Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Firestore Operations Manager · jeremylongshore | DecimalAI

jeremylongshore/firestore-operations-manager

SkillScore71Maintained

Manage Firebase/Firestore operations including CRUD, queries, batch processing, and index/rule guidance. Use when you need to create/update/query Firestore documents, run batch writes, troubleshoot missing indexes, or plan migrations. Trigger with phrases like "firestore operations", "create firestore document", "batch write", "missing index", or "fix firestore query".

Databy jeremylongshore

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Data Engineer packcommunitymigrationfirestore-operations

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/jeremylongshore-firestore-operations-manager/SKILL.md

decimalai skills pull jeremylongshore-firestore-operations-manager --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/jeremylongshore-firestore-operations-manager/SKILL.md https://app.decimal.ai/s/jeremylongshore-firestore-operations-manager/SKILL.md

Raw file: /s/jeremylongshore-firestore-operations-manager/SKILL.md ↗ · machine-readable summary at /s/jeremylongshore-firestore-operations-manager.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

24 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 22d ago

Yes — +17% lift+13% tokens0% turns71% of whole cases pass with skill (17/24)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	26%	0%
case-06	✗→✓	▲ Improved	22%	0%
case-09	✗→✓	▲ Improved	12%	0%
case-16	✗→✓	▲ Improved	34%	0%
case-05	✓→✓	＝ Same ✓	0%	0%

Showing 5 of 24 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

jeremylongshore / claude-code-plugins-plus-skills

skills/.curated/firestore-operations-manager/SKILL.md

View on GitHub ↗

License MITImported 8/25/2026Version v1Bundled 4 files · scripts

Skill contents

scripts/

references/

SKILL.md

Firestore Operations Manager

Operate Firestore safely in production: schema-aware CRUD, query/index tuning, batch processing, and guardrails for permissions and cost.

Overview

Use this skill to design Firestore data access patterns and implement changes with the right indexes, security rules, and operational checks (emulator tests, monitoring, and rollback plans).

Prerequisites

A Firebase project with Firestore enabled (or a local emulator setup)
A clear collection/document schema (or permission to propose one)
Credentials for the target environment (service account / ADC) and a plan for secrets

Instructions

Identify the operation: create/update/delete/query/batch/migration.
Confirm schema expectations and security rules constraints.
Implement the change (or propose a patch) using safe patterns:

prefer batched writes/transactions where consistency matters
add pagination for large queries

Check indexes:

detect required composite indexes and provide firestore.indexes.json updates

Validate:

run emulator tests or a minimal smoke query
confirm cost/perf implications for the query pattern

Output

Code changes or snippets for the requested Firestore operation
Index recommendations (and config updates when needed)
A validation checklist (emulator commands and production smoke tests)

Error Handling

Permission denied: identify the rule/role blocking the operation and propose least-privilege changes.
Missing index: provide the exact composite index needed for the query.
Hotspot/latency issues: propose sharding, pagination, or query redesign.

Examples

Example: Fix a failing query

Request: “This query needs a composite index—what do I add?”
Result: the exact index definition and a safer query pattern if needed.

Example: Batch migration

Request: “Backfill a new field across 100k docs.”
Result: batched write strategy, checkpoints, and rollback guidance.

Resources

Full detailed guide (kept for reference): ${CLAUDE_SKILL_DIR}/references/SKILL.full.md
Firestore docs: https://firebase.google.com/docs/firestore
Firestore indexes: https://firebase.google.com/docs/firestore/query-data/indexing

Illustrative Want to see what jeremylongshore/firestore-operations-manager would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/30/2026, 10:28 UTC · 24 cases

