human-writing
让 AI 写的中文读起来像一个具体的人在说话。通用创作与改稿 Skill，开箱即用。
Runssource: GitHubPythonMITcommit 5c0c30d33648
Python, MIT licensed. The project labels itself: agent skills, chinese writing, creative writing and writing skill.
human-writing runs. An Argusic agent installed it in 2 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
All 36 tests pass; check_prose.py correctly reports issues on SKILL.md and passes README.md. The Skill is ready for use by placing the human-writing/ directory in the agent's skills path.
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. 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.
- Install time
- 2 minutes
- Cold machine to finish
- under a minute
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- python3 -m unittest discover -s tests -v: Ran 36 tests, all passed (OK). python3 human-writing/scripts/check_prose.py README.md: exit 0, clean. python3 human-writing/scripts/check_prose.py human-writing/SKILL.md: exit 1, correctly flagged 12 failures and 10 warnings.
- Model tokens used
- 41,566
- Exact commit tested
- 5c0c30d33648
- 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.
**CI:** The GitHub workflow validates by running `python -m unittest discover -s tests -v` on Pytho… **Installation:** This is a Skill (not a package/app), so "install" means placing the `human-writin… **Verification:** Both the test suite and the prose checker were exercised and produced documented … tokens used 41,566 All 36 tests pass with exit code 0. The checker is being exercised. Let me now compile the final re… Everything works. Here's the summary: **Tests:** All 36 tests pass (OK, exit 0). **Checker tool:** `check_prose.py` runs successfully on the README (clean pass, exit 0), and on SKI… **CI:** The GitHub workflow validates by running `python -m unittest discover -s tests -v` on Pytho… **Installation:** This is a Skill (not a package/app), so "install" means placing the `human-writin… **Verification:** Both the test suite and the prose checker were exercised and produced documented …
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 minutes, faster than the median of the 118 comparable projects Argusic has measured.
- Nothing broke on the way: zero errors between clone and running.
- 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 119 agent-skills projects Argusic has installed and timed, human-writing was the 41st fastest to reach a running state, and 90 of 119 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 2 minutes after the clone.
- Following its own README: the documented path worked with nothing to fix.
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)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/human-writing)Questions
- Does human-writing run?
- Yes. human-writing runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test human-writing?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5c0c30d33648. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test human-writing?
- The run that produced this verdict cost $0.01: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does human-writing take to install?
- 2 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 human-writing need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing human-writing?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does human-writing compare with the alternatives?
- Of the 119 agent-skills projects Argusic has installed and timed, human-writing was the 41st fastest to reach a running state, and 90 of 119 reached one at all.
- Where is the evidence for human-writing?
- 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.