CtrlK
BlogDocsLog inGet started
Tessl Logo

weather

Check current weather, rain, temperature, and short forecasts for a city, region, airport code, or coordinates using a live public endpoint.

68

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 an exemplary lean skill: executable commands, exact response-field mappings, an availability fallback, and security cautions (URL-encoding untrusted input, treating fetched content as untrusted) with zero padding. Nothing material is missing for a single-purpose live-data skill.

DimensionReasoningScore

Conciseness

The ~30-line body contains no concept explanations Claude already knows — it goes straight to executable commands, exact JSON field paths, a compact-format one-liner, and short operational cautions. Every token earns its place; nothing could be trimmed without losing function, so the lean 5 anchor fits and the 4 anchor's "minor over-explanation" is absent.

5 / 5

Actionability

Fully executable copy-paste curl commands with sensible flags (--fail --silent --show-error --max-time 20), exact response fields (current_condition[0].temp_C, precipMM, etc.), a compact-format variant, and a concrete fallback endpoint (wttr.is). Not a 4 because there are no gaps: both JSON and pre-formatted output paths are covered for the common cases.

5 / 5

Workflow Clarity

This is a simple single-purpose skill (fetch and report weather) where the action is unambiguous, which the scoring notes allow to score 5; it even includes an error-recovery checkpoint ("If wttr.in is unavailable, retry the same path at https://wttr.is/") and prompt-injection/untrusted-input handling. No destructive or batch operations exist, so the validation cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and the skill is under 50 lines with no need for external references, so per the scoring notes well-organized sections alone warrant a 5. Sections (intro/trigger guidance, Fetch, JSON fields, compact format, cautions) are clearly headed and nothing that belongs in a separate file is inlined.

5 / 5

Total

20

/

20

Passed

Description

70%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.

A concrete, third-person, well-scoped description with good natural trigger terms and minimal conflict risk, weakened only by the absence of an explicit 'Use when...' clause. Adding one sentence of trigger guidance would lift it to top-tier quality.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user asks about weather, rain, temperature, or forecasts for a location, or mentions needing live/updated conditions.'

Include a few more natural synonyms in the description (e.g., wind, humidity, 'will it rain', 'how hot/cold') to round out trigger-term coverage.

Consider naming the data source (wttr.in) in the description so users and Claude can distinguish it from other data-lookup skills.

DimensionReasoningScore

Specificity

"Check current weather, rain, temperature, and short forecasts for a city, region, airport code, or coordinates" names several concrete data points and explicit input forms, but all hang off the single verb "Check", so coverage is several-actions-with-minor-gaps rather than the multiple distinct verbs of the 5 anchor. Not a 3 because far more than 1-2 concrete capabilities are named.

4 / 5

Completeness

The 'what' is clear (check weather, rain, temperature, short forecasts), but there is no 'Use when...' clause or equivalent explicit trigger guidance — the 'when' is only weakly implied by the topic. Per the judging guidelines this caps completeness at 3; a 4 would require at least an implicit-but-stated usage trigger.

3 / 5

Trigger Term Quality

Natural phrases users would say — "current weather", "rain", "temperature", "short forecasts" — are present, matching the good-coverage anchor. Not a 5 because common synonyms and variations (e.g., "wind", "humidity", "will it rain", "hot/cold") are absent; not a 3 because the core natural vocabulary is well covered rather than partially missing.

4 / 5

Distinctiveness Conflict Risk

"Current weather... forecasts for a city, region, airport code, or coordinates using a live public endpoint" carves out a clear niche with distinct trigger vocabulary that would not naturally invoke any other skill. The 4 anchor's "minor overlap risk with closely related skills" does not apply here.

5 / 5

Total

16

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
EKKOLearnAI/hermes-studio
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.