claude-skills
67 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer.
Runssource: GitHubPythonMITcommit 882ef55e377d
Python, MIT licensed. The project labels itself: ai agents, claude, claude code, claude marketplace and claude skills.
claude-skills runs. An Argusic agent installed it in 7 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
python3 scripts/validate-skills.py passes with 0 errors, make test runs 12/12 passing, and the site builds 99 static pages successfully via Node 20
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, 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.
- site/scripts/sync-content.mjs uses import.meta.dirname (Node 21+) but container has Node 182 minutes
- python command not found; Makefile and test script used bare python1 minute
- pyyaml not installed; validate-skills.py fell back to broken simple parser producing 17 false errors1 minute
- pyright and ruff not on PATH1 minute
- astro requires Node >=20 but container ships Node 181 minute
- Install time
- 7 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- make test exited 0, 12/12 passed; make validate exited 0, 67 skills validated (0 errors); npx [email protected] ./node_modules/.bin/astro build in site/ completed with 99 pages built; npx prettier --check on source markdown files passed
- Model tokens used
- 274,298
- Exact commit tested
- 882ef55e377d
- 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.
**Fixes applied:** 1. **`python` not found** — Made `python3` the canonical Python command in `Makefile` and `scripts/… 2. **`pyyaml` missing** — `pip3 install --break-system-packages pyyaml`. Without it `validate-skill… 3. **`pyright` not on PATH** — Changed `pyright` to `npx pyright` in the `lint` target. 4. **`ruff` not on PATH** — Changed `ruff` to `python3 -m ruff` in the `lint` and `format` targets. 5. **`site build` requires Node >=20** — `site/scripts/sync-content.mjs` uses `import.meta.dirname`… **What works now:** - `make validate` — 0 errors, 217 warnings (expected from the pre-existing codebase) - `make test` — 12/12 tests pass - `make lint` — ruff, formatter, pyright pass; prettier on source files passes - `npm run build` in `site/` — 99 pages built successfully via Node 20 - `make site-build` — would need Node 20 in PATH (container default is 18)
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.
- Recovered from all 5 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.
What did not, or is not known
- Took 7 minutes to install, slower than the median of the 21 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 22 ai-agents projects Argusic has installed and timed, claude-skills was the 14th fastest to reach a running state, and 14 of 22 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 7 minutes after the clone.
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/claude-skills)Questions
- Does claude-skills run?
- Yes. claude-skills runs. Argusic installed and launched it on a clean machine in 7 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test claude-skills?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 882ef55e377d. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test claude-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 claude-skills take to install?
- 7 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 claude-skills need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing claude-skills?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does claude-skills compare with the alternatives?
- Of the 22 ai-agents projects Argusic has installed and timed, claude-skills was the 14th fastest to reach a running state, and 14 of 22 reached one at all.
- Where is the evidence for claude-skills?
- 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.