Tessl • The management layer for AI agent skills

The body is an exemplary lean, fully executable reference: copy-paste curl commands with expected outputs, clear scope-based request selection, and good platform-specific notes. The only notable gap is the Open-Meteo fallback's geocoding step, which names the action but gives no command or URL for finding coordinates.

Suggestions

Add the executable geocoding step for the Open-Meteo fallback, e.g. the geocoding API URL (https://geocoding-api.open-meteo.com/v1/search?name=London) with a one-line example, so the fallback path is fully copy-paste ready.

Optionally add an expected-output snippet for the Open-Meteo JSON response (as done for wttr.in) so the fallback's result shape is visible at a glance.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: every section is actionable (curl commands, format codes, platform notes, tips) with no explanation of concepts Claude already knows and no padding. "Two free services, no API keys needed" and "Free, no key, good for programmatic use" are brief, decision-relevant context, not filler — fits the score-5 anchor.	5 / 5
Actionability	The wttr.in commands are copy-paste ready with example outputs ("curl -s \"https://wttr.in/London?format=3\" # Output: London: ⛅️ +8°C") and cover the common cases, but the Open-Meteo fallback's step "Find coordinates for a city, then query" provides no executable command or URL for geocoding — a minor gap matching the score-4 anchor. Not 5 because of that missing step; not 3 because all provided code is fully executable rather than pseudocode.	4 / 5
Workflow Clarity	This is a simple, single-purpose skill and the single action is unambiguous: the scope-based decision guidance ("Choose one request that matches the user's scope. Do not fetch current conditions separately when a today or forecast request already includes them.") clearly routes current-only vs. today vs. full forecast vs. JSON fallback. No destructive or batch operations, so no validation requirement applies — score 5 under the simple-skill rule.	5 / 5
Progressive Disclosure	The body is a compact (~60-line), well-organized single-page skill with clear sections (primary service, fallback service, tips) and no content that belongs in separate bundle files — no bundle files exist and none are needed. Everything inline earns its place, and the external docs link (https://open-meteo.com/en/docs) is clearly signaled, fitting the score-5 anchor for a simple skill with well-organized sections.	5 / 5
	Total	19 / 20 Passed

Description

65%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 concise and concrete about what the skill does, with a distinct weather niche, but it omits any "when to use" trigger guidance and lacks common trigger synonyms such as temperature or rain. Adding an explicit "Use when..." clause would resolve its main weakness.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks about current weather, a forecast, or temperature for a city or location."

Include natural trigger synonyms such as "temperature", "rain", or "humidity" so the description matches more of the phrasings users actually say.

Optionally note the no-API-key/free nature or location support (city names, airport codes) to round out capability coverage.

Dimension	Reasoning	Score
Specificity	"Get current weather and forecasts" names the domain plus two concrete actions (get current conditions, get forecasts), but does not comprehensively cover capabilities (locations, units, JSON output), matching the score-3 anchor. It is not 4 because it does not list several specific actions with only minor gaps, and not 2 because the actions named are concrete rather than generic.	3 / 5
Completeness	The description has a clear "what" ("Get current weather and forecasts") but no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the "what" is concrete and specific, not vague.	3 / 5
Trigger Term Quality	"weather", "current weather", and "forecasts" are natural phrases users would say, giving good keyword coverage matching the score-4 anchor. Not 5 because common natural synonyms such as "temperature", "rain", or "humidity" are missing.	4 / 5
Distinctiveness Conflict Risk	"current weather" and "forecasts" occupy a clear, narrow niche with distinct trigger terms; there is minimal risk of this description firing for an unrelated skill. Fits the score-5 anchor ("clear niche with distinct triggers; minimal conflict risk").	5 / 5
	Total	15 / 20 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: HKUDS/nanobot
Path: nanobot/skills/weather/SKILL.md
Revision: 9adbcc2

Reviewed: 3 days ago

Discovery Implementation Validation

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.

weather

Table of Contents

Is this your skill?