architecture-drawer

architecture-drawer

English · 简体中文

A skill for Claude Code, Codex, Open Code, Pi Agent, and other AI coding agents: turn a text description of your system architecture into an editable PowerPoint architecture diagram.

What it is

Turn text descriptions of an architecture into editable PPT diagrams: the agent generates an SVG from your description, auto-validates the layout, then exports to native PowerPoint shapes.

vs. direct image generation

Showcase

All diagrams below were generated entirely from text descriptions by the skill, then scored by the 13-dimension evaluator (each scored ≥76/100). They double as the regression suite under evals/ — including the first non-architecture case (a process flowchart).

vLLM — High-Throughput LLM Inference Serving (PagedAttention)

Six-layer request pipeline (client → API server → engine → paged KV cache → execution → optimizations). Solid edges = data flow; dashed = cache/block management. Scheme S1 Monochrome Blue.

MLIR AI Compiler — Multi-Stream Execution Pipeline

A 4-layer × multi-column matrix (graph optimization → transformation → lowering → codegen) with vertical-fusion grouping and a concurrent multi-stream overlap timeline. 8-accent categorical palette.

Agent Infrastructure — Layered Architecture

Five horizontal layers (application → orchestration → core capabilities → execution → infrastructure) with a cross-cutting security/observability band. Bilingual CN/EN labels. Neutral grays + 5 colored core modules.

CI/CD Deployment Pipeline — Process Flowchart

The first non-architecture case: a top-to-bottom process flowchart with four quality-gate decisions (Build → Lint/SAST → Tests → Smoke) whose "No" branches converge via gray junction merge points onto a single Failed terminator. Green terminators · yellow decision diamonds · orange I/O hexagon · purple double-border subprocesses. Flowchart role palette (color = role).

Best Practices

1. Start with a clear text description. Before coding, describe the architecture in prose—how many layers, what components each layer has, how they connect, and any special annotations. A crisp text spec (like the specs in evals/*/input.md) is the single biggest predictor of a quality diagram. For open-source projects, you can use the system architecture description from DeepWiki.
2. Let the skill generate. Submit the text description to the skill and let it generate the initial gen.py and SVG. The evaluator automatically catches overlaps, dangles, and crossings.
3. The skill auto-reviews the score. If the score is ≥80, the diagram is structurally sound. If <80, the agent can automatically fix layout issues via auto_refine or by iterating on the evaluator report.
4. Export to PPTX for final polish. Run svg_to_pptx() to get an editable PowerPoint file. Tweak colors, fonts, arrows, and layout there to match your brand or publication style—these belong in the presentation layer, not the generator code.

Suggested workflow: first discuss with DeepWiki or your agent to produce a clear text description of the system architecture, then use this skill to quickly generate a PPTX diagram, and finally fine-tune colors, labels, and other details directly in PPT.

Install (Claude Code)

This repo is a plugin marketplace. Add it and install the plugin:

/plugin marketplace add Andy1314Chen/architecture-drawer
/plugin install architecture-drawer@architecture-drawer

Or from the CLI:

claude plugin marketplace add Andy1314Chen/architecture-drawer
claude plugin install architecture-drawer@architecture-drawer

Scope with --scope project (shared via version control) or --scope local (gitignored). Default is user.

Codex CLI

Codex CLI fully supports the Agent Skills directory structure.

Copy the skill directory into Codex's skills folder (usually ~/.codex/skills/):

cp -r plugins/architecture-drawer/skills/architecture-drawer ~/.codex/skills/architecture-drawer

Or install project-scoped (recommended):

mkdir -p .codex/skills
cp -r plugins/architecture-drawer/skills/architecture-drawer .codex/skills/

Once installed, ask Codex naturally — the workflow in SKILL.md is consumed automatically:

> Draw the architecture of vLLM and export to PPTX

Other agent platforms (Gemini CLI, Cursor, Copilot)

Each skill is a standalone Agent Skills spec directory. Copy it into your platform's skills location (typically .agents/skills/):

cp -r plugins/architecture-drawer/skills/architecture-drawer .agents/skills/architecture-drawer

Dependencies

The agent generates a gen.py that imports four pure-Python modules (svg_utils.py, evaluator.py, semantic_qa.py, svg2pptx.py) co-located in the skill. You don't write this code — the agent does. Install these once so generated diagrams can render and export:

Testing

The suite is layered so each layer is cheap, deterministic, and covers a distinct failure mode:

The agent-replay layer is the closest to real usage: the skill is installed (never inlined), a real agent discovers it via its native skill mechanism, and the harness — not the agent — re-runs the produced gen.py deterministically. It needs the pi CLI and a provider key; backend wiring lives in tests/agent_backends.py. Pin both the provider and the model (--agent-provider zai --agent-model glm-5.3, or PI_AGENT_PROVIDER/PI_AGENT_MODEL) — the headless run otherwise inherits pi's interactive default provider, which may lack credentials and fail with an opaque upstream 403; a bare --model id can also be ambiguous across providers. Other options: --agent-iter N caps the stateless refine rounds (default 3), --agent-eval <name> restricts the run to one frozen eval, and --agent-case <dir> replays an ad-hoc case outside the frozen set — any directory containing an input.md spec; it never enters the deterministic regression set (no gen.py requirement, no golden snapshot), the agent authors gen.py in the sandbox, and --agent-keep retains everything under output/agent_replay/<dir-name>/.

Repository layout

architecture-drawer/
├── .claude-plugin/marketplace.json              # Claude Code marketplace registry
├── plugins/architecture-drawer/
│   ├── .claude-plugin/plugin.json               # plugin manifest
│   └── skills/architecture-drawer/
│       ├── SKILL.md                             # agent-consumable workflow (spec-compliant)
│       ├── scripts/                             # svg_utils.py · evaluator.py · semantic_qa.py · svg2pptx.py
│       ├── references/design_specs.md           # 4 preset color schemes (S1–S4)
│       ├── evals/                               # 8 regression cases (7 architecture + 1 flowchart, gen.py each)
│       └── assets/
├── tests/                                       # pytest: layered regression (see "Testing")
│   ├── conftest.py                              # fixtures, thresholds, score helpers, CLI options
│   ├── agent_backends.py                        # Pi coding-agent backend + leak-free sandbox builder
│   ├── test_regression.py                       # deterministic quality+snapshot for every frozen gen.py
│   ├── test_skill_spec.py                       # Agent Skills spec compliance
│   ├── test_doc_api.py                          # doc ↔ API drift guard (always on)
│   ├── test_semantic_qa.py                      # semantic QA: marker/size/label/route/text checks
│   ├── test_agent_replay.py                     # opt-in real-agent replay (Pi)
│   └── golden/*.svg                             # snapshot baselines
└── examples/                                    # minimal demo of the generate-evaluate-export loop

Community

Thanks to the LINUX DO community. The project gained wider reach, discussion, and real-world feedback after being shared there, and those conversations have helped me keep finding issues and improving architecture-drawer.

References & acknowledgments

The geometry/connection detection draws on several open-source projects (their reference docs and validators were studied): ink-graph, fireworks-tech-graph, svg-animations, svg-design, and svg2pptx (the architectural blueprint for the PPTX export module). See the full credits in SKILL.md.

License

MIT — see LICENSE.