drawio-skill
Agent skill that turns natural language, code, Terraform/K8s, SQL, OpenAPI, AsyncAPI, Protobuf and GraphQL sources into editable, tested draw.io architecture diagrams: incremental sync, multi-view projection, drift diff, CI architecture tests, whiteboard derasterize, interactive HTML/PPTX/Mermaid exports.
Runssource: GitHubhomepagePythonMITcommit 7b996a17d055
Python, MIT licensed. The project labels itself: agent skills, architecture, architecture diagram, asyncapi, bpmn, c4 model, claude code and diagram.
drawio-skill runs. An Argusic agent installed it in 0 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The drawio-skill project runs fully: 174 unit tests pass, the diagramctl CLI (12 subcommands) works end-to-end for core semantic workflows, all importers produce correct IR, the MCP server responds with 9 tools, and the shape/index/validate infrastructure is operational. Only the draw.io desktop binary (for native export) and Graphviz (for auto-layout) are missing from this container.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- test_views_and_story_are_accessible failed: write_drawio fallback (_grid_page) did not emit UserObject wrappers for cross-page linked nodes when Graphviz was absent3 minutes
- Install time
- under a minute
- Cold machine to finish
- 10 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- python3 -m unittest discover -s tests: 174 passed, 10 skipped (8 no Graphviz dot, 2 no drawio CLI). diagramctl doctor/build/inspect/query/test/whatif/story all produced correct output. shapesearch resolved dynamodb correctly. validate checked .drawio files clean. mcp_server listed 9 tools.
- Model tokens used
- 81,848
- Exact commit tested
- 7b996a17d055
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 2, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
],
'test_depth': 'tier1_real',
'verified_how': 'python3 -m unittest discover -s tests: 174 passed, 10 skipped (8 no Graphviz d…
'final_state': 'The drawio-skill project runs fully: 174 unit tests pass, the diagramctl CLI (1…
}
print('ARGUSIC_RESULT:' + json.dumps(result))
\"" in /work/repo
succeeded in 0ms:
All done. The project is fully operational — the only changes made were fixing the `_grid_page` fal…
tokens used
81,848
All done. The project is fully operational — the only changes made were fixing the `_grid_page` fal…Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 0 minutes, faster than the median of the 8 comparable projects Argusic has measured.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
Of the 9 agent-skills projects Argusic has installed and timed, drawio-skill was the 1st fastest to reach a running state, and 8 of 9 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 0 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agent-skillsarchitecturearchitecture-diagramasyncapibpmnc4-modelclaude-codediagramdiagrams-as-codedrawioflowchartgithub-actionsgraphqlimage-to-diagramkubernetesmcp-serverprotobufsysmlterraformuml
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/drawio-skill)Questions
- Does drawio-skill run?
- Yes. drawio-skill runs. Argusic installed and launched it on a clean machine in 0 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test drawio-skill?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7b996a17d055. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test drawio-skill?
- The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does drawio-skill take to install?
- 0 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does drawio-skill need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing drawio-skill?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does drawio-skill compare with the alternatives?
- Of the 9 agent-skills projects Argusic has installed and timed, drawio-skill was the 1st fastest to reach a running state, and 8 of 9 reached one at all.
- Where is the evidence for drawio-skill?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.