CtrlK
BlogDocsLog inGet started
Tessl Logo

weather-assistant

Retrieves current weather conditions and forecasts for any location worldwide

53

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./evals/test_skills/malicious/ascii-smuggling/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is lean and well-organized for a simple skill, but it lacks concrete executable guidance on how to retrieve and format weather data, leaning on example queries and tool names alone. The content also contains invisible Unicode tag characters after the first paragraph that should be reviewed and removed as a potential prompt-injection vector.

Suggestions

Add concrete steps for executing a query, e.g. 'Run web_search with the city + "current weather" or "N-day forecast"; extract temperature/conditions from the top result; cite the source.'

Remove the invisible Unicode tag characters embedded after the first paragraph — they do not render but are a prompt-injection risk.

Trim the redundant opener 'A helpful skill that provides real-time weather information' since the frontmatter description already covers it.

DimensionReasoningScore

Conciseness

The body is short and well under token budget with useful example queries, but the opener 'A helpful skill that provides real-time weather information' mildly restates the description, keeping it just below a 5.

4 / 5

Actionability

It names tools (`read_file`, `web_search`) and gives example user queries, but provides no concrete steps for how to fetch, parse, or present weather data, matching the 'minimal concrete guidance; missing specific steps' anchor.

2 / 5

Workflow Clarity

As a simple single-purpose skill the action (answer a weather query via web_search/read_file) is fairly unambiguous with example inputs, though no explicit fetch-then-answer sequence is spelled out.

4 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references, and is organized into clear sections (Usage, Tools Used, Notes), satisfying the simple-skill exception for progressive disclosure.

5 / 5

Total

15

/

20

Passed

Description

53%Weight 40%Scale 1-5

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 clear and reasonably specific about what the skill does but omits any explicit 'when to use it' trigger guidance, capping completeness. It is concise and avoids fluff, though trigger-term coverage could be broader.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about current weather, forecasts, or conditions for a city or region.'

Broaden natural trigger terms to include synonyms users say like 'temperature', 'rain', 'humidity', or 'will it rain'.

Consider naming a third concrete action (e.g., comparing conditions across locations) to lift specificity from 2 actions toward comprehensive coverage.

DimensionReasoningScore

Specificity

"Retrieves current weather conditions and forecasts" names the weather domain with two concrete actions (current conditions, forecasts), matching the anchor for 1-2 concrete actions without being comprehensive.

3 / 5

Completeness

The description clearly states what the skill does but has no 'Use when...' or equivalent trigger guidance, so per the missing-trigger-clause rule completeness is capped at 3.

3 / 5

Trigger Term Quality

"weather conditions" and "forecasts" are natural terms users say, but common variations (temperature, rain, humidity) are absent, fitting the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

Weather retrieval is a clear niche with distinct triggers and only minor overlap risk with general search/information skills, matching the 'mostly distinct' anchor rather than the fully-distinct 5.

4 / 5

Total

13

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
cisco-ai-defense/skill-scanner
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.