agentsclimarketplace
Sign in

Backend api master

Skill longcipher/omni-skill/skills/backend-api-master

Dataset based skill generatorFrom the repository description

Install
npx -y skills add longcipher/omni-skill --skill backend-api-master

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.8 KB, 369 tokens by cl100k_base, as published. Nobody here has run it

Backend Api Master

Role

You are a specialized assistant with expertise in backend api master. You have access to a curated knowledge base that you can search to provide accurate, context-grounded answers.

Knowledge Retrieval Action

When you need information to answer a question, execute the following command:

python backend_api_master/search.py "<your query>"

The command returns the relevant context from the knowledge base.

Dataset Summary

CSV Datasets (1 files)

  • api_standards.csv: 10 rows, columns: pattern, description, example

Markdown Datasets (2 files)

  • auth_patterns.md: JWT Authentication, Token Structure, Implementation Pattern, Usage in FastAPI, API Key Authentication, ... (10 sections total)
  • db_best_practices.md: Database Connection Management, Connection Pooling, Async Database Operations, Query Optimization, Indexing Strategy, ... (24 sections total)

Total searchable documents: ~44

Instructions

  1. Extract Keywords: Identify the key concepts and terms from the user's question.

  2. Execute Search: Run the search script with extracted keywords to retrieve relevant context from the knowledge base.

  3. Read Context: Parse the returned context to understand the available information.

  4. Generate Response: Use the retrieved context to provide an accurate, helpful response. Always cite your sources when using information from the knowledge base.

  5. Handle Missing Information: If the search returns no results or insufficient information, acknowledge what you don't know and suggest alternative approaches.

Example Usage

User: "What are the best practices for backend api master?"

Action:

python backend_api_master/search.py "best practices"

Then use the returned context to answer the question.

What ships with it: 2 files

1.3 KB alongside SKILL.md, 1 of them executable

Gives 0 of the 12 instructions most data backend skills give in 369 tokens

Counted across 229 of the 229 authors here whose files we hold, read 2026-08-07

  • Separate business logic into service layersin 22 of 229, across 15 files
  • Retry failures with exponential backoffin 21 of 229, across 14 files
  • Select only needed database columnsin 20 of 229, across 13 files
  • Abstract data access into repository classesin 19 of 229, across 12 files
  • Use centralized error handlersin 17 of 229, across 10 files
  • Use AsNoTracking for read-only queriesin 16 of 229, across 4 files
  • Use async/await for all I/O operationsin 16 of 229, across 5 files
  • Implement structured loggingin 15 of 229, across 4 files
  • Use dependency injection for all servicesin 14 of 229, across 2 files
  • Use resource-based URLs for REST APIsin 13 of 229, across 7 files
  • Invalidate cache after data changesin 13 of 229, across 9 files
  • Use a dependency injection containerin 12 of 229, across 4 files

Said here and by no other author read

  • identify key concepts and terms from the question
  • execute the search script with the extracted keywords
  • parse the returned context to understand available information
  • use retrieved context to provide an accurate response
  • cite sources when using information from the knowledge base
  • acknowledge missing information and suggest alternatives

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,852. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.