patent-disclosure-skill
中国专利.skill：专利点挖掘与交底书（发明/实用/外观）编写，通俗解读专利，嗅探政策动向，辅助审查答复。
Runs with mockssource: GitHubhomepagePythonMITcommit 1acef5c8bf95
Python, MIT licensed. The project labels itself: chinese, disclosure, obsidian, patent and skill.
patent-disclosure-skill runs, with stand-ins for the services it depends on. An Argusic agent installed it in 4 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Python 3.12 venv with all 13 pip dependencies installed (python-docx 1.2.0, PyYAML 6.0.3, playwright 1.63.0, etc.), Playwright Chromium 153.0.8010.12 downloaded and browser probe returns ok=true, md_to_docx/docx_to_md roundtrip produces valid .docx and .md, mermaid_render converts mermaid code fences to PNG, all 7 sub-skill test suites pass (367 passed, 8 skipped).
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 92 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.
- playwright chromium browser not found on first probe2 minutes
- externally-managed-environment error on system pip install1 minute
- patent-map test failed due to floating-point PCA assertion without numpy; patent-oa tests couldn't collect without numpy1 minute
- Install time
- 4 minutes
- Cold machine to finish
- 5 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- pytest passed all 7 sub-skill test suites: patent-disclosure 189/6, patent-application 37, patent-docket 11, patent-search 40/9, patent-reader 58, patent-map 13, patent-oa 19/2 = 367 passed, 8 skipped. md_to_docx produced valid .docx from .md, docx_to_md roundtripped it, mermaid_render produced PNG from mermaid fence, browser.py --probe returned ok=true channel=chromium.
- Model tokens used
- 151,951
- Exact commit tested
- 1acef5c8bf95
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
succeeded in 654ms: PROBE: ok=true channel=chromium error= 3. md_to_docx roundtrip: MD -> DOCX -> MD 已写入: /tmp/test_disclosure.docx 图片目录: /tmp/test_disclosure_back_media 4. mermaid_render: MD with mermaid -> PNG 1 fig_001.png 5. All 7 test suites passed 2026-09-27T13:20:58.742763Z ERROR codex_core::session: failed to record rollout items: thread 01a0e… tokens used 151,951
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
- Installed in 4 minutes.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.03 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/patent-disclosure-skill)Questions
- Does patent-disclosure-skill run?
- patent-disclosure-skill runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 4 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test patent-disclosure-skill?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1acef5c8bf95. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test patent-disclosure-skill?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does patent-disclosure-skill take to install?
- 4 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 patent-disclosure-skill need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing patent-disclosure-skill?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for patent-disclosure-skill?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.