Answer weather queries with a fixed demo response.
67
58%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./examples/evaluation/claudecode/.claude/skills/weather-query/SKILL.mdQuality
Discovery
32%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 is brief and identifies the domain (weather) and a basic action (answering with a demo response), but it lacks explicit trigger guidance ('Use when...'), natural keyword variations, and multiple concrete actions. It would benefit from more specificity about when to invoke the skill and what kinds of weather queries it handles.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about weather, forecasts, temperature, or current conditions.'
Include natural trigger term variations such as 'forecast', 'temperature', 'weather report', 'current weather', '.weather'.
Clarify the scope more concretely, e.g., 'Returns a hardcoded demo weather response for testing purposes. Does not call real APIs.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain ('weather queries') and a single action ('answer... with a fixed demo response'), but does not list multiple concrete actions or elaborate on capabilities. | 2 / 3 |
Completeness | It describes what the skill does but lacks any explicit 'Use when...' clause or trigger guidance, and per the rubric a missing 'Use when' clause caps completeness at 2. Additionally, the 'what' is minimal, so this falls to a 1. | 1 / 3 |
Trigger Term Quality | Includes 'weather queries' which is a natural keyword, but misses common variations like 'forecast', 'temperature', 'weather report', 'current weather', etc. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'fixed demo response' adds some distinctiveness from a real weather skill, but 'weather queries' alone could overlap with any weather-related skill. | 2 / 3 |
Total | 7 / 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 an extremely minimal demo skill that serves its narrow purpose (returning fixed weather data) with maximum conciseness. Its main weakness is the limited actionability — it only covers one city with no guidance on how to handle other weather queries or edge cases. For a demo/placeholder skill, it's adequate but not particularly instructive.
Suggestions
Add brief guidance on how to respond when asked about weather for cities other than Shenzhen (e.g., 'For any other city, state that only Shenzhen demo data is available').
Include a brief example of expected input/output to make the skill more actionable (e.g., 'User: What's the weather in Shenzhen? → Response: The weather in Shenzhen is sunny, 25°C.').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean — only 3 short sentences with the fixed data. No unnecessary explanation or padding. Every token serves a purpose. | 3 / 3 |
Actionability | The instruction is concrete (use fixed demo data, don't mention the skill), but it's limited to a single hardcoded response for one city. There's no guidance on handling other cities, edge cases, or how to format the response. | 2 / 3 |
Workflow Clarity | This is a simple, single-purpose skill with an unambiguous action: return fixed demo data when asked about weather. No multi-step process or destructive operations are involved, so the single clear instruction suffices. | 3 / 3 |
Progressive Disclosure | For a skill this simple (under 10 lines, single task), no external references or additional files are needed. The content is well-organized and self-contained. | 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.
0c1ec2b
Table of Contents
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.