agentleFS
mrlynnmrlynn/claude-skills/mongodb-skills/CLAUDE.md

claude-skills / mongodb-skills

CLAUDE.md8 starsChanged 9 months agoMITView on GitHub

8 production-ready skills extracted from the MongoDB Hackathon Platform. Each skill provides battle-tested patterns for building Next.js + MongoDB applications following MongoDB DevRel conventions. All tools use Python 3.7+ standard library only. No external dependencies.

  • Reads credentials

The file

We split this CLAUDE.md into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    All tools use Python 3.7+ standard library only.

    line 22
  2. Very specific:

    Check that a .env file has all required variables for selected skills.

    line 32
  3. Distinctive:

    All skills in this collection meet the following standards:

    line 89
  4. Distinctive:

    Real code, not pseudocode: Every code pattern is extracted from a production application

    line 91
  5. Distinctive:

    Python tools are deterministic: No LLM/API calls — pure local computation

    line 95

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
CLAUDE.md

MongoDB DevRel Skills

Overview

8 production-ready skills extracted from the MongoDB Hackathon Platform. Each skill provides battle-tested patterns for building Next.js + MongoDB applications following MongoDB DevRel conventions.

Skills Catalog

SkillDescriptionPython Tools
mongodb-nextjs-scaffoldNext.js + MongoDB + Auth + MUI project bootstrapbrand_color_checker.py, env_checker.py
mongodb-rbac-middlewareNextAuth v5 with 8-role RBAC and edge middlewarerole_matrix_generator.py
mongodb-email-systemTemplated transactional email with DB-backed templatestemplate_variable_checker.py
mongodb-atlas-provisioningSelf-service Atlas cluster management via Admin API v2atlas_cost_estimator.py
mongodb-ai-featuresAI integration: summarization, RAG pipeline, usage trackingembedding_cost_estimator.py, chunk_size_analyzer.py
mongodb-event-platformEvent lifecycle: CRUD, registration, feedback, judgingfeedback_form_generator.py
mongodb-partner-portalSponsor/partner management with 5-tier systemtier_report_generator.py
mongodb-devrel-advisorMeta-skill: conventions, branding, architecture decisions(none)

Python Tool Catalog

All tools use Python 3.7+ standard library only. No external dependencies.

brand_color_checker.py

Validate CSS/theme files against the MongoDB brand palette.

python mongodb-nextjs-scaffold/scripts/brand_color_checker.py path/to/theme.ts
python mongodb-nextjs-scaffold/scripts/brand_color_checker.py path/to/theme.ts --format json

env_checker.py

Check that a .env file has all required variables for selected skills.

python mongodb-nextjs-scaffold/scripts/env_checker.py .env --skills scaffold,rbac,email
python mongodb-nextjs-scaffold/scripts/env_checker.py .env --skills all --format json

role_matrix_generator.py

Generate a role-to-route permission matrix from an admin-guard configuration file.

python mongodb-rbac-middleware/scripts/role_matrix_generator.py path/to/admin-guard.ts
python mongodb-rbac-middleware/scripts/role_matrix_generator.py path/to/admin-guard.ts --format json

template_variable_checker.py

Parse email templates and report missing or unused variables.

python mongodb-email-system/scripts/template_variable_checker.py path/to/templates/
python mongodb-email-system/scripts/template_variable_checker.py path/to/templates/ --format json

atlas_cost_estimator.py

Estimate monthly Atlas cost for a cluster configuration.

python mongodb-atlas-provisioning/scripts/atlas_cost_estimator.py --tier M10 --provider AWS --region us-east-1
python mongodb-atlas-provisioning/scripts/atlas_cost_estimator.py config.json --format json

embedding_cost_estimator.py

Project Voyage AI and OpenAI embedding costs for a given document count and query volume.

python mongodb-ai-features/scripts/embedding_cost_estimator.py --docs 1000 --queries-per-month 5000
python mongodb-ai-features/scripts/embedding_cost_estimator.py --docs 1000 --queries-per-month 5000 --format json

chunk_size_analyzer.py

Analyze markdown files and recommend optimal chunk sizes for RAG ingestion.

python mongodb-ai-features/scripts/chunk_size_analyzer.py path/to/docs/
python mongodb-ai-features/scripts/chunk_size_analyzer.py path/to/docs/ --format json

feedback_form_generator.py

Generate a FeedbackFormConfig JSON document from a simple YAML specification.

python mongodb-event-platform/scripts/feedback_form_generator.py spec.yaml
python mongodb-event-platform/scripts/feedback_form_generator.py spec.yaml --format json

tier_report_generator.py

Generate a partner engagement summary report from partner data.

python mongodb-partner-portal/scripts/tier_report_generator.py partners.json
python mongodb-partner-portal/scripts/tier_report_generator.py partners.json --format json

Quality Standards

All skills in this collection meet the following standards:

  • Real code, not pseudocode: Every code pattern is extracted from a production application
  • Architecture decisions documented: Each skill explains WHY, not just WHAT
  • Common pitfalls listed: Known gotchas that save hours of debugging
  • Self-contained: Each skill can be used independently (dependencies are noted, not required)
  • Python tools are deterministic: No LLM/API calls — pure local computation
  • Standard library only: Python scripts have zero external dependencies

Related Skills

Skills reference each other where patterns overlap:

  • mongodb-nextjs-scaffold → foundation for all other skills
  • mongodb-rbac-middleware → depends on scaffold's auth setup
  • mongodb-email-system → depends on scaffold's DB connection
  • mongodb-atlas-provisioning → depends on scaffold + RBAC
  • mongodb-ai-features → depends on scaffold's singleton pattern
  • mongodb-event-platform → depends on scaffold, RBAC, email
  • mongodb-partner-portal → depends on scaffold, RBAC, email
  • mongodb-devrel-advisor → references all other skills

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.