agentleFS
Sign inStart free
fmindfmind/dotfiles/skills/google-developer/SKILL.md

google-developer

Skill13 starsChanged 4 days agoMITView on GitHub

Find Google developer docs and vendor skills (google/skills): Cloud, Ads, Analytics.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • fmind/dotword for word, first seen Nov 8, 2026

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Review before installing: follow the shared vendor-skill policy to review the selected immutable snapshot and install only the required …

    line 26
  2. Very specific:

    Protect Ads credentials and spend: keep developer tokens and OAuth credentials out of arguments and logs.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Google Developer Catalog

Route Google product work to the relevant selection in google/skills. Existing owners keep their procedures: gcloud (CLI identity and cloud defaults), cloud-run, infra-as-code, gws, agy, model-providers, agent-frameworks, colab, and kaggle.

Workflow

  1. Identify the product and operation: filter the generated catalog index by product keyword instead of listing every description, then choose the product group below:

    curl -fsSL https://raw.githubusercontent.com/google/skills/main/index.json \
  | jq -r '.skills[] | select((.name + " " + .description) | test("bigquery"; "i")) | .name'
  2. Review before installing: follow the shared vendor-skill policy to review the selected immutable snapshot and install only the required project-scoped guidance. A catalog lookup does not authorize executing its results.
  3. Verify guidance before acting: compare the selected guidance and the installed code with current official docs.
TaskCatalog group and selection
Compute, data, AI, GKE, operations, securitycloud; select the actual product plus applicable CLI/authentication guidance.
Advertising APIs and SDKsads; distinguish Ads API, Data Manager, Mobile Ads, and IMA.
Analytics reporting or configurationanalytics; Data API for reports, Admin API for properties and settings.
Sign in with Google or token bindingidentity; Sign in with Google for web, DPoP adoption.
Another Google product or documentation lookupdevelopers; retrieving-developer-knowledge for documentation search.

Gotchas

  • Protect Ads credentials and spend: keep developer tokens and OAuth credentials out of arguments and logs. Use test accounts and validate_only before authorized live mutations; campaign changes can affect spend.
  • Distinguish Analytics IDs; bound queries: API property IDs differ from G-... measurement IDs. Bound queries and exports, account for quotas, and keep sensitive reports out of Git.
  • Select skills, not whole plugins: select skills rather than importing an entire host plugin; hooks, MCP servers, and permissions are separate integrations. Cloud defaults and mutation scope remain with the owning workflow.

Official Skills

Upstream: google/skills, with cloud, ads, analytics, developers, and identity groups. Use its current index for the selected package rather than maintaining a copy of the product catalog.

Documentation

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free