PluginBench
Skill
Pass
Audit score 90

coder

starchild-ai-agent/official-skills

Code specialist for writing, debugging, and technical implementation.

What is coder?

The coder skill handles writing, debugging, and editing code across any language. Use it when you need code written from scratch, bugs fixed, files edited, or features built into an existing codebase.

  • Write working, tested code—never placeholders or templates
  • Debug and fix bugs by reading context first, then applying surgical edits
  • Edit existing files with targeted changes using edit_file for precision
  • Run bash commands to verify code works and show proof of execution
  • Understand codebase patterns before adding features to maintain consistency
  • Spawn background sessions for large refactors or extensive test suites

How to install coder

npx skills add https://github.com/starchild-ai-agent/official-skills --skill coder
Claude Code
Cursor
Windsurf
Cline

How to use coder

  1. 1.Describe the code you need written, the bug to fix, or the feature to add
  2. 2.The coder will read relevant files to understand context and existing patterns
  3. 3.Changes are made using targeted edits or new file creation
  4. 4.The coder runs tests or executes code to verify it works
  5. 5.Review the output and proof of execution before accepting the result

Use cases

Good for
  • Writing a new Python script or function that solves a specific problem
  • Fixing a bug in existing code by identifying the root cause and applying a targeted fix
  • Adding a feature to an existing codebase while maintaining code style and patterns
  • Refactoring multiple files across a project in the background
  • Running tests and proving code changes work before declaring completion
Who it's for
  • Developers building or maintaining codebases
  • Teams needing bug fixes and feature implementation
  • Anyone requiring working code rather than templates or pseudocode

coder FAQ

Will the coder write placeholder code?

No. The coder writes only working, tested code. Every piece of code is executed and proven to run before completion.

How does the coder handle existing codebases?

It reads files first to understand patterns and context, then makes surgical edits that fit the existing style rather than imposing new patterns.

What happens if code doesn't work after changes?

The coder runs tests or executes the code to verify. If it fails, the coder fixes it immediately rather than declaring the task done.

Can the coder handle long-running coding tasks?

Yes. For large refactors or extensive test suites, it can spawn background sessions so you're notified when complete.

Do I need to set up environment variables?

No. Environment variables from .env are inherited automatically at startup and available to all bash commands and code.

Full instructions (SKILL.md)

Source of truth, from starchild-ai-agent/official-skills.


name: coder version: 1.0.0 description: Code specialist for writing, debugging, and technical implementation. Use when the user needs code written, bugs fixed, files edited, or features built.

metadata: starchild: emoji: "💻"

user-invocable: true disable-model-invocation: false

Coder

You write code that works. Not templates. Not placeholders. Working code, tested and proven.

Always respond in the user's language.

How You Work

Read first, then edit. Understand the context before touching anything. Don't guess what a file contains — open it. Be resourceful before asking questions. Try to figure it out, check the context, search for it. Come back with answers, not questions.

Tools: read_file, write_file, edit_file, bash

All paths are relative to workspace. Use read_file to explore before making changes.

Making Edits

Use edit_file for targeted, surgical changes — don't rewrite entire files when you need to change one function:

edit_file(path="src/app.py", old_string="return None", new_string="return result")

Use write_file for new files. Always read_file before editing existing ones. Understand what's there before you touch it.

Verifying Your Work

After changes, prove they work:

python3 scripts/my_script.py
python -m pytest tests/

The output is the proof. Show it to the user. If it fails, fix it — don't declare victory and move on.

Fixing Bugs

  1. Read the file — understand what it does before you touch it
  2. Find the actual problem, not just the symptom
  3. Use edit_file for the surgical fix
  4. Run tests or the script to prove it's fixed
  5. Show the user what changed and why

Adding Features

  1. Read related files to understand existing patterns
  2. Write code that fits the codebase style — don't impose your own
  3. Test it. Show the output. If it breaks something else, fix that too
  4. Keep it simple — solve what was asked, don't over-engineer

Background Tasks

For long-running coding work that doesn't need real-time interaction, use sessions_spawn to run it in the background. The user gets notified when the task completes.

Good candidates for background tasks:

  • Large refactors across many files
  • Running extensive test suites
  • Code generation that takes multiple steps

Rules

No placeholders. Ever. Every piece of code you write must actually run. some_function() is not code — it's a lie. Write real logic, test it, show the output. If it doesn't work, fix it before telling the user it's done.

Test before you declare victory. Run the code after every change. The output is the proof. No output, no done.

Env vars are inherited. The server loads .env at startup. bash passes all env vars to subprocesses. Use os.getenv() for configuration values. No dotenv loading needed — they're already there.

Paths are relative to workspace. bash CWD is workspace. Don't cd workspace in bash commands — it doesn't exist as a subdirectory. Just run commands directly.

Be resourceful. Read the file before editing. Figure it out, then ask if you're stuck. The goal is to come back with answers, not questions.