joeseesun GitHub avatar

qiaomu-goal-meta-skill

joeseesun

qiaomu-goal-meta-skill transforms vague requests into a copy-ready Codex /goal command with defaults, verification, boundaries, and pause conditions.

Stars

803

7-day growth

No data

Forks

60

Open issues

1

License

MIT

Last updated

2026-06-11

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It solves the core reason agent tasks fail—vague goals—by generating a structured 'task contract' that includes verification evidence, constraints, iteration policy, and stop conditions, all without requiring users to fill out forms.

Who it is for

  • Developers using Codex, Claude Code, or compatible agent environments
  • Product managers or designers who need to turn fuzzy ideas into executable tasks
  • Developers building apps, games, scripts, or Chrome extensions with AI agents
  • Anyone who wants to create safe, copyright-avoiding goals for agent execution

Use cases

  • Turning 'make an app' into a goal with step-by-step verification and constraints
  • Generating a safe /goal for a GTA-like browser game that explicitly avoids copyrighted IP
  • Creating a discovery-first goal for an unfamiliar domain (e.g., medical imaging tool) with pause conditions
  • Converting a bug-fix or refactoring request into a goal with write boundaries and iteration limits

Strengths

  • Produces a copy-ready /goal with concrete verification evidence (commands, logs, screenshots) instead of vague checks
  • Includes both a default conservative execution plan and numbered optional adjustments for key decisions
  • Provides separate English-compatible field labels (Verification, Constraints, Boundaries, etc.), making it usable in multilingual teams
  • Built-in linter script (lint_goal_command.py) catches placeholder text, vague verification, and unsafe permissions

Considerations

  • Only creates the /goal command; it does not execute the goal itself
  • Defaults to MVP-level goals; complete product strategy, deployment, and monetization require explicit requests
  • Requires a compatible agent environment (Codex, Claude Code) and Node.js/npx for installation

README quick start

安装

Description

Turn vague or complex Codex tasks into strong `/goal` commands with outcome, verification, constraints, boundaries, iteration policy, completion evide

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482