roboflow-api-reference
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.
78
71%
Does it follow best practices?
Impact
84%
1.15xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/api-reference/SKILL.mdEvaluation results
55%
10%Quality Control Defect Detector
Inference SDK usage and bounding box corner extraction
Uses inference-sdk
0%
0%
Uses InferenceHTTPClient
0%
0%
Correct api_url
0%
50%
api_key passed to client
0%
0%
model_id format
50%
100%
Confidence param used
100%
100%
Correct x1/y1 computation
100%
100%
Correct x2/y2 computation
100%
100%
98%
17%Traffic Camera Dataset: Project Setup and Training Pipeline
Project creation, bulk upload, version generation, and training kickoff
Uses roboflow SDK
100%
83%
Valid project type
100%
100%
Required project fields
100%
100%
Valid split values
100%
100%
Camera metadata attached
75%
100%
Duplicate handling
100%
100%
Version generation with preprocessing
50%
100%
Training status via version GET
21%
100%
Metrics location noted
92%
100%
100%
7%Annotated Safety Inspection Report Generator
Roboflow Workflow invocation with correct request format
Workflow endpoint used
65%
100%
POST with JSON body
100%
100%
api_key in JSON body
100%
100%
Inputs object structure
100%
100%
No format=image param
100%
100%
No basic inference endpoint for visualization
100%
100%
- Repository
- roboflow/computer-vision-skills
- Commit
02936d5
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.