hf-doctor
Skill0 starsChanged 4 months agoApache-2.0View on GitHub
Diagnose the ML Intern environment, Hugging Face auth, uv, tokens, job pricing catalog, and data directory. Use at setup, when any HF call returns an auth error, or when jobs and sandboxes fail unexpectedly.
- Pipes a download into a shell
- Reads credentials
- Installs packages
In this repository5 other files it gives its agents.
- dataset-auditSkill
- hf-jobsSkill
- ml-autopilotSkill
- ml-internSkill
- trackioSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Every check ok: say so in one line and move on with the pending task.
- Distinctive: line 23
After fixing auth, rerun this skill to confirm, then continue whatever task was blocked.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Environment check results:
"${CLAUDE_PLUGIN_ROOT}/bin/hf-doctor" 2>&1 || echo '{"check": "doctor", "ok": false, "detail": "hf-doctor failed to run, is uv installed?"}'Interpret the results above for the user, shortest useful form:
- Every check ok: say so in one line and move on with the pending task.
- uv missing: it is the runtime for every plugin tool. Install:
curl -LsSf https://astral.sh/uv/install.sh | sh(macOS/Linux) orbrew install uv. - HF token missing or whoami failing: the fix is
hf auth loginwith a Write token from https://huggingface.co/settings/tokens, or exportingHF_TOKEN. Jobs, sandboxes, uploads, and access-restricted datasets all need write access. GPU jobs also need a positive credit balance in HF billing, which is separate from the token. - GITHUB_TOKEN missing: warn only;
hf-gh-examplesworks anonymously at a low rate limit. SetGITHUB_TOKEN, or just log in withgh auth loginand the tools reuse that token automatically. - Hardware catalog unreachable: cost estimates fall back to the static table; job submission still works.
- trackio unknown: informational; jobs install it as a dependency at run time.
- pyright_lsp absent: informational; the bundled Python language server config stays dormant until
npm install -g pyright, which turns on live diagnostics for training scripts. - MCP tools missing: the bundled
hfserver may need auth, point the user at/mcpto authenticate it.
After fixing auth, rerun this skill to confirm, then continue whatever task was blocked.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

