Agent skill · google
finding-google-skills
Locates and loads the right Google product skill on demand from a remote catalog index, instead of preloading every skill. Use at the START of any request touching a Google product, API, or developer platform - including Google Cloud (GKE, Cloud Run, IAM, BigQuery, Vertex AI, Spanner), Google Ads, Google Analytics, Google Workspace (Gmail, Drive, Admin SDK), Chrome and Chrome extensions, Android, Firebase, YouTube, Google Maps, Gemini and the Gemini API, Google Play, and Flutter. Consult the index before answering from memory or searching the web. Don't use for non-Google products.
What it needs
About 4k tokens when loaded.
What this skill does
Google Skill Finder Routes a request to the published Google skills that apply to it. The catalog lives outside this file and is fetched on demand, so loading this skill costs almost nothing until a lookup actually happens. Workflow 1. Fetch the catalog byte-exactly. Retrieve https://raw.githubusercontent.com/google/skills/main/index.json with a raw shell fetch (curl, wget; curl.exe on Windows PowerShell). It must arrive byte-for-byte, every entrypoint URL intact and unaltered. With no shell fetch tool but Node present, node -e "fetch(process.argv[1]).then(r=>r.text()).then(t=>console.log(t))" {url} also returns bytes. The catalog is about 75 KB and may not fit in a single tool result; a truncated preview is alphabetical, so it reads as though only the first few products exist. Prefer narrowing it before reading. With jq: curl -sS {url} jq -r '.skills[] select((.name+" "+.description) test("gke";"i")) "\(.name)\t\(.entrypoint)"'. In Windows PowerShell: (Invoke-RestMethod {url}).skills Where-Object { $.description -match "gke" } Select-Object name, entrypoint -First 3. With neither, a plain grep -o over the raw JSON still isolates candidate names. Where no filtering tool exists, write the catalog to a file and read it in parts (curl -sS {url} -o skills-index.json, or Invoke-WebRequest {url} -OutFile skills-index.json). This is often the better option regardless: it survives truncation, and re-reading a local file costs nothing. Delete it when the request is done. If only a summarizing fetch tool is available, phrase the request as extraction, not transcription: "List every entrypoint field in this document, one per line, exactly as written." Requesting it verbatim returns nothing usable. 2. Confirm the retrieval worked before using it. A tool call that returns without raising is not a success. It succeeded only if the body parses as JSON and holds a skills array. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills google/finding-google-skills--822e5a