architecture-diagram
Skill15 starsChanged 5 months agoMITView on GitHub
Generate a human-friendly overview infographic by scanning the live project structure, including workspace crates, skills, and scripts. Use this skill whenever the user asks to regenerate, refresh, or update the overview diagram. Triggers on phrases like "update the overview", "regenerate the overview SVG", or "sync the overview".
44 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- nohemi20231/design-skillstheir own version, first seen Nov 8, 2026
- seayniclabs/homelab-infra-mcptheir own version, first seen Nov 8, 2026
- ashleysbrain/skillstheir own version, first seen Nov 8, 2026
- ZhouYinLong-lab/Dog-Skillstheir own version, first seen Nov 8, 2026
- delorenj/skillstheir own version, first seen Nov 7, 2026
- d-o-hub/github-template-ai-agentsedited, first seen Nov 3, 2026
Used with
Projects with it also use competitor-news-monitor, blocked-page-recovery 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.
aivrarSkillcompetitor-news-monitor
Watch named companies for material news; cited digests.
Also in 6 projects that use this
aivrarSkillblocked-page-recovery
Recover blocked/paywalled/WAF'd pages via fallbacks.
Also in 6 projects that use this
john-data-chenSkillteams-meeting-pipeline
Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.
Also in 8 projects that use this
john-data-chenSkilltouchdesigner-mcp
Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.
Also in 5 projects that use this
Tommy-ywSkillsongwriting-and-ai-music
Songwriting craft, AI music generation prompts (Suno focus), parody/adaptation techniques, phonetic tricks, and lessons learned. These are tools and ideas, not rules. Break any of them when the art calls for it.
Also in 9 projects that use this
mae616Skillp5js
p5.js(クリエイティブコーディング)のProcessing由来「コードでスケッチ」思想を軸に、setup/drawループ・座標系・インタラクション・パフォーマンス最適化を整理する。p5.js、Processing、クリエイティブコーディング、ジェネラティブアート、インタラクティブ表現、ビジュアルプログラミング、Canvas描画、パーティクル、フラクタル、ノイズ表現に関する相談で必ず使うこと。ユーザーが「コードでアート」「動くビジュアル」「インタラクティブな描画」と言った場合にも適用する。
Also in 9 projects that use this
- +3 more from aivrar
Other versions44 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- d-o-hub/github-template-ai-agents★ 212% same
Wrote their own version · 43
- NousResearch/hermes-agent★ 262ksame name
- lahfir/agent-desktop★ 19ksame name
- vercel-labs/agent-desktop★ 19ksame name
- Cocoon-AI/architecture-diagram-generator★ 7.4ksame name
- Tommy-yw/RunbookHermes★ 546same name
- Mathews-Tom/armory★ 340same name
- aivrar/portable-hermes-agent★ 239same name
- konraddzbik/architecture-diagram-skill★ 143same name
- proyecto26/system-design-skills★ 118same name
- microsoft/github-copilot-modernization★ 48same name
33 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 repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms-full.txtllms.txt
- llms.txtllms.txt
- anti-ai-slopSkill
- atomic-commitSkill
- build-rustSkill
- codacySkill
- crates-io-name-checkSkill
- dora-reportSkill
- goap-agentSkill
- harnessSkill
- issue-triageSkill
- lint-rustSkill
- metrics-reporterSkill
- privacy-firstSkill
- release-rustSkill
- reviewing-pull-requestsSkill
- secret-lintSkill
- self-fix-loopSkill
- skill-creatorSkill
- skill-evaluatorSkill
- stacked-prsSkill
- task-decompositionSkill
- test-rustSkill
- tokio-performanceSkill
- triz-analysisSkill
- triz-solverSkill
- verify-actionsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 42 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 51
After the script exits:
- Distinctive: line 54
If counts differ from the last known state, summarize what changed.
- Very specific: line 91
Never commit a partially regenerated diagram: if export fails, the stale SVG stays in place and silently keeps advertising old counts.
