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.mdQuality
Discovery
57%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description effectively identifies its domain and distinguishes itself from a related skill, but lacks explicit trigger guidance ('Use when...') and concrete actions Claude would perform. It reads more like a reference document summary than an actionable skill description, and could benefit from natural user-facing trigger terms and a clear 'when to use' clause.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Roboflow API endpoints, authentication setup, SDK installation, or troubleshooting API error codes.'
Include natural trigger terms users would say, such as 'API key', 'upload image', 'model prediction', 'Roboflow Python SDK', or 'API request'.
Reframe the description to include concrete actions, e.g., 'Provides URL patterns, authentication details, request parameters, and error code references for Roboflow REST and Inference APIs. Helps set up SDK quick-starts.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Roboflow REST and Inference APIs) and lists several categories of information (URL patterns, auth, parameters, error codes, SDK quick-start), but these describe reference content categories rather than concrete actions Claude would perform. | 2 / 3 |
Completeness | The 'what' is reasonably covered (protocol-level facts for Roboflow APIs), but there is no explicit 'Use when...' clause. The cross-reference to 'roboflow-inference' provides some implicit boundary guidance but doesn't constitute an explicit trigger statement. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Roboflow', 'REST', 'Inference APIs', 'auth', 'SDK', 'error codes', and 'URL patterns' which users might mention. However, it misses common natural variations like 'API key', 'upload image', 'predict', 'detect objects', or 'Roboflow API call' that users would naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | The description clearly carves out a niche (protocol-level API reference for Roboflow) and explicitly distinguishes itself from a sibling skill ('roboflow-inference' for deployment strategy and Workflow execution), making it unlikely to conflict with other skills. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured API reference overview that provides concrete, actionable quick-start code and clear routing tables for different use cases. Its main weakness is some verbosity in the meta-notes at the top and minor redundancy between tables. The progressive disclosure to detailed sub-pages is well-executed.
Suggestions
Trim or remove the two-paragraph meta-note at the top about plugin vs MCP resource precedence — this is operational context that could be a single sentence or moved to a separate meta file.
Consider consolidating the 'API Hosts' table and 'Host Selection Guide' table to reduce redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with well-structured tables, but includes some unnecessary verbosity: the two-paragraph meta-note at the top about plugin vs MCP resources is lengthy, and some explanations (like 'It handles auth, retries, and response parsing') add marginal value for Claude. The host selection guide partially duplicates the API hosts table. | 2 / 3 |
Actionability | Provides fully executable, copy-paste-ready Python code for both inference-sdk and roboflow SDK quick starts. Authentication methods, install commands, and host URLs are all concrete and specific. The host selection guide gives clear, actionable routing decisions. | 3 / 3 |
Workflow Clarity | This is primarily a reference/lookup skill rather than a multi-step workflow skill. The host selection guide provides clear decision logic for choosing the right endpoint. For a reference-style skill, the single-action patterns are unambiguous and well-sequenced (install → configure client → call). | 3 / 3 |
Progressive Disclosure | The skill serves as a clear overview with well-signaled one-level-deep references to detailed pages (inference patterns and REST API endpoints via roboflow://skills/api-reference/inference and rest-api). Content is appropriately split — overview and quick-start here, detailed endpoint docs elsewhere. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- roboflow/computer-vision-skills
- Commit
02936d5
- Reviewed
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.