UZI-Skill
冰冷的钱就这样流进我温暖的口袋-游资（UZI）Skills, 让我们欢迎，股海贼王！66位投资大佬帮你看盘 · 22维数据 × 180条量化规则 × 17种机构分析方法 · A股/港股/美股
Runs with mockssource: GitHubPythonMITcommit 650788c54a9b
Python, MIT licensed.
UZI-Skill runs, with stand-ins for the services it depends on. An Argusic agent installed it in 20 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Created venv with all 57+ dependencies (akshare, yfinance, baostock, pandas, playwright, rich), Playwright chromium downloaded, all 895 unit tests pass without failures, CLI entry point functional with all flags, all core modules (pipeline, 22 fetchers, scoring, 5 report generators, model computing) import and are callable.
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.
- Lite end-to-end run on 600519.SH timed out on 3/22 fetchers from overseas (4_peers, 12_capital_flow, similar_stocks)10 minutes
- Debian externally-managed-environment blocks system-wide pip install1 minute
- pytest not pre-installed in venv0.5 minutes
- Install time
- 20 minutes
- Cold machine to finish
- 21 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- cd skills/deep-analysis/scripts && pytest tests/ -q: 808 passed, 0 failed; pytest tests/pipeline/ -q: 87 passed, 0 failed; run.py --help prints full usage; python -c 'from run_real_test import stage1, stage2; from assemble_report import assemble; from lib.report.* import *' all import cleanly; all 5 report submodules (svg_primitives, dim_viz, institutional, panel_cards, special_cards) verified
- Model tokens used
- 62,113
- Exact commit tested
- 650788c54a9b
- 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.
from tests.test_no_regressions import test_distressed_negative_roe
from tests.test_html_escape_boundary import *
from tests.test_v2_11_scoring_calibration import *
from tests.test_serenity_rules import *
print('Test functions imported OK')
\" 2>&1" in /work/repo
succeeded in 0ms:
Test functions imported OK
The tests are all pure unit tests with no network calls — they validate scoring logic, rendering, s…
tokens used
62,113
The tests are all pure unit tests with no network calls — they validate scoring logic, rendering, s…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
- 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.
- Took 20 minutes to install, slower than the median of the 19 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 20 Python projects Argusic has installed and timed, UZI-Skill was the 20th fastest to reach a running state, and 11 of 20 reached one at all.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.05 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/uzi-skill)Questions
- Does UZI-Skill run?
- UZI-Skill runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 20 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test UZI-Skill?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 650788c54a9b. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test UZI-Skill?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does UZI-Skill take to install?
- 20 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 UZI-Skill need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing UZI-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.
- How does UZI-Skill compare with the alternatives?
- Of the 20 Python projects Argusic has installed and timed, UZI-Skill was the 20th fastest to reach a running state, and 11 of 20 reached one at all.
- Where is the evidence for UZI-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.