From api-registry
Use BEFORE writing API config, env setup, auth, LLM client init, or debugging an external service. Returns authoritative source URLs, latest version, and deprecation warnings. Triggers on any named library/API/tool.
How this skill is triggered — by the user, by Claude, or both
Slash command
/api-registry:api-registryThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**You MUST consult the registry before emitting API configuration or diagnosing API failures.** Training data for rapidly changing APIs (Groq models, better-auth config, Supabase, Vercel, Railway, Next.js) goes stale within days.
You MUST consult the registry before emitting API configuration or diagnosing API failures. Training data for rapidly changing APIs (Groq models, better-auth config, Supabase, Vercel, Railway, Next.js) goes stale within days.
Identify the service. Extract the name from the user's request (better-auth, groq, supabase, etc.).
Check the registry:
tsx ${CLAUDE_PLUGIN_ROOT}/scripts/lookup.ts <name>
If found:
vendor_url, docs_url, changelog_url, latest_version, last_checked inline.deprecated_notes is set, render a 🚨 WARNING block BEFORE writing any config.last_checked > 14 days, remind user to /api-registry:refresh <name> OR proceed but flag uncertainty./api-registry:docs <name> <query> for any non-trivial config question.If not found:
<name> isn't in the registry. Add it via /api-registry:add <name>?⚠️ No registered source for <name>; answer may reflect stale training data.Never emit config code that cites training-data recall when a registered docs_url exists. Always route through /api-registry:docs.
Provides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.
npx claudepluginhub tyroneross/rosslabs-ai-toolkit --plugin api-registry