Automated summary
Usage guide for a weather plugin that tells the assistant which of 12 tools to pick for conditions, forecasts, alerts, radar and model imagery, and meteorological calculations.
Strengths
- Explicit intent-to-tool mapping table for common weather questions
- Batching rule that combines multiple model variables into a single image call
- Geographic zoom guidance with concrete lat/lon and radius examples instead of defaulting to full-CONUS maps
- Notes that wx_brief already bundles conditions, forecast and alerts, preventing redundant calls
Limitations
- Assumes all 12 plugin tools are actually installed and available
- Little guidance on units, error handling, or what to do when a tool returns nothing
- US-centric: international coverage is reduced to a pointer to wx_global
Use it when a weather question must be answered with the weather plugin installed and the right tool choice is not obvious.
Do not use it when the weather plugin and its tools are unavailable, or for tasks unrelated to meteorology.
Security analysis
SafeThis is a pure usage-guide document for a fictional weather plugin's tools. It contains no shell commands, no network calls beyond referencing its own wx_* tools, no credential or secret handling, no file writes, and no obfuscated payloads. There is no execution surface here—only guidance on selecting and batching weather data/image tools—so the listing risk is negligible.
No concerns found
How this analysis is madeExamples
What's the severe weather threat from Indiana to New York this afternoon? Show me CAPE and updraft helicity zoomed on that corridor.Show me the 18z HRRR around Oklahoma City with cape, helicity, uh and srh.What's the dewpoint if the temperature is 30°C and relative humidity is 65 percent?name: weather-plugin description: Guide for using the weather plugin — data queries, radar imagery, model maps, and meteorological calculations version: 2.0.0 metadata: hermes: tags: [weather, radar, forecast, meteorology] category: weather
Weather Plugin Usage Guide
You have 12 weather tools. Prefer lightweight data tools and only use images when asked.
Tool Selection
"How's the weather in [place]?" → wx_conditions
"What's the forecast?" → wx_forecast
"Any warnings/watches?" → wx_alerts
"Show me the radar" → wx_radar_image
"Show me CAPE/temperature/wind map" → wx_model_image (use comma-separated vars: "cape,helicity,uh,srh" for multiple in ONE call)
"What's the severe weather outlook?" → wx_severe
"Weather in Tokyo/London/etc" → wx_global (worldwide)
"Calculate dewpoint/wind chill/LCL" → wx_calc
"Is there a tornado threat?" → wx_severe first, then wx_model_image --var cape or --var helicity for visual
"What does the HRRR show?" → wx_model_image with appropriate var
"Show me the 18z HRRR" → wx_model_image with cycle: 18
"Sounding at a point" → wx_sounding
IMPORTANT: Only these 12 tools exist
wx_conditions, wx_forecast, wx_alerts, wx_metar, wx_brief, wx_global, wx_severe, wx_radar_image, wx_model_image, wx_storm_image, wx_calc, wx_sounding
Do NOT try to call any other tool names.
Rules
- Start lightweight. Use
wx_conditionsorwx_briefbefore heavier tools. - Images only when asked. Don't call image tools unless the user wants to SEE something.
- US vs international. Use
wx_globalfor non-US locations. - Calculations are verified.
wx_calcuses metrust — 205 Rust-backed functions verified against MetPy. - Don't stack redundant calls.
wx_briefalready includes conditions + forecast + alerts. - BATCH model images. NEVER call wx_model_image multiple times for different variables. Use comma-separated vars in ONE call:
"cape,helicity,uh,srh". This generates all images at once. - Severe weather package. For severe weather analysis, use:
var: "cape,helicity,uh,srh"— one call, 4 images. - ZOOM to threat area. When the user asks about a specific region (e.g., "Indiana to New York"), ALWAYS pass lat/lon and radius_km to zoom in. Don't show full CONUS when they asked about a corridor. Examples:
- "Ohio Valley" →
lat: 39.5, lon: -83, radius_km: 400 - "Indiana to New York" →
lat: 40.5, lon: -77, radius_km: 500 - "Texas" →
lat: 31.5, lon: -99, radius_km: 500 - "Southeast" →
lat: 33, lon: -85, radius_km: 600 - "Great Plains" →
lat: 38, lon: -99, radius_km: 600Use your geographic knowledge to pick appropriate center + radius.
- "Ohio Valley" →
wx_calc Examples
- Dewpoint:
{"function": "dewpoint_from_relative_humidity", "args": {"temperature": "30 degC", "relative_humidity": "65 percent"}} - Wind chill:
{"function": "wind_chill", "args": {"temperature": "-5 degC", "speed": "30 km/hr"}} - Heat index:
{"function": "heat_index", "args": {"temperature": "95 degF", "relative_humidity": "60 percent"}} - LCL:
{"function": "lcl", "args": {"pressure": "1000 hPa", "temperature": "30 degC", "dewpoint": "20 degC"}}
Image Tools
wx_radar_image and wx_model_image return PNG file paths in JSON.
For radar: provide NEXRAD site ID (KRTX=Portland, KTLX=OKC, KLOT=Chicago) or lat/lon. Default 1024px, 200km range, 10dBZ noise filter.
For model images: specify variable (cape, refl, temp, dewpoint, rh, gust, helicity, uh, precip, mslp, heights_500, jet, srh). Add lat/lon + radius_km to zoom. Use cycle parameter for specific model runs.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/weather-plugin-usage-guide-mrwakeyy/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/weather-plugin-usage-guide-mrwakeyy' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/weather-plugin-usage-guide-mrwakeyy/download' --output '.skill-downloads/weather-plugin-usage-guide-mrwakeyy/SKILL.md.part' && mv '.skill-downloads/weather-plugin-usage-guide-mrwakeyy/SKILL.md.part' '.skill-downloads/weather-plugin-usage-guide-mrwakeyy/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/weather-plugin-usage-guide-mrwakeyy/SKILL.md' && test -s '.skill-downloads/weather-plugin-usage-guide-mrwakeyy/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/weather-plugin' && cp -R '.skill-downloads/weather-plugin-usage-guide-mrwakeyy' '.claude/skills/weather-plugin'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/weather-plugin-usage-guide-mrwakeyy'openskills read 'weather-plugin-usage-guide-mrwakeyy'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/weather-plugin-usage-guide-mrwakeyy/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Create Interactive Maps with kepler.gl
Data & AI
Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.
Agent-Driven Parameter Optimization
Data & AI
Guide for optimizing configurable systems with a measurable objective, using bounded trials and evidence-based recommendations.
ICP Visitor Outreach
Data & AI
Identify signed-up users matching the ideal customer profile but stalled, and draft personalized outreach to re-engage them.