文件或目录；默认把标书视为敏感信息。
  • 默认不联网补素材；如用户要求联网，应先提醒风险。
  • 默认保持 drawio 流程；不要因为“图片模型更快”就擅自切换渲染后端。
  • 若内容拥挤，优先改 spec 的节点文案、分组或结构，不要靠缩字号硬过阈值。

工作流

1. 规划

  • 若已提供 spec_file，可跳过。
  • 默认使用 config.yaml:planning.planning_mode=ai：
    1. 运行 plan_roadmap.py 生成 plan_request.json/plan_request.md
    2. 宿主 AI 写 roadmap-plan.md 和 spec_draft.yaml
    3. 再次运行脚本校验 spec_draft.yaml
  • 规划阶段要同时看立项依据与研究内容，不只看 2.1 研究内容。

2. 落到 spec

  • 优先级：用户自带 spec_file > 规划阶段的 spec_draft.yaml > 从输入文件自动抽取。
  • spec 至少明确阶段、节点、输入输出和风险/备选方案。
  • 模板字段可选；默认不强制绑定某个 template_ref。

3. 确定性渲染

python3 nsfc-roadmap/scripts/generate_roadmap.py \
  --spec-file ./roadmap_output/spec.yaml \
  --output-dir ./roadmap_output \
  --rounds 5
  • 渲染时固化 spec_latest.yaml
  • 生成交付文件与每轮证据
  • draw.io CLI 缺失时按配置决定提示、降级或停止

4. 评估与优化

  • 默认最多 5 轮，具体以 config.yaml:evaluation 为准。
  • 每轮至少识别三类问题：
    • P0：缺研究内容、逻辑断裂、孤立节点、不可读
    • P1：布局混乱、配色干扰、字号过小
    • P2：间距、边距、箭头清晰度等一般优化
  • 停止策略只看配置：early_stop、stop_strategy=plateau 或 stop_strategy=ai_critic
  • 多维度自检默认覆盖 structure / visual / readability

5. 可选：AI 自主闭环

  • 若希望由宿主 AI 决定“是否继续、改哪里”，在 config_local.yaml 中启用 evaluation.stop_strategy: ai_critic。
  • 脚本会在 output_dir/.nsfc-roadmap/ai/ 下生成：
    • ai_critic_request.md
    • ai_critic_response.yaml
    • 每轮 ai_pack_round_XX/

6. 可选：Nano Banana PNG-only（Gemini / OpenAI gpt-image-2）

  • 只有用户明确要求时才启用。
  • 先做连通性检查：
python3 nsfc-roadmap/scripts/nano_banana_check.py

  • .env 中可通过 IMAGE_PROVIDER=openai 切到 OpenAI；未显式指定时，默认优先沿用既有 GEMINI_* 配置。

  • 然后再生成 PNG：

python3 nsfc-roadmap/scripts/generate_roadmap.py \
  --spec-file ./roadmap_output/spec.yaml \
  --output-dir ./roadmap_output \
  --rounds 1 \
  --renderer nano_banana

常用命令

# 规划
python3 nsfc-roadmap/scripts/plan_roadmap.py --proposal /path/to/proposal --output ./roadmap_output

# 生成
python3 nsfc-roadmap/scripts/generate_roadmap.py --spec-file ./roadmap_output/spec.yaml --output-dir ./roadmap_output --rounds 5

# 图片模型连通性
python3 nsfc-roadmap/scripts/nano_banana_check.py

参考材料

  • config.yaml
  • references/models/templates.yaml
  • references/models/README.md
  • assets/evaluation_rubric.md

FAQ

What does the nsfc-roadmap skill do?

当用户明确要求"生成 NSFC 技术路线图/技术路线图绘制/roadmap/flowchart"或需要把标书研究内容转成"可打印、A4 可读"的技术路线图时使用。默认输出可编辑源文件（.drawio）与可嵌入文档的渲染结果（.svg/.png/.pdf）；当用户主动提及 Nano Banana 图片模型时，可切换为 PNG-only 模式，并兼容 Gemini 与 OpenAI gpt-image-2。⚠️ 不适用：用户只是想修改某张已有图片的格式/尺寸（应使用图片处理技能）、只是想润色技术路线文字描述（应直接改写正文）。

How do I install nsfc-roadmap?

Run npx skills add https://github.com/huangwb8/chineseresearchlatex --skill nsfc-roadmap in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/nsfc-roadmap/ (personal) or .claude/skills/nsfc-roadmap/ (project).

Which AI agents can use nsfc-roadmap?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is nsfc-roadmap safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains nsfc-roadmap?

It is published by huangwb8 in huangwb8/chineseresearchlatex. It has 88 recorded installs.

More from huangwb8/chineseresearchlatex

View all →

systematic-literature-review

huangwb8/chineseresearchlatex

当用户明确要求"做系统综述/文献综述/related work/相关工作/文献调研"时使用。AI 自定检索词，多源检索→去重→AI 逐篇阅读并评分（1–10分语义相关性与子主题分组）→按高分优先比例选文→自动生成"综/述"字数预算→资深领域专家自由写作（固定摘要/引言/子主题/讨论/展望/结论），保留正文字数与参考文献数硬校验，强制导出 PDF 与 Word。支持多语言翻译与智能编译（en/zh/ja/de/fr/es）。

Code Quality & Workflow826 installs

nsfc-justification-writer

huangwb8/chineseresearchlatex

Open the skill to read its SKILL.md instructions.

Docs & Writing379 installs

nsfc-research-content-writer

huangwb8/chineseresearchlatex

Open the skill to read its SKILL.md instructions.

Docs & Writing307 installs

nsfc-research-foundation-writer

huangwb8/chineseresearchlatex

Open the skill to read its SKILL.md instructions.

Docs & Writing235 installs

nsfc-abstract

huangwb8/chineseresearchlatex

Open the skill to read its SKILL.md instructions.

204 installs

nsfc-reviewers

huangwb8/chineseresearchlatex

Open the skill to read its SKILL.md instructions.

191 installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs