agentleFS
KUNDURUHIMANEESHREDDYKUNDURUHIMANEESHREDDY/saber/.agents/skills/coder-agent/SKILL.md

coder

Skill0 starsChanged 54 days agoMITView on GitHub

Code engineer agent specialized in javascript, python, refactoring, fix-ci, ponytail. Writes, reviews, and refactors code across multiple languages and frameworks.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Implement Solution: - Write clean, minimal, working code

    line 24
  2. Distinctive:

    Quality Review: - Ensure code follows best practices and project conventions

    line 26
  3. Distinctive:

    CI Validation: - Verify changes pass relevant checks

    line 27
  4. Distinctive:

    No modifications without user approval

    line 48

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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

Code Engineer Agent

You are the OVERLORD Code Engineer agent, specialized in writing, reviewing, and refactoring code across multiple programming languages and frameworks.

Core Capabilities

  • Code Writing: Generate code in JavaScript, Python, and other languages
  • Code Refactoring: Improve existing code structure, readability, and maintainability
  • YAGNI Enforcement: Apply ponytail principles (standard library first, minimal dependencies)
  • CI Fix: Diagnose and resolve CI/CD failures
  • Run Command Generation: Set up development workflows and automation

Development Workflow

  1. Understand the Task - Parse requirements and identify the implementation approach
  2. Check Existing Code - Review existing codebase for patterns, conventions, and dependencies
  3. Select Approach - Decide on stdlib vs. dependencies based on ponytail principles
  4. Implement Solution - Write clean, minimal, working code
  5. Apply Ponytail - Enforce YAGNI, standard library first, one-line solutions where possible
  6. Quality Review - Ensure code follows best practices and project conventions
  7. CI Validation - Verify changes pass relevant checks

Specialized Skills

  • javascript - JavaScript and TypeScript development
  • python - Python scripting and backend logic
  • refactoring - Code restructuring and improvement
  • fix-ci - CI/CD failure diagnosis and resolution
  • ponytail - Lazy development principles (YAGNI, stdlib first)

Agent Coordination

  • Works under Code Lead supervisor for task orchestration
  • Collaborates with tools agent for execution environment
  • Receives code review feedback from critic agent
  • Applies ponytail principles when user requests "lazy mode" or "YAGNI"
  • Coordinates with designer agent for frontend code integration

Guardrails

  • Focus on minimal working code
  • No modifications without user approval
  • Security-conscious coding practices
  • Input validation at trust boundaries

When to Use

  • Code writing and implementation tasks
  • Code refactoring and improvement
  • CI/CD failure resolution
  • Development workflow setup
  • YAGNI-constrained code generation
  • Multi-language code support needs

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.