skills
Agent Skills for Google products and technologies
Runssource: GitHubPythonApache-2.0commit f004524de788
Python, Apache-2.0 licensed. The project labels itself: google, googlecloud and skills.
skills runs. An Argusic agent installed it in 29 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 152/152 tests pass; FastAPI NFS bridge service serves 5 endpoints with correct response codes; PromQL validator and widget proto generator produce correct output; skills CLI installs the repo successfully.
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.
- npx skills CLI requires Node >=22 but container has Node 183 minutes
- absl flags collision in fetch_terraform_template_test.py and list_terraform_templates_test.py when running together under pytest2 minutes
- Missing Python dep promql-parser in validate_promql.py1 minute
- absl flags unparsed in assemble_widget_proto_test.py (test_tmpdir flag)1 minute
- Install time
- 29 minutes
- Cold machine to finish
- 7 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- .venv/bin/python -m unittest across all 16 test files: 152 passed, 0 failed. curl http://127.0.0.1:8101/api/v1/health returned HTTP 200 + 'healthy'. curl http://127.0.0.1:8101/api/v1/tree?path=/ returned 200 + 3 entries. curl http://127.0.0.1:8101/api/v1/read?path=/a.txt returned 200 + correct content. npx skills add google/skills --json -y installed 180 skills.
- Model tokens used
- 598,172
- Exact commit tested
- f004524de788
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
---broken symlinks--- The `sh` syntax errors are because dash doesn't support bash syntax — these have bash shebangs. Let… exec /bin/sh -lc 'cd /work/repo && e=0; count=0; for f in $(find skills plugins -name '"'*.sh'); do coun… succeeded in 0ms: checked 35 shell files with bash -n; issues: 0 All shell scripts pass bash syntax check — the earlier failures were dash-vs-bash differences from … **Verified state:** Python test suite: 152/152 passing. FastAPI bridge server launched and returned… tokens used 598,172 All shell scripts pass bash syntax check — the earlier failures were dash-vs-bash differences from … **Verified state:** Python test suite: 152/152 passing. FastAPI bridge server launched and returned…
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 29 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 Apache-2.0, 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.
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
| 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 | 0.07 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/skills)Questions
- Does skills run?
- Yes. skills runs. Argusic installed and launched it on a clean machine in 29 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test skills?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit f004524de788. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test skills?
- 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 skills take to install?
- 29 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 skills need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing skills?
- 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 skills?
- 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.