ground-zeroshot Skill
Ground CXR findings using MI2 zero-shot classification. Returns per-finding probabilities bucketed into positive/possible for the agent to use when writing the report. Published by microsoft in healthcareai-examples.
What is ground-zeroshot Skill?
Ground CXR findings using MI2 zero-shot classification. Returns per-finding probabilities bucketed into positive/possible for the agent to use when writing the report. Published by microsoft in healthcareai-examples. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Design and media
- Writing
- Design and media use cases
- Writing use cases
Technical details
- Install or run with Copy skill directory
When to use ground-zeroshot Skill
- Use it for design and media.
- Use it for writing.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/healthcareai-examples
- Skill file: agentic/medimageinsight/skills/ground-zeroshot/SKILL.md
What it does
Ground CXR findings using MI2 zero-shot classification. Returns per-finding probabilities bucketed into positive/possible for the agent to use when writing the report.
Skill instructions
ground-zeroshot Calls the MI2 zero-shot classifier and returns bucketed per-finding probabilities. Does not write a report — the agent produces the report using the write-report skill after grounding. Budget - Tool calls: 1 — exactly one mcpmedimageinsigzeroshotclassify call per image. - Do not retry on success. How to use 1. Resolve the image. If imagepath is an http(s) URL, pass it through to the tool unchanged — do NOT download it, curl it, or turn it into a local file; the MCP server fetches URLs itself. Otherwise it is a local path: the MCP tool runs in a different working directory, so if it is not absolute, resolve it via realpath; if it can't be resolved, ask the user. 2. Assemble the label list. Read the canonical label list from below and use those strings verbatim. Append any caller-provided extralabels. 3. Call the classifier. Call mcpmedimageinsigzeroshotclassify with filepath = absolute path and labels = assembled list. One call per image. 4. Bucket the scores. Use these
Explore related resources
Frequently asked questions
What is ground-zeroshot?
ground-zeroshot is a open-source AI agent skill with Copy skill directory. Ground CXR findings using MI2 zero-shot classification. Returns per-finding probabilities bucketed into positive/possible for the agent to use when writing the report.
Who is ground-zeroshot best for?
ground-zeroshot is best for reusing agent instructions, scripts, and references, design and media workflows, writing workflows.
How do I install ground-zeroshot?
Install or run ground-zeroshot using Copy skill directory. Check ground-zeroshot for the latest setup command.
Is ground-zeroshot actively maintained?
ground-zeroshot may need a closer maintenance check before production use.
Auto-fetched from GitHub.
