ligolnik/flight-weather-watch
Aviation weather briefing tool that fetches WPC prog charts, QPF, AWC products, and FAA A/FD data, overlays flight routes, and generates HTML briefings with Claude analysis.
79
79%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, highly specific description that clearly communicates the skill's capabilities with concrete aviation-domain terminology. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The domain specificity naturally reduces conflict risk and provides excellent trigger terms.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for a weather briefing, preflight weather, or route weather analysis for a flight.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: fetches WPC surface prog charts, QPF precipitation forecasts, extended day progs, AWC icing/turbulence/SIGMET charts, overlays flight route on each chart, and produces a self-contained HTML briefing with analysis. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with detailed capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the nature of the task description. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords a pilot or aviation user would say: 'aviation weather briefing', 'VFR', 'IFR', 'flight', 'icing', 'turbulence', 'SIGMET', 'surface prog charts', 'precipitation forecasts', 'flight route'. Good coverage of domain-specific terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — aviation weather briefings with specific chart types (WPC, AWC, SIGMET) and flight route overlay. Very unlikely to conflict with any other skill. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill that provides clear CLI usage with concrete examples and real-world context like airport code mappings and timezone conversions. Its main weaknesses are moderate verbosity (explaining output contents Claude could discover, timezone tables Claude already knows) and lack of validation checkpoints in the workflow. The skill effectively covers the happy path and common error cases but could be tighter.
Suggestions
Remove or significantly trim the timezone conversion table — Claude already knows timezone offsets and DST rules. A single line like 'Convert local departure time to UTC based on the departure airport's timezone (accounting for DST)' suffices.
Trim the Output section to just the key facts Claude needs (e.g., 'Produces a self-contained HTML file opened in browser; includes GO/MARGINAL GO/NO-GO recommendation, chart images with magenta route overlay, TAFs, winds aloft, and AFDs') rather than listing every component.
Add a brief validation step after running the command, e.g., 'Verify the HTML opened successfully and contains chart images — if charts are missing, check error output and retry.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some information that could be trimmed, such as the detailed timezone conversion table (Claude knows timezones) and the explanation of what the HTML output contains. The user's preferred airports section is useful project-specific context, but the output section is somewhat verbose. | 2 / 3 |
Actionability | Provides fully executable commands with concrete examples, specific flag descriptions, and real ICAO codes. The cache re-run example is copy-paste ready with actual arguments. The command structure is unambiguous. | 3 / 3 |
Workflow Clarity | The main workflow (run the command) is clear, and the cache rebuild workflow has explicit steps. However, there are no validation checkpoints — no guidance on verifying the output is correct, checking that charts loaded properly, or what to do if the LLM analysis seems wrong. Error handling is listed but as a reference section rather than integrated into a workflow. | 2 / 3 |
Progressive Disclosure | Content is reasonably well-organized with clear sections, but it's somewhat monolithic — the options table, timezone table, user airport preferences, output description, and error handling are all inline. Some of this (like the full output description or requirements) could be separated or trimmed since it's reference material rather than operational guidance. | 2 / 3 |
Total | 9 / 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.
Reviewed
Table of Contents