Qiaomu Goal Meta Skill

What it does

When your agent uses it

• The user asks for Codex goal instructions
• Plan-to-goal interviews
• Success criteria
• Verification commands

Example prompts

• “/qiaomu-goal-meta-skill”

Requirements

• Python 3

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

1. 1Restate the task as an outcome, not an activity.
2. 2Classify the task using references/default-goal-strategy.md: familiar vs unknown domain, low vs high risk, new work vs existing project.
3. 3Choose best defaults for low-risk unknowns and write a one-sentence reason.
4. 4Identify missing information across the Goal contract
5. 5If the task is under-specified, prefer numbered multiple-choice adjustments with defaults. Use references/interview-checklist.md.
6. 6For Chinese-first users, produce the Chinese recommended execution goal first, then an English-compatible mirror that preserves the same…
7. 7Check the command against references/goal-command-playbook.md.
8. 8For file deliverables, run python3 scripts/lint_goal_command.py before calling the goal done.

What it can do on your machine

Read from SKILL.md and the folder at commit f29e018. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python3
  • make

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • x.com
  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Qiaomu Goal Meta Skill loads about 1.7k tokens when it runs, and up to ~8.1k if it reads all its reference files. Until then it costs about 101 tokens; SKILL.md has 672 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~101

When it runs · the whole SKILL.md, loaded when a task matches

~1.7k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~8.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from joeseesun/qiaomu-goal-meta-skill at commit f29e018, republished under its MIT licence (© joeseesun). 672 words, ~1,728 tokens.

name

qiaomu-goal-meta-skill

description

Turn vague or complex Codex tasks into strong `/goal` commands with outcome, verification, constraints, boundaries, iteration policy, completion evidence, and pause/block conditions. Use when the user asks for Codex goal instructions, Goal 指令, 目标指令, `/goal` prompts, 中文 Goal 模板, plan-to-goal interviews, success criteria, verification commands, or bounded agent work definitions.

/goal Create a first-version local MVP for the requested task, inspect project-provided commands before changing code, implement the core user-visible workflow, and keep unrelated systems unchanged.
Verification: run the smallest project-provided checks, start the local app or relevant runtime, complete the core workflow once, and capture logs/screenshots or command output as evidence.
Constraints: do not add accounts, paid services, production changes, destructive operations, or unrelated features unless requested.
Boundaries: write only inside the new project directory or the directly related existing project files.
Iteration policy: implement one focused workflow at a time, rerun checks after meaningful changes, inspect logs before retrying, and make at most 3 focused improvement rounds before reporting remaining risks.
Stop when: the core workflow is proven by runtime evidence and checks pass or missing checks are explicitly reported.
Pause if: credentials, payments, production data, destructive changes, legal/medical/financial decisions, copyrighted assets, or unclear ownership is required.

/goal 基于用户需求创建第一版本地 MVP，先读取项目已有命令和约束，实现核心用户可见流程，并避免改动无关系统。
验证：运行项目提供的最小相关检查，启动本地应用或对应运行环境，完整走通一次核心流程，并用日志、截图或命令输出作为证据。
约束：不加入账号、付费服务、生产变更、破坏性操作或无关功能，除非用户明确要求。
边界：只写入新项目目录，或只修改现有项目中与该功能直接相关的文件。
迭代策略：一次实现一个聚焦工作流，每次有意义改动后重跑检查，重试前先读日志，最多做 3 轮聚焦改进后报告剩余风险。
完成条件：核心流程有运行证据证明可用，检查通过或明确说明缺少配置。
暂停条件：需要凭证、付费、生产数据、破坏性操作、法律/医疗/金融判断、版权素材或所有权不清时暂停。

© joeseesun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files (scripts, references) in the repository root of joeseesun/qiaomu-goal-meta-skill.

• SKILL.md
• .gitignore
• LICENSE
• README.md
• agents/interface.yaml
• manifest.json
• references/default-goal-strategy.md
• references/goal-command-playbook.md
• references/interview-checklist.md
• scripts/lint_goal_command.py

Open the folder on GitHubat commit f29e018