Install payload
Install payload is mixed and needs spot-checking.
67% (4/6)
1 trusted · 4 review · 1 limited in this set — compare to see which signals differ.
6 results in this view
3 trust signals differ in this sample: Package trust, Source provenance, Submitter
Signals differ on Package trust, Source provenance, Submitter — add entries to compare before you install.
Rollout signal scan
Biggest gaps: metadata review, package integrity. 0 entries have 2+ required gaps.
Install payload
Install payload is mixed and needs spot-checking.
67% (4/6)
Most at-risk entries in this view
Adoption queue
4/6 visible results are in hold tier and need mitigation before adoption.
1 blockers: Metadata review
70/100
Request metadata review from maintainers or internal owners.
mcp/hugging-face-mcp-server · trust trusted · confidence 83%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
skills/huggingface-skills · trust review · confidence 67%
1 blockers: Metadata review
42/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
agents/full-stack-ai-development-agent · trust limited · confidence 67%
2 blockers: Metadata review, Install payload
36/100
Request metadata review from maintainers or internal owners.
Add install/config payload for reproducible team rollout.
Collect package checksum or signed artifact information.
tools/gradio · trust review · confidence 50%
2 blockers: Metadata review, Install payload
36/100
Request metadata review from maintainers or internal owners.
Add install/config payload for reproducible team rollout.
Collect package checksum or signed artifact information.
tools/ray · trust review · confidence 50%
2 blockers: Metadata review, Safety notes
24/100
Request metadata review from maintainers or internal owners.
Capture safety notes with misuse/guardrail guidance.
Document privacy posture and data handling expectations.
rules/python-data-science-expert · trust review · confidence 33%
Decision confidence
3/6 results are low-confidence and need review before adoption.
Confident candidate for staged adoption.
74/100
mcp/hugging-face-mcp-server · trust trusted
Address Metadata review, Package integrity before broader rollout.
54/100
skills/huggingface-skills · trust review
Address Metadata review, Package integrity before broader rollout.
48/100
agents/full-stack-ai-development-agent · trust limited
Hold adoption until Metadata review, Package integrity are resolved.
36/100
tools/gradio · trust review
Hold adoption until Metadata review, Package integrity are resolved.
36/100
tools/ray · trust review
Hold adoption until Metadata review, Safety notes are resolved.
28/100
rules/python-data-science-expert · trust review
Freshness distribution
Median age 170 days; 3 fresh of 6 scanned. Re-verify the oldest entries.
Theme distribution
83% of this view shares the top theme. Leading themes: machine-learning, ai, datasets.
26 distinct themes across 6 scanned
Apache-2.0 Python framework for building and sharing machine-learning demos, AI web apps, model interfaces, chatbots, API front ends, and interactive evaluation tools.
Access Hugging Face Hub and Gradio AI applications
Official Hugging Face Agent Skills collection for Claude Code, Codex, Cursor, Gemini CLI, and other skills-compatible agents, covering Hub CLI workflows, datasets, model search, Spaces, Gradio, fine-tuning, evaluations, local models, papers, Trackio, ZeroGPU, transformers.js, TRL, and the Hugging Face MCP server.
Apache-2.0 distributed AI compute engine for scaling Python, ML data processing, training, tuning, reinforcement learning, and model serving workloads.
Full-stack AI development specialist bridging frontend, backend, and AI/ML with AI-assisted coding workflows, intelligent code generation, and end-to-end type safety
scikit-learn ML modeling rule that audits for data leakage, enforces Pipeline-based preprocessing, and validates cross-validation rigor (StratifiedKFold, GroupKFold, TimeSeriesSplit) for defensible model evaluation