agentleFS
Sign inStart free
JacobinwweyJacobinwwey/notemdpro/skills/diagram-generator/SKILL.md

diagram-generator

Skill2 starsChanged 39 days agoMITView on GitHub

Generate source-grounded diagrams with explicit relationships and capability-checked exports.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use attack-chain, binary-diff and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • DorianGalloSkill

    attack-chain

    Also in 6 projects that use this

  • DorianGalloSkill

    binary-diff

    跨版本符号迁移与二进制差分。当你有旧版本的符号/逆向结果，需要快速迁移到新版本时使用。 适用场景：内核缺 PDB 用旧版符号推导、程序更新后批量迁移函数名、应用更新后快速定位新偏移。 核心方法：用 LLM 做结构化差异比对，程序化输入输出，成本极低（200 函数 ~1 元）。 触发关键词：符号迁移、bindiff、跨版本、PDB 缺失、函数偏移迁移、symbol migration、binary diff、版本对比。

    Also in 6 projects that use this

  • Roshu18Skill

    pentest-tools

    Tool selection policy for BearStrike based on target type, scan risk, and signal strength.

    Also in 7 projects that use this

  • hardw00tSkill

    llm-security

    LLM and AI application security testing skill for prompt injection (direct, indirect, multimodal), system-prompt extraction, RAG poisoning, memory poisoning, MCP server injection, skill-file injection, agentic tool misuse, computer-use UI injection, and excessive agency. Authorization required — this skill tests AI systems you are explicitly permitted to assess. Triggers on requests to test LLM / AI-agent / RAG / MCP / computer-use security, perform prompt injection, extract system prompts, poison RAG or memory, audit agent tool use, or evaluate AI guardrails.

    Also in 6 projects that use this

  • +8 more from DorianGallo

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the full authorized source.

    line 12
  2. Distinctive:

    Keep hierarchy separate from cross-branch relationships.

    line 14
  3. Distinctive:

    Prefer deterministic renderer placement: closely related blocks should be nearer.

    line 15
  4. Distinctive:

    Use workflow-runner for complete diagnostics.

    line 18

“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Diagram generator

English

Canonical action: generate-diagram; accept generate-experimental-diagram as an alias. preview-diagram requires an available host renderer.

  1. Read the full authorized source. Identify required concepts, source references, ownership hierarchy and explicit directed predicates. Keep a coverage inventory.
  2. Select an available target. Mermaid text is supported by the bundled validator; Drawnix, SVG and PDF need an actual host adapter. Never claim an unavailable format was exported.
  3. Keep hierarchy separate from cross-branch relationships. Preserve all required nodes and source-supported relations, including reciprocal and distinct predicates. Do not invent edges merely to connect isolated concepts.
  4. Prefer deterministic renderer placement: closely related blocks should be nearer; route from boundaries, reserve label space and reduce crossings/overlap. Never delete content to improve geometry. Revalidate coverage after any reorder.
  5. Validate canonical source before preview/export. For a host SVG-to-PDF path, require sanitized SVG, resolved style/inheritance support, valid dimensions/viewBox, proportional page-size limits and a nonempty parseable PDF. Preserve source plus intermediate artifacts and report the failing stage when unsupported or unsuccessful.

Use workflow-runner for complete diagnostics. A successful text generation does not establish rendered export success.

中文

规范操作名为 generate-diagram，接受 generate-experimental-diagram 兼容别名。preview-diagram 需要实际可用的宿主渲染器。

  1. 阅读完整的已授权来源，整理必要概念、来源引用、归属层级和显式有向谓词，保留覆盖清单。
  2. 选择可用目标。随附验证器支持 Mermaid 文本；Drawnix、SVG 和 PDF 需要真实宿主适配器，不得把不可用格式报告为已导出。
  3. 分离层级与跨分支关系，保留全部必要节点及来源支持的关系，包括反向关系和不同谓词。不得为了连接孤立概念而虚构连线。
  4. 优先使用确定性渲染排布：紧密关联块相邻，连接节点边界，预留标签空间，减少交叉与重叠。不得删除内容改善几何效果；重排后重新验证覆盖。
  5. 预览/导出前验证规范源。宿主 SVG 到 PDF 路径应支持净化、样式/继承解析、有效尺寸/viewBox、等比例页面尺寸限制，以及非空且可解析的 PDF。保留源与中间产物，能力不支持或失败时报告具体阶段。

完整诊断遵循 workflow-runner。文本生成成功不代表渲染导出成功。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free