jamesmoss/random-lunch
Orders a random lunch for me from Feedr.co.
54
54%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
40%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 identifies a very specific niche (ordering random lunch from Feedr.co), which makes it distinctive, but it is poorly constructed overall. It uses first person ('for me') which is inappropriate, lacks a 'Use when...' clause, and provides minimal detail about what the skill actually does or its capabilities. The grammar error ('Order's' instead of 'Orders') also reduces professionalism.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to order lunch, get food from Feedr, or wants a random meal suggestion.'
Expand the description of capabilities, e.g., 'Places a randomized lunch order from Feedr.co, selecting from available restaurants and menu items.'
Rewrite in third person voice and fix grammar: change 'Order's a random lunch for me' to 'Orders a random lunch from Feedr.co' and include additional trigger terms like 'food', 'meal', 'Feedr'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names a specific domain (ordering lunch) and a specific platform (Feedr.co), but describes only one action ('orders a random lunch') without detailing concrete steps or capabilities. | 2 / 3 |
Completeness | It describes what it does (orders a random lunch from Feedr.co) but has no explicit 'Use when...' clause or trigger guidance, and the 'what' is minimal. Per rubric, missing 'Use when' caps completeness at 2, and the weak 'what' brings it to 1. | 1 / 3 |
Trigger Term Quality | Includes natural keywords like 'lunch' and 'Feedr.co' that users might say, but misses common variations like 'food order', 'meal', 'catering', or 'random meal'. Coverage is limited. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'random lunch' and 'Feedr.co' is highly specific and unlikely to conflict with other skills. It occupies a very clear niche. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
44%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is admirably concise and has a clear personality, but it lacks the actionable detail needed for reliable execution. There are no concrete steps for navigating the Feedr UI, no handling of authentication or error states, and no validation checkpoints for a process that involves spending real money.
Suggestions
Add concrete step-by-step workflow for navigating Feedr: how to identify unordered days, how to select dishes, and how to confirm the order.
Include validation checkpoints such as verifying the order total before submission and confirming the order was successfully placed.
Add guidance on handling common failure modes: authentication prompts, sold-out items, days with no available options, or budget constraints that can't be met.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is brief and every sentence conveys a unique instruction or constraint. No unnecessary explanation of what Feedr is or how Chrome plugins work. | 3 / 3 |
Actionability | The instructions are entirely vague and high-level with no concrete steps, selectors, commands, or examples of how to interact with the Feedr website. There's no guidance on how to navigate the UI, click elements, or handle authentication. | 1 / 3 |
Workflow Clarity | This is a multi-step process (visit site, find unordered days, select dishes, check budget, optionally add extras, submit order) but the steps are not sequenced, there are no validation checkpoints, and no error handling for common issues like authentication failures or sold-out items. | 1 / 3 |
Progressive Disclosure | This is a very short, simple skill under 50 lines with no need for external references. The content is well-organized in a few clear paragraphs covering the task, constraints, and preferences. | 3 / 3 |
Total | 8 / 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.
Reviewed
Table of Contents