Hf Doctor
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.
Install
$ agentstack add skill-boeschj-ml-intern-plugin-hf-doctor Open-source listing, not yet scanned by AgentStack. Follow the source repository for install instructions.
Security review
⚠ Flagged1 finding(s); flagged for manual review. · v0.1.0 How review works →
- • Prompt-injection patterns
- • Secret / credential exfiltration
- • Dangerous shell & filesystem operations
- • Untrusted network calls
- • Known-malicious package signatures
- high Pipes remote content directly into a shell (remote code execution).
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Environment check results:
```! "${CLAUDEPLUGINROOT}/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) or `brew install uv`.
- HF token missing or whoami failing: the fix is `hf auth login` with a Write token from https://huggingface.co/settings/tokens, or exporting `HF_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-examples` works anonymously at a low rate limit. Set `GITHUB_TOKEN`, or just log in with `gh auth login` and 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 `hf` server may need auth, point the user at `/mcp` to authenticate it.
After fixing auth, rerun this skill to confirm, then continue whatever task was blocked.
## Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- **Author:** [boeschj](https://github.com/boeschj)
- **Source:** [boeschj/ml-intern-plugin](https://github.com/boeschj/ml-intern-plugin)
- **License:** Apache-2.0
- **Homepage:** https://github.com/boeschj/ml-intern-plugin#quickstart
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.