roboflow-product-navigation
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.
74
91%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted description that clearly communicates both what the skill does and when to use it. It includes specific trigger terms (upload, annotate, train, deploy) and a clear domain (app.roboflow.com navigation). The only minor weakness is that the capability description could be slightly more specific about the range of features or pages covered.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Roboflow web app navigation) and some actions (upload, annotate, train, deploy, mapping to URLs), but doesn't list comprehensive specific capabilities beyond these examples. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (explaining where Roboflow features live, mapping intents to specific page URLs) and 'when' (starts with 'Use when explaining where Roboflow features live' and specifies trigger intents like upload, annotate, train, deploy). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'upload', 'annotate', 'train', 'deploy', 'app.roboflow.com', 'page URLs', and 'Roboflow features'. These cover the main intents a user would express when looking for navigation help. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — it's specifically about navigating the app.roboflow.com web UI and mapping user intents to page URLs. This is unlikely to conflict with other skills due to the very specific domain (Roboflow app navigation). | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality reference skill that efficiently maps Roboflow web app intents to URL patterns. The table-based format is ideal for this type of lookup content — concise, scannable, and immediately actionable. The content is well-organized with a clear hierarchy, though the sheer volume of entries could arguably be split across files for better progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely lean and well-structured as a reference table. No unnecessary explanations of what Roboflow is or how web apps work. Every line maps directly to a URL pattern and its purpose. The only slight overhead is the agent-sourcing note at the top, but that serves a functional purpose. | 3 / 3 |
Actionability | Every entry provides a concrete URL pattern and a brief description of what's found there. Claude can directly construct URLs by substituting workspace/project/version slugs. The tables serve as a complete, copy-paste-ready lookup for navigation tasks. | 3 / 3 |
Workflow Clarity | This is a reference/lookup skill rather than a multi-step workflow skill. The URL hierarchy is clearly presented (Workspace → Project → Version → Model), and the tables are logically sequenced from broad (workspace) to specific (version). For a navigation reference, this level of clarity is sufficient and appropriate. | 3 / 3 |
Progressive Disclosure | The skill references one related page (`roboflow://skills/product-navigation/features-by-page`) which is good, but the content itself is quite long (~150 lines of tables) and could benefit from splitting detailed sections (e.g., workspace settings, version-level pages) into separate reference files. However, for a flat lookup table, keeping it in one file is defensible. | 2 / 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.