generated: '2026-08-02'
method: searched
source: https://github.com/roboflow/computer-vision-skills
notes: These are Roboflow FIRST-PARTY Agent Skills, saved verbatim from the provider's own public repo — not generated by
  this pipeline. Roboflow ships them as a Claude/Codex/Cursor plugin (npx @roboflow/skills install) alongside the hosted MCP
  server, and also serves them as MCP resources at roboflow://skills/<name>/. Each SKILL.md is reproduced unmodified; supporting
  reference pages that sit beside them in the upstream repo are not mirrored here.
license: Apache-2.0
repo_stars_at_harvest: 29
install:
  npm: npx @roboflow/skills install
  cursor: https://cursor.com/marketplace/roboflow
  plugin: https://github.com/roboflow/computer-vision-skills/blob/main/.claude-plugin/plugin.json
mcp_server: mcp/roboflow-mcp.yml
skill_count: 9
skills:
- file: roboflow-api-reference.md
  name: roboflow-api-reference
  description: Protocol-level facts for Roboflow REST and Inference APIs — URL patterns, auth, parameters, error codes, and
    SDK quick-start. For deployment strategy and Workflow execution patterns, see roboflow-inference.
  upstream: https://github.com/roboflow/computer-vision-skills/blob/main/skills/api-reference/SKILL.md
  mcp_resource: roboflow://skills/api-reference/SKILL.md
- file: roboflow-cloud-storage.md
  name: roboflow-cloud-storage
  description: Use when connecting cloud storage (AWS S3 / S3-compatible or Google Cloud Storage) to Roboflow to mirror images
    into a workspace — creating storage credentials, defining datasources (bucket-mirror configs), selecting objects with
    glob rules, validating access, and running/scheduling mirror jobs.
  upstream: https://github.com/roboflow/computer-vision-skills/blob/main/skills/cloud-storage/SKILL.md
  mcp_resource: roboflow://skills/cloud-storage/SKILL.md
- file: roboflow-custom-weights-upload.md
  name: roboflow-custom-weights-upload
  description: Use when uploading locally trained model weights (YOLO, RF-DETR, YOLO-NAS, PaliGemma, Florence-2) to Roboflow
    — the client-side Python SDK upload flow, safe API key handling, per-family packaging requirements, and verifying the
    upload.
  upstream: https://github.com/roboflow/computer-vision-skills/blob/main/skills/custom-weights-upload/SKILL.md
  mcp_resource: roboflow://skills/custom-weights-upload/SKILL.md
- file: roboflow-data-management.md
  name: roboflow-data-management
  description: Use when uploading images, labeling, organizing datasets, creating Roboflow projects (detection/segmentation/keypoint/classification),
    tags, splits, versions, or RoboQL search.
  upstream: https://github.com/roboflow/computer-vision-skills/blob/main/skills/data-management/SKILL.md
  mcp_resource: roboflow://skills/data-management/SKILL.md
- file: roboflow-inference.md
  name: roboflow-inference
  description: Deployment option comparison (serverless, dedicated, self-hosted, batch) and Workflow execution patterns. For
    raw API URL patterns, auth, and request/response formats, see roboflow-api-reference.
  upstream: https://github.com/roboflow/computer-vision-skills/blob/main/skills/inference/SKILL.md
  mcp_resource: roboflow://skills/inference/SKILL.md
- file: roboflow-plans-and-pricing.md
  name: roboflow-plans-and-pricing
  description: Use when answering questions about Roboflow plans, credit usage, or cost estimation; directs users to roboflow.com/pricing
    for current dollar amounts.
  upstream: https://github.com/roboflow/computer-vision-skills/blob/main/skills/plans-and-pricing/SKILL.md
  mcp_resource: roboflow://skills/plans-and-pricing/SKILL.md
- file: roboflow-product-navigation.md
  name: roboflow-product-navigation
  description: Use when explaining where Roboflow features live in the app.roboflow.com web app, mapping intents like upload,
    annotate, train, deploy to specific page URLs.
  upstream: https://github.com/roboflow/computer-vision-skills/blob/main/skills/product-navigation/SKILL.md
  mcp_resource: roboflow://skills/product-navigation/SKILL.md
- file: roboflow-training-and-evaluation.md
  name: roboflow-training-and-evaluation
  description: Use when training Roboflow models, improving accuracy, or setting up a production feedback loop — covers architecture
    selection, model IDs, checkpoints, evaluation metrics, the iterative improvement playbook, and Active Learning through
    the Project Model Workflow block.
  upstream: https://github.com/roboflow/computer-vision-skills/blob/main/skills/training-and-evaluation/SKILL.md
  mcp_resource: roboflow://skills/training-and-evaluation/SKILL.md
- file: roboflow-universe.md
  name: roboflow-universe
  description: Use when searching for or using public datasets/models on Roboflow Universe (universe.roboflow.com), the open
    repository of 1M+ computer vision datasets and 50K+ pre-trained models.
  upstream: https://github.com/roboflow/computer-vision-skills/blob/main/skills/universe/SKILL.md
  mcp_resource: roboflow://skills/universe/SKILL.md