“Common” is measured: kept by at least 6 in 10 of the 42 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
Overview Diagram
Generates a human-friendly overview infographic showing what the project is, how to get started, what's inside, and how it all connects.
Execution
Step 1 — Locate Project Root
ls .agents/ Cargo.toml 2>/dev/null || echo "NOT_FOUND"Step 2 — Generate the Diagram
python .agents/skills/architecture-diagram/scripts/generate_overview.py \
--root . \
--out .template/overview.excalidraw \
--svg-out .template/overview.svgThe script auto-discovers at runtime:
- Workspace crates →
cargo metadata(with Cargo.toml glob fallback) - AI skills →
.agents/skills/*/directories - Commands →
.opencode/commands/*.md - Quality checks →
config/xtask.jsontier check lists - CI jobs → job IDs across
.github/workflows/*.yml
Step 3 — Sync to Docs
cp .template/overview.svg docs/src/overview.svgscripts/sync-architecture.sh performs steps 2 and 3 in one shot and is what
the Update Overview Diagram workflow runs.
Step 4 — Confirm and Report
After the script exits:
- Tell the user the output path.
- Report counts: N crates · M skills.
- If counts differ from the last known state, summarize what changed.
Output
.template/overview.excalidraw— editable Excalidraw source.template/overview.svg— generated SVG for docs embedding
What the stats mean
The "BY THE NUMBERS" cards are derived, never hand-written. If a number looks wrong, fix the discovery logic rather than editing the generated files.
| Stat | Source |
| Workspace Members | cargo metadata workspace members (includes examples/* and benchmarks) |
| Crates | directories under crates/ that contain a Cargo.toml |
| AI Skills | .agents/skills/*/SKILL.md |
| CI Jobs | unique job IDs across .github/workflows/*.yml |
| Quality Checks | union of the checks lists for every tier in config/xtask.json |
| Shell scripts | scripts/*.sh |
Quality Checks previously scraped scripts/quality-gates.sh for cargo
invocations. That script is now a thin wrapper around cargo xtask, so the
count collapsed to 1 while the real gate ran nineteen checks. Do not
reintroduce command-scraping for this number.
Optional Dependencies
Node.js (for SVG/PNG export)
Required for SVG/PNG export from Excalidraw:
npm ciWithout Node.js, use --no-export to generate only the .excalidraw source.
Never commit a partially regenerated diagram: if export fails, the stale SVG
stays in place and silently keeps advertising old counts. Check that the
EXPORTED: lines appear before committing.
cargo must be on PATH for accurate crate discovery. Without it the script
falls back to parsing Cargo.toml globs and prints a warning — that path now
reports the same totals, but the warning is a signal that the run is degraded.
CLI Flags
| Flag | Description |
--root PATH | Workspace root (default: .) |
--out PATH | Excalidraw output path (default: .template/overview.excalidraw) |
--svg-out PATH | SVG export path (default: .template/overview.svg) |
--png-out PATH | PNG export path (optional, not tracked) |
--no-export | Skip SVG/PNG export (Excalidraw only) |
Rationalizations
| Rationalization | Reality |
| "The overview is close enough, no need to regenerate" | Stale diagrams mislead new contributors about project structure. |
| "I'll update the diagram manually" | Manual edits break on next regeneration and introduce inconsistencies. |
Red Flags
- Committing workspace changes without regenerating the overview.
- Manually editing the SVG instead of using the generator script.
- Direct push failures caused by missing retry loops or unhandled concurrent updates on main (see case
update-diagram-push-20260917in.agents/ci/regression-matrix.json).
Why the PNG is not committed
PNG export rasterises through the local font stack, so the same diagram yields
different bytes on a CI runner than on a developer machine. The SVG and
Excalidraw outputs are byte-identical everywhere. Because nothing embeds the
PNG — the README and docs both use overview.svg — committing it produced a
spurious "regenerate overview diagram" PR on every workflow run. Generate one
ad hoc with --png-out when you need a raster preview; do not commit it.
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.

