GC

gsemet/copilot-goal-skill

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

18 stars 质量 68 趋势 36MIT

An orchestrator for GitHub Copilot that bounces between a Builder (does the work) and an Inspector (judges the result) until the goal is met.

概览

— an orchestrator that bounces between a Builder (does the work) and an Inspector (judges the result) until the goal is met. You need to enable Copilot YOLO mode to use this skill efficiently. Autopilot is a similar feature directly provided by Copilot. It used to use hardcoded rules to find out if a task is done, which was not reliable. Starting VS Code 1.124, , instead of relying on custom rules. For that you need to set chat.autopilot.advanced.enabled to true in your VS Code settings. However, by Autopilot if you care about the following: - the goal.md is clearly defined, written in your repository - Use a smarter model for inspector (Autopilot uses a small utility model) - Git audit trail (you can see in the history the different review, retry, ...) 1. — asks clarifying questions until it can write a clear goal with measurable acceptance criteria 2. — explores your repo for conventions, quality gates, commit rules 3. — immutable goal.

README

以下为原文 README 节选,完整内容请查看原文。

Goal Skill for GitHub Copilot

Verified autonomous task completion — an orchestrator that bounces between a Builder (does the work) and an Inspector (judges the result) until the goal is met.

[!TIP] You need to enable Copilot YOLO mode to use this skill efficiently.

Important: Why Not Just Autopilot?

Autopilot is a similar feature directly provided by Copilot. It used to use hardcoded rules to find out if a task is done, which was not reliable.

[!IMPORTANT]

Starting VS Code 1.124, Autopilot CAN be configured to use an utility model to evaluate to completion of the task, instead of relying on custom rules.

For that you need to set chat.autopilot.advanced.enabled to true in your VS Code settings.

However, this skill is not deprecated by Autopilot if you care about the following:

  • the goal.md is clearly defined, written in your repository
  • Use a smarter model for inspector (Autopilot uses a small utility model)
  • Git audit trail (you can see in the history the different review, retry, …)

How It Works

  1. Relentless interview — asks clarifying questions until it can write a clear goal with measurable acceptance criteria
  2. Project discovery — explores your repo for conventions, quality gates, commit rules
  3. Writes a goal file — immutable goal.md with acceptance criteria that becomes the single source of truth
  4. Builder → Inspector loop — the Builder implements and commits; a separate Inspector (different model, fresh context) independently verifies against the goal; if FAIL, the Builder gets feedback and tries again
  5. Git commit trail — each iteration is committed, so you can review the history of coder and inspector decisions
  6. Summary and squash — when the Inspector says PASS, you get a summary and a ready-to-use squash command

Architecture

Run the Goal skill with GPT-6 Luna (copilot). The default subagent models are:

Agent Model Role
Builder GPT-5.6 Luna (copilot) Implements the goal
Inspector GPT-6.1 Sol (copilot) Verifies independently

The Inspector runs on a separate model with fresh context by design — it forces clear, verifiable acceptance criteria. If the Inspector can’t tell whether the goal is met, the goal was poorly defined.

Installation

Marketplace

Install this project as Marketplace in VS code settings:

https://github.com/gsemet/copilot-goal-skill.git

Manual

在 GitHub 查看完整 README

推荐工具

换一个关键词,或者移除筛选条件。

安装

npx skillfish add gsemet/copilot-goal-skill
新手?先看 mcpskill.org 教程 →