Lift

+17%

71% vs 54%

Agent turns

1.0 vs 1.0

Tokens

+13%

3,089.63 vs 2,734.29

fail → pass · 4pass → pass · 13fail → fail · 7

Per-case results (24)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 We have a Firestore query filtering by status == 'active' and ordering by createdAt desc with a limit of 50. In production this query fails with a missing index error. Show how to fix the query, provide the exact index configuration file update, and give a validation checklist.	fail→pass	14,147	13,374	-5%	1	1	0%	1,727	2,173	+26%	0	0	—
case-02 We need to backfill a new field isArchived: false across 50,000 documents in the orders collection in Firestore. Provide the migration script approach, error handling, and operational checks.	fail→fail	18,399	19,118	+4%	1	1	0%	3,488	4,164	+19%	0	0	—
case-03 Our application increments a viewCount document field on every pageview for a viral post in Firestore. Under heavy load, writes fail with contention errors. Provide the operational design and implementation.	fail→fail	33,290	21,306	-36%	1	1	0%	4,847	3,340	-31%	0	0	—
case-04 A client app receives PERMISSION_DENIED when attempting to update userProfiles/{userId} in Firestore. The current rule allows read to everyone but blocks writes. Users should only be able to update their own profile's displayName and bio fields. Provide the rule patch and validation checklist.	fail→fail	14,698	9,253	-37%	1	1	0%	1,785	2,230	+25%	0	0	—
case-05 We need a Node.js script to fetch all 200,000 documents from the analytics_events collection in Firestore to generate a local report. How should we structure the data access code?	pass→pass	15,232	16,346	+7%	1	1	0%	2,751	2,761	+0%	0	0	—
case-06 We need to transfer 50 dollars from user A's balance document to user B's balance document in Firestore. Write the implementation code with consistency guarantees and validation steps.	fail→pass	15,123	20,400	+35%	1	1	0%	3,005	3,679	+22%	0	0	—
case-07 We have a subcollection comments under top-level collections like posts/{postId}/comments in Firestore. We want to query all comments ordered by createdAt descending where flagged == true. Provide the query code and index configuration.	pass→pass	13,054	14,943	+14%	1	1	0%	1,594	2,378	+49%	0	0	—
case-08 We are designing a multi-tenant chat application in Firestore with 10,000 organizations, each having up to 100 channels and 1,000,000 messages. Write the schema structure and query design.	pass→pass	31,263	25,491	-18%	1	1	0%	5,163	5,487	+6%	0	0	—
case-09 Instead of deleting user documents in Firestore, we soft-delete them by setting deletedAt timestamp and exclude them from active user list queries. Provide the query pattern, index config, and validation checklist.	fail→pass	19,693	18,894	-4%	1	1	0%	2,891	3,235	+12%	0	0	—
case-10 Users report stale data when reopening our web app after being offline. How should we check snapshot state and configure Firestore SDK local caching?	pass→pass	19,088	19,069	-0%	1	1	0%	2,645	3,003	+14%	0	0	—
case-11 We need to prevent updates to Firestore documents in invoices once invoice.status is set to 'paid'. Provide the exact Firestore Security Rule snippet and explain the validation checks.	pass→pass	14,011	14,828	+6%	1	1	0%	1,576	2,305	+46%	0	0	—
case-12 We need to purge 80,000 expired log documents from the system_logs collection in Firestore. Write the deletion script logic with operational safety checks.	fail→fail	20,830	16,620	-20%	1	1	0%	3,837	3,594	-6%	0	0	—
case-13 Users want to search products in Firestore matching any of 5 target tags and order results by price ascending. Show the query, index configuration, and smoke test checks.	pass→pass	18,170	15,264	-16%	1	1	0%	2,579	2,615	+1%	0	0	—
case-14 A dashboard listening to the entire orders collection in Firestore via onSnapshot is causing read cost spikes. How do we refactor this query pattern and validate cost impact?	pass→pass	21,154	23,606	+12%	1	1	0%	2,887	3,866	+34%	0	0	—
case-15 We need to set up unit testing for our Firestore security rules and client queries prior to staging deployment. Write the test runner commands and validation checklist.	fail→fail	14,744	11,215	-24%	1	1	0%	2,458	2,582	+5%	0	0	—
case-16 We want Firestore to automatically expire and delete documents in our sessions collection older than 7 days without custom Cloud Functions. How do we configure this native feature?	fail→pass	14,964	10,563	-29%	1	1	0%	1,848	2,470	+34%	0	0	—
case-17 Firestore is auto-indexing a high-cardinality searchKeywords field on our documents collection, driving up storage costs. How do we disable single-field indexing for this field in configuration?	pass→pass	14,636	12,682	-13%	1	1	0%	1,746	1,890	+8%	0	0	—
case-18 A third-party webhook delivers payment confirmation events that update user subscription status in Firestore. Webhook retries might happen. How do we implement idempotent handling and validation?	fail→fail	16,716	15,840	-5%	1	1	0%	3,438	4,019	+17%	0	0	—
case-19 Fetching author profiles separately for 50 blog posts from Firestore causes N+1 queries. How should we denormalize author display fields and handle profile updates?	pass→pass	18,549	19,812	+7%	1	1	0%	2,911	3,660	+26%	0	0	—
case-20 We built forward pagination with startAfter. Now we need backward pagination ('Load previous messages') for a chat feed in Firestore. How do we implement backward pagination efficiently?	pass→pass	17,380	18,516	+7%	1	1	0%	3,509	3,352	-4%	0	0	—
case-21 We need to enforce schema validation in firestore.rules for products: name must be string, price must be a positive number. Write the rule patch and validation strategy.	pass→pass	10,572	14,218	+34%	1	1	0%	2,254	2,629	+17%	0	0	—
case-22 We wrote a TypeScript Firebase Cloud Function onDocumentCreated('orders/{orderId}') that sends confirmation emails via SendGrid. How do we deploy this Cloud Function using Firebase CLI?	pass→pass	8,912	6,224	-30%	1	1	0%	1,951	1,858	-5%	0	0	—
case-23 We want to export Firestore data continuously to Google BigQuery for business intelligence analysis. How do we configure the Firebase Stream Firestore to BigQuery extension?	pass→pass	17,294	20,306	+17%	1	1	0%	2,643	3,701	+40%	0	0	—
case-24 We need to set up Firebase Authentication custom claims so user roles like admin are stored in Auth JWT tokens via Node.js Admin SDK. Write the Admin SDK setup script.	fail→fail	10,828	16,678	+54%	1	1	0%	2,090	3,160	+51%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted. The headline lift of +17 percentage points is the difference between those two pass rates over the 24 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 54.2%
Pass rate with the skill: 70.8%
Cases attempted: 24
Cases counted toward lift: 24
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/30/2026, 10:28 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-01

Prompt

We have a Firestore query filtering by status == 'active' and ordering by createdAt desc with a limit of 50. In production this query fails with a missing index error. Show how to fix the query, provide the exact index configuration file update, and give a validation checklist.

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run71

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+16% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 22 days ago

Other measured skills in the registry, with their headline benchmark lift.