← ClaudeAtlas

copilot-clilisted

Executes tasks using the GitHub Copilot CLI (`copilot`). Automatically determines the safest permission mode (plan, editor, or autopilot) based on the task type.
yu-iskw/coding-agent-skills · ★ 1 · AI & Automation · score 55
Install: claude install-skill yu-iskw/coding-agent-skills
# executing-copilot ## Purpose Use this skill to perform coding, research, or automation tasks using the `copilot` CLI. It maps requests to Copilot's native tool-permission flags to balance automation with security. ## Permission Tiers | Tier | Mode | Flag(s) | Capability | Approval Required | Typical Tasks | | :---- | :------------- | :----------------------- | :------------------------------------------- | :------------------ | :---------------------------------------- | | **0** | `plan` | _(none)_ | Read-only analysis; prompts for every tool. | **No** | Code review, audits, research. | | **1** | `editor` | `--allow-tool='write'` | Auto-approves file edits; prompts for shell. | **Yes** | Refactoring, documentation, lint fixes. | | **2** | `autopilot` | `--allow-all-tools` | Auto-approves ALL tools (edits + shell). | **Yes (High Risk)** | CI/CD, complex builds, automated testing. | ## Implementation Workflow ### 1. Analyze & Classify Analyze the user's intent to determine the required permission tier. - **Tier 0 (Plan)**: Does the task only involve reading code, analyzing architecture, or gathering information? - **Tier 1 (Editor)**: Does the task involve modifying files but no autonomous shell command execution? - **Tier 2 (Autopilot)**: Does the task require running tests, build scripts, or ma