From attune-help
Get context warnings for a file based on its extension and name. Surfaces known gotchas before the user hits them. Triggers on: warn me, gotchas, pitfalls, what should I watch out for, check this file.
How this skill is triggered — by the user, by Claude, or both
Slash command
/attune-help:lookup-warnThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
File-context warnings for the file the user is editing or
File-context warnings for the file the user is editing or
about to edit. Uses the lookup_warn MCP tool, which maps
the file extension and name to relevant tags and returns
the top N matching warning and task templates.
If no file path is provided, use AskUserQuestion:
question: "Which file should I check?"
header: "lookup-warn"
options:
- label: "The file I'm currently viewing"
description: "Use the IDE selection (if one is active)"
- label: "A different file"
description: "Provide a path relative to the project root"
If an IDE selection is available, prefer it without asking.
lookup_warn with:
file_path — the user's filemax_results — 3 by default, or what the user asked fortemplate_dir — .help/templates if the project has one,
otherwise omitcount is 0, tell the user there are no known warnings
for this file type and suggest running lookup-list to
browse topics manually.warnings array as a list item.## Warnings for `<file-path>`
3 relevant topics:
1. <first warning content>
2. <second warning content>
3. <third warning content>
*To look up any of these topics in more detail, say 'look up X'.*
Keep entries compact — the templates are already rendered. Don't paraphrase the tool output.
npx claudepluginhub smart-ai-memory/attune-docs --plugin attune-helpProvides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.