nature-skills
符合nature论文学术表达和科研绘图的Skill
Runssource: GitHubPythonApache-2.0commit bd4e415c1dca
Python, Apache-2.0 licensed. The project labels itself: codex skills, nature and nature skills.
nature-skills runs. An Argusic agent installed it in 2.3 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
20 nature-skills packages installed to ~/.codex/skills/ and verified byte-identical. All 104 Python tests pass, both bash test suites pass, all 6 repository validation scripts pass, and all asset files are well-formed.
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 97.3 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.
- npx skills requires Node >=22 but 18.19.1 is installed1.2 minutes
- rsync binary not found (no root to apt install)0.8 minutes
- PyYAML and pytest not in system Python0.3 minutes
- Install time
- 2 minutes
- Cold machine to finish
- 13 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- python3 -m pytest tests/ passed 9/9; python3 -m pytest scripts/tests/ passed 95/95 (9 skipped for optional deps); both bash test suites passed; scripts/update-codex-skills.sh --check confirmed all 20 skills MATCH in ~/.codex/skills/; all 6 validation scripts pass; all 5 assets validated via ffmpeg
- Model tokens used
- 70,625
- Exact commit tested
- bd4e415c1dca
- 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.
**1. `npx skills add` fails — Node.js version too old** (Node 18.19.1, needs >=22). Fix: used the r… **2. `update-codex-skills.sh` fails — `rsync` not installed** (no root to `apt install`). Fix: wrot… **3. PyYAML and pytest not available** in the system Python. Fix: created a venv (`/tmp/nature-skil… **4. Duplicate `test_generate_star_history.py`** in `tests/` and `scripts/tests/` causes a pytest c… All fixes required no changes to the repository itself — only environment workarounds. ## What was verified - **All 6 validation scripts** pass: `validate-readmes`, `validate-readme-mirror`, `validate-reposi… - **All 104 Python tests pass** (95 pass + 9 skipped due to optional deps PyMuPDF/matplotlib — thos… - **Both bash test suites pass**: `test-update-codex-skills-safety` (prune safety + rollback) and `… - **All 20 skills installed** to `~/.codex/skills/` and verified byte-identical via `diff` (`update… - **All 5 asset files** (`readme-banner-cn.png`, `readme-banner-en.png`, `star-history.svg`, `star-… - **`index.html`** is valid 97KB HTML structure.
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 2.3 minutes.
- Recovered from all 3 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 Apache-2.0, as reported by its host.
- Measured 3 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.
- A quick evaluation: it was running 2.3 minutes after the clone.
Run history
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/nature-skills)Questions
- Does nature-skills run?
- Yes. nature-skills runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test nature-skills?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit bd4e415c1dca. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test nature-skills?
- The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does nature-skills take to install?
- 2.3 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 nature-skills need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing nature-skills?
- 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 nature-skills?
- All 3 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.