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。
Runssource: GitHubhomepagePythonMITcommit 1acef5c8bf95
Python, MIT licensed. The project labels itself: chinese, disclosure, obsidian, patent and skill.
patent-disclosure-skill runs. An Argusic agent installed it in 53 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Python dependencies installed in venv, Playwright Chromium browser functional, all 374 tests pass across 7 patent skill packages, and CNIPA patent crawl works end-to-end against the real Chinese patent office website.
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 96 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.
- No system Chrome/Edge browser found for Playwright18 minutes
- Missing numpy broke patent-map PCA projection test10 minutes
- Externally managed Python environment prevented system-wide pip install4 minutes
- CNIPA live search tests (9) timed out against real epub.cnipa.gov.cn
- Install time
- 53 minutes
- Cold machine to finish
- 15 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- pytest across 7 sub-skill test suites: 374 passed, 1 skipped; CNIPA epub chain test with '知识图谱' keyword returned 3 real patent records from epub.cnipa.gov.cn; browser probe confirmed playwright chromium works
- Model tokens used
- 296,805
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
| `patent-docket` | 11 | all passed | | `patent-search` | 40 (+9 live deselected) | all passed | | `patent-reader` | 58 | all passed | | `patent-map` | 13 | all passed | | `patent-oa` | 20 (+1 skipped) | all passed | | **Total** | **374 passed, 1 skipped** | | **Issues encountered and resolved:** 1. **Externally-managed Python environment** (PEP 668) — fixed by creating a venv 2. **Missing browser for Playwright** — fixed by installing Playwright's bundled Chromium 3. **Missing numpy** for the patent-map PCA projection test — fixed by pip installing numpy 4. **CNIPA live tests timed out** — the real patent office site was unreachable for the `patent-sea… **Browser probe**: `PROBE: ok=true channel=chromium` — Playwright can launch the bundled Chromium b…
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 53 minutes.
- Recovered from all 4 errors 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.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs | 100.00 | 0.12 | |
| 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?
- Yes. patent-disclosure-skill runs. Argusic installed and launched it on a clean machine in 53 minutes, hitting 4 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. 2 attempts are 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 $0.12: 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?
- 53 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?
- 4 things broke in the recorded run, and 4 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?
- 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.