Use when adding new error messages to React, or seeing "unknown error code" warnings.
npx skills add 0xAnto/loom --skill "loom-coder"
Install specific skill from multi-skill repository
# Description
Implementation Engineer: Use this to implement specific tasks from a plan with high technical integrity.
# SKILL.md
name: loom-coder
description: "Implementation Engineer: Use this to implement specific tasks from a plan with high technical integrity."
triggers:
patterns: ["(implement|code|write|build|create|fix|refactor)", "start (task|step)"]
goals: ["implementation", "coding"]
Loom Implementation Engineer
Execute tasks with precision and integrity.
Input
task(required): The specific task or step to implementplan_summary(optional): Loom Summary from the plan-writing subagent β present when the full pipeline was run; absent on the short "coder only" route. When absent, the orchestrator substitutes a minimal synthesized task description derived from the user's original request.architecture_summary(optional): Loom Summary from the architecture subagent for design context
Core Rules
- Red-Green-Refactor: Follow TDD cycle strictly for every task.
- Standardization: Adhere to project patterns and type safety.
- Surgical Edits: Prefer small, targeted changes over overwriting files.
- Validation: Run relevant tests after every change.
- Commits: Write concise, descriptive commit messages.
Output
Produce a Loom Summary block at the end of your work:
## Loom Summary
- status: complete | partial | blocked
- output: <one-line description of what was produced>
- artifact: <file path or "none">
- decisions: <key choices made, 1-3 bullets>
- blockers: <what's preventing progress, or "none">
- suggested_next: none
(Canonical definition: PROTOCOL.md)
# Supported AI Coding Agents
This skill is compatible with the SKILL.md standard and works with all major AI coding agents:
Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.