Not in the top 1,000 by GitHub stars
dingtingli/dtl-skills
A collection of open-source skills created by @dingtingli.
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
anthropic-diagram/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a86c4806780a → a86c4806780a
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a86c4806780a
No earlier version was observed for comparison.
145GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days
Heat
0.3- 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
- anthropic-diagram
anthropic-diagram
How it works
anthropic-diagram
When your agent uses it
Generate editorial-style diagrams in the Anthropic blog visual style as .drawio files. Use this skill whenever the user wants to create a diagram, flowchart, architecture diagram, comparison chart, swimlane, or any visual that should look like Anthropic's blog article illustrations. Trigger on prompts like "draw a diagram", "create a flowchart", "visualize this process", "make an architecture diagram", "画流程图", "画架构图", "帮我画", or any request to turn text/process descriptions into a visual — even if the user doesn't say "Anthropic style" explicitly. This skill produces the calm, editorial, publication-quality look characteristic of Anthropic's technical blog.
What it loads into context
Frontmatter
151 tokensAlways available to the agent
SKILL.md
3,770 tokensWhen the skill is activated
Reference documents
10,615 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Step 1: Analyze the Request
- Step 2: Build the DiagramSpec
- Step 3: Generate draw.io XML
- Step 4: Layout rules
- Step 5: Write and open
- Quality checklist
- Reference files
Files
README.mddoc7,253 bytesREADME_CN.mddoc8,246 bytesreferences/color-palette.mddoc11,698 bytesreferences/pattern-library.mddoc17,735 bytesskill.mdcore13,115 bytesskill.mdcore13,115 bytesskill.mdcore13,115 bytesskill.mdcore13,115 bytes
Read SKILL.md
# Anthropic-Style Diagram Skill
Generate draw.io diagrams that match the editorial, warm, minimalist visual style of Anthropic's blog article illustrations.
## Workflow
```
User text → DiagramSpec (written out as text) → Styled draw.io XML → .drawio file
```
---
## Step 1: Analyze the Request
Skills included
- anthropic-diagram
Repository facts
- License
- MIT
- Created
- Mar 25, 2026
- Last pushed
- Mar 25, 2026
- Forks
- 23
- Open issues
- 0
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 3 notes
anthropic-diagram/skill.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedanthropic-diagram/skill.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedanthropic-diagram/skill.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 9 network referencesin 2 files: anthropic-diagram/README_CN.md:6 anthropic-diagram/README.md:5
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 9 signals by file
anthropic-diagram/README.md
- Network accessline 5
A Claude Code skill that generates editorial-style diagrams in the visual language of [Anthropic's technical blog](https://claude.com/blog/product-management-on-the-ai-exponential) — calm, warm, and publication-ready — as `.drawio` files. - Network accessline 22
**Output format**: `.drawio` files (editable in [draw.io](https://www.drawio.com/) / diagrams.net), with optional PNG/SVG export. - Network accessline 86
This skill is designed for [Claude Code](https://github.com/anthropics/claude-code). To install: - Network accessline 91
> **Prerequisite**: [draw.io Desktop](https://www.drawio.com/) must be installed if you want files to open automatically after generation.
anthropic-diagram/README_CN.md
- Network accessline 6
一个 Claude Code 技能，用于生成具有 [Anthropic 技术博客](https://claude.com/blog/product-management-on-the-ai-exponential) 视觉语言风格的编辑型图表，简洁、温暖，并输出为 `.drawio` 文件。 - Network accessline 24
**输出格式**：`.drawio` 文件（可在 [draw.io](https://www.drawio.com/) / diagrams.net 中编辑），并可选择导出为 PNG/SVG。 - Network accessline 26
**使用方法**：打开 http://draw.io 网站，在 Create New Diagram 页面，直接将`.drawio` 文件拖入网站即可。 - Network accessline 94
> **前置条件**：如果你希望生成后自动打开文件或者自动生成 PNG 格式，则需要先安装 [draw.io Desktop](https://www.drawio.com/)。 - Network accessline 139
> **前置条件**：需要先安装 [draw.io Desktop](https://www.drawio.com/)。
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.
Signal confidence: 9 facts
- Network access in prose of documentationanthropic-diagram/README.md:5Low confidence
- Network access in prose of documentationanthropic-diagram/README.md:22Low confidence
- Network access in prose of documentationanthropic-diagram/README.md:86Low confidence
- Network access in prose of documentationanthropic-diagram/README.md:91Low confidence
- Network access in prose of documentationanthropic-diagram/README_CN.md:6Low confidence
- Network access in prose of documentationanthropic-diagram/README_CN.md:24Low confidence
- Network access in prose of documentationanthropic-diagram/README_CN.md:26Low confidence
- Network access in prose of documentationanthropic-diagram/README_CN.md:94Low confidence
- Network access in prose of documentationanthropic-diagram/README_CN.md:139Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md anthropic-diagram/skill.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md anthropic-diagram/skill.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md anthropic-diagram/skill.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md anthropic-diagram/skill.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md anthropic-diagram/skill.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md anthropic-diagram/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.
