diagram
Skill1 starsChanged 3 months agoMITView on GitHub
Generates technical diagrams using the D2 language, with automatic color-contrast verification and diagram-type detection.
51 other projects use a version of this.
Adopted by
Most recently taken up by
- jame-hv/brse-toolkittheir own version, first seen Nov 8, 2026
- clearsmog/claude-skillstheir own version, first seen Nov 8, 2026
- domengabrovsek/agent-configtheir own version, first seen Nov 8, 2026
- domengabrovsek/claudetheir own version, first seen Nov 8, 2026
- ActuallyNodejam/openpaperworktheir own version, first seen Nov 8, 2026
- seayniclabs/homelab-infra-mcptheir own version, first seen Nov 8, 2026
Used with
Projects with it also use ios-sync, benchmark-models 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.
Saqlain-811Skillios-sync
Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)
Also in 4 projects that use this
ShreyRaviSkillbenchmark-models
Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchmark, which measures web page performance. Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".
Also in 5 projects that use this
ShreyRaviSkilllanding-report
Read-only queue dashboard for workspace-aware ship. Shows which VERSION slots are currently claimed by open PRs, which sibling Conductor workspaces have WIP work likely to ship soon, and what slot /ship would pick next. No mutations — just a snapshot. Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next". (gstack)
Also in 5 projects that use this
timurgaleevSkilldocument-generate
Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.
Also in 4 projects that use this
Saqlain-811Skillios-clean
Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)
Also in 3 projects that use this
seek888Skillopen-gstack-browser
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".
Also in 4 projects that use this
- +2 more from ShreyRavi
- +1 more from Saqlain-811
Other versions51 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 51
- garrytan/gstack★ 141ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- HybridAIOne/hybridclaw★ 159same name
- Kastalien-Research/thoughtbox★ 64same name
- jantichy/claude★ 45same name
- domengabrovsek/agent-config★ 22same name
- domengabrovsek/claude★ 22same name
- heathdutton/claude-d2-diagrams★ 16same name
- johnlindquist/claude-workshop-skills★ 16same name
41 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- alloy-structural-analysisSkill
- analyzing-architectureSkill
- color-accessibilitySkill
- daily-briefingSkill
- design-docSkill
- eng-career-goals-writerSkill
- gh-repo-managementSkill
- git-commit-helperSkill
- jiraSkill
- jqSkill
- morphirSkill
- newrelic-cliSkill
- oli-storage-managerSkill
- project-instructorSkill
- qmd-searchSkill
- rigorous-reviewSkill
- save-zkSkill
- scalaSkill
- smart-initSkill
- sourcegraph-searchSkill
- structured-memorySkill
- visualizeSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 43 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Use this skill whenever a system architecture, data flow, sequence diagram, or service interaction needs to be visualized.
- Distinctive: line 25
Strict Typing: Every entity is a simple shape with a class and structured metadata.
- Very specific: line 39
Context: Use D2 "Groups" (empty containers) for Domains (e.g., Analytics_Domain).
- Very specific: line 42
Actors: Use shape: person for human users or external systems.
- Distinctive: line 57
DO NOT: use semicolons in style blocks.
- Distinctive: line 58
DO NOT: use local file paths for icons.
- Very specific: line 64
Use undefined classes (tags) such as systembe for grouping components.
“Common” is measured: kept by at least 6 in 10 of the 43 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.
Files
Diagram Creator
Generate professional architecture and sequence diagrams using the D2 declarative language. Output is a rigorous engineering artifact modeling complex distributed systems with precision, enforcing strict separation between inventory (what exists) and topology (how it connects) - with automatic color-contrast verification and diagram-type detection
When to use me
Use this skill whenever a system architecture, data flow, sequence diagram, or service interaction needs to be visualized. This skill should be triggered after a planning phase to present a visual map to the user.
Core Instructions
Core Philosophy: "Measure Once, Cut Twice"
- Inventory First: You must define every entity fully (metadata, technology, owner) before drawing a single line.
- Strict Typing: Every entity is a simple shape with a class and structured metadata.
- Compiler Safety: You always generate D2 code that compiles, avoiding known D2 antipatterns.
Instructions
1. Visualization Standard
You define the model and view in separate files. The model file (models.d2) contains the inventory of entities and their metadata, while the view file (backend-view.d2) contains the topology (connections) and styling. This separation ensures clarity and maintainability.
- You Always reference the files
models.d2andbackend-view.d2for examples of how to structure your code. - You view files must import model files to reference entities.
- You Always validate your D2 files using the d2 CLI tool against the view files
2. C4 Model Integration
- Context: Use D2 "Groups" (empty containers) for Domains (e.g.,
Analytics_Domain). - Container: Runtime units (Services, DBs).
- Component: Code units (Libraries, DAGs).
- Actors: Use
shape: personfor human users or external systems.
3. D2 Code Structure (Strict Hierarchy)
You must generate code in this exact order to ensure compilation:
- Metamodel (Classes):
- Critical Constraint: Classes must be defined at the root.
- Critical Constraint: No nesting. You cannot define a class inside
classes. - Critical Constraint: No inheritance. One class cannot reference another via
class:.
- Domain Contexts: Empty groups with
fill: transparent. - Entity Inventory: Define objects using dot notation (
Domain.Entity). No connections here. - Topology: Define connections (
->) in separate files after suspending unwanted classes.
Negative Constraints (Guardrails)
- DO NOT mix entity definitions with relationships.
- DO NOT use semicolons in style blocks.
- DO NOT use local file paths for icons.
- DO NOT nest classes inside the
classesblock.
Canonical Example
- Reference the
models.d2andbackend-view.d2files as examples - Use undefined classes (tags) such as
systembefor grouping components. Thedomain_actorclass is defined with specific styles, and then bothsystembeanddomain_actorare applied to theapi_servicecomponent.
Execution Steps
- Analyze the user's request to identify Domains, Containers, and Components.
- Draft the Inventory list mentally, and assigning tech stacks.
- Generate the D2 code following the instructions strictly.
- Recommend diagram type — once the model/view files exist, run
python3 main.py recommend-diagram-type --model_path <view-file>.d2. This parses actual entity/relationship counts, cycles, actor shapes, and edge ordering from the file and returnssequence,state, orc4— a deterministic decision, not a free-form read of the user's request. If the recommendation doesn't match what was drafted in step 1, prefer the tool's output and adjust the structure. - Check contrast — run
python3 main.py check-contrast --model_path models.d2. This validates every class'sfill/font-colorpair againstpastel textcolorand reports mismatches. Fix any"ok": falseresult before rendering.- Known limitation: this check assumes plain black/white text and will report
_md/_grpmarkdown classes as failing even when they intentionally use a tintedfont-color(see the styling comment at the top ofmodels.d2). Treat_md/_grpclass failures as informational, not blocking — thestrokevsfilldistinction on those classes is the real readability signal, notfont-color.
- Known limitation: this check assumes plain black/white text and will report
- Preview — render just the class/legend definitions from
models.d2to a small SVG first (d2 models.d2 preview.svg) and confirm it compiles cleanly before rendering the full diagram. - Render the full view file to SVG (
d2 backend-view.d2 output.svg) and present the result.
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
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.

