agentleFS
jalbarrangjalbarrang/skills/firestore/SKILL.md

firestore

Skill2 starsChanged 3 months agoMITView on GitHub

Read Firestore data from the command line — list collections, query documents with filters, fetch a document by path, count documents, and map relations between collections. Use when the user asks to inspect Firestore, query a collection, check a document, count matching documents, or explore the data model of a Firebase project.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read-only Firestore access through the published @dreki-gg/firestore-cli package.

    line 8
  2. Very specific:

    Every command prints a human digest to stdout.

    line 50

≈ “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

firestore

Read-only Firestore access through the published @dreki-gg/firestore-cli package. No scripts ship with this skill — every command runs via npx:

npx -y @dreki-gg/firestore-cli <command>

Setup

  1. Config file — .agents/firestore.json in the project, walked up from the working directory:
{
  "defaultEnvironment": "prod",
  "environments": {
    "dev":  { "projectId": "my-dev-project",  "serviceAccountKeyPath": ".agents/sa.dev.json" },
    "prod": { "projectId": "my-prod-project", "serviceAccountKeyPath": ".agents/sa.prod.json" }
  }
}
  1. A service-account JSON key at each serviceAccountKeyPath. GOOGLE_APPLICATION_CREDENTIALS and .firebaserc work as fallbacks when no config file exists.

Select a non-default environment with --env <name> on any command. Missing config or keys produce an actionable error listing the paths that were tried.

Commands

npx -y @dreki-gg/firestore-cli collections [path]
npx -y @dreki-gg/firestore-cli query <collection> [--where field,op,value]... [--order-by field[,dir]] [--limit n] [--start-after id]
npx -y @dreki-gg/firestore-cli get <docPath>
npx -y @dreki-gg/firestore-cli count <collection> [--where field,op,value]...
npx -y @dreki-gg/firestore-cli relation-map <collection>
  • collections — root collections, or subcollections of a document path like users/abc123.
  • query — --where is repeatable; op is a Firestore operator (==, !=, <, <=, >, >=, array-contains, in). Values are coerced (numbers, booleans) automatically.
  • get — full document path, e.g. users/abc123.
  • count — server-side aggregate count, cheap even on large collections.
  • relation-map — scans local source code plus sampled field values to infer which collections reference each other.

Output contract

Every command prints a human digest to stdout. Large result sets are also written to a temp file whose path is printed — read that file for the complete JSON.

Etiquette

This CLI is read-only by design. For writes, use the project's own tooling or the Firebase console — never improvise writes against production data.

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.