skillsgate
Runssource: GitHubhomepageTypeScriptMITcommit 917098adf251
TypeScript, MIT licensed. The project labels itself: ai, ai tools, skills and skills management.
skillsgate runs. An Argusic agent installed it in 12 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
With a locally installed Node 22.23.3, `npm install`, the web build, and the desktop build succeed; the Electron desktop app launches on the virtual display with IPC handlers initialized and its SQLite database migrated (7 tables, 5 seeded skills), and the web app serves HTTP 200 responses with real HTML in both dev mode and the local Worker production build.
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.
- react-router dev failed: 'React Router Vite plugin not found in Vite config' because CLI resolved node to system Node 183 minutes
- Container had only Node 18.19.1; project requires Node 22+2 minutes
- node build/server/index.js cannot run the built web bundle under plain Node (Worker only)2 minutes
- Desktop `npm run dev` aborted: Electron SUID sandbox helper not configured (container has no setuid chrome-sandbox)1 minute
- Install time
- 12 minutes
- Cold machine to finish
- 12 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- curl -s -o /dev/null -w %{http_code} http://127.0.0.1:8788/ returned 200; Electron launched on DISPLAY=:99, stayed up >30s with '[ipc] registerIpcHandlers initialized' repeated twice, and its live DB inspection via Electron's Node showed 7 tables, schema_version=4, cached_skills rows=5; npm run build (web) and npm run build -w @skillsgate/desktop both exited 0
- Model tokens used
- 389,395
- Exact commit tested
- 917098adf251
- 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.
- Environment gap: container ships only Node 18.19.1 but the monorepo requires Node 22+; downloaded… - `npm install` succeeded (591 packages, only deprecation/audit warnings; audit = upstream deps, no… - Both workspaces build: `npm run build -w @skillsgate/desktop` exit 0, `npm run build` (web) exit … **Launch / runtime verification** - Desktop: `electron . --no-sandbox` on `DISPLAY=:99` ran the main process for a full 30s timeout, … - Web: `react-router dev` / `vite --config vite.config.ts` served the app; root HTTP 200 with real … - No test suites exist in the repo (no `test` scripts, no test/spec files), so `launch_succeeded` r… **Errors recorded** 1. Node 18 → Node 22 requirement (installed local Node 22, fixed). 2. `react-router dev` reported "React Router Vite plugin not found in Vite config" — caused by the … 3. Desktop `npm run dev` aborted on the Electron SUID sandbox (container has no setuid chrome-sandb… 4. `node build/server/index.js` fails on Node (bundle is Worker-targeted) — expected deployment mod…
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 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 MIT, as reported by its host.
What did not, or is not known
- Took 12 minutes to install, slower than the median of the 110 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 111 ai projects Argusic has installed and timed, skillsgate was the 81st fastest to reach a running state, and 77 of 111 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.
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/skillsgate)Questions
- Does skillsgate run?
- Yes. skillsgate runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test skillsgate?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 917098adf251. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test skillsgate?
- The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does skillsgate take to install?
- 12 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 skillsgate need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing skillsgate?
- 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.
- How does skillsgate compare with the alternatives?
- Of the 111 ai projects Argusic has installed and timed, skillsgate was the 81st fastest to reach a running state, and 77 of 111 reached one at all.
- Where is the evidence for skillsgate?
- 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.