Goal Crafter

Goal Crafter

Turn a vague task into a verifiable goal that an AI agent can run unattended.

Leading principle: A goal without a checkable completion criterion is just a wish. The agent must be able to answer "Am I done?" without asking a human.

Invocation modes

Choose the mode before following the process:

• Standalone mode: the user brings a vague task or directly asks for a goal. Run Phase 1 and clarify the task one question at a time.
• Compiled-handoff mode: an upstream skill such as to-goal invokes this skill after to-spec, to-tickets, or triage. The approved spec, selected ticket, tracker evidence, and repository state supply the answers. Do not interview the user again. Apply only this skill's verifiability rules and target-harness formatting.

In compiled-handoff mode, if a required product decision or completion condition is genuinely absent from the sources, report that the source is not agent-ready and name the missing evidence. Do not reopen the planning interview from inside goal compilation.

Process

Phase 1 — Clarify the task

Run this phase only in standalone mode. In compiled-handoff mode, extract the five answers from the upstream evidence without asking questions.

Ask the user, one question at a time:

1. What exactly should the agent do?

Get the task in one sentence. If it's vague ("优化代码", "改进 UI"), push for specifics.

1. Where does it run?

Which project / repo / workspace? Is there a specific branch or file area?

1. What does DONE look like?

This is the most important question. Push for observable, machine-checkable conditions:

| ❌ Vague (bad) | ✅ Verifiable (good) | |---|---| | "代码质量提高" | "tsc --noEmit 0 errors + eslint 0 warnings" | | "UI 更好看" | "页面在 375px / 768px / 1440px 三个断点下视觉一致，无溢出" | | "修复所有 bug" | "npm test 全部通过，且 git diff 只包含修复相关改动" | | "写好文档" | "README.md 包含安装/使用/API 三个章节，每个章节有代码示例" | | "性能优化" | "Lighthouse Performance 分数 ≥ 90，LCP "把这个 goal 粘贴到 [agent 名称] 里，它就会自己跑到完成。如果中途卡住，告诉我哪条完成标准没达到，我帮你调。"

In compiled-handoff mode, the upstream skill owns the delivery wrapper. Return the goal in the requested harness format without adding this standalone closing line.

---

Examples

Example 1: Code review automation

User: "帮我写个 goal，自动审查 PR"

Clarified:

• Task: 审查当前分支相对于 main 的所有改动
• Where: hive-private 仓库
• Done: 输出一份审查报告，列出所有 P0/P1 问题，每个问题标注文件和行号
• Constraints: 只读，不改文件
• Agent: Claude Code

Output:

Goal: 审查当前分支相对于 origin/main 的 diff

Completion criteria:
- [ ] 已读取完整的 git diff
- [ ] 已检查安全漏洞（SQL 注入、XSS、密钥泄露）
- [ ] 已检查逻辑错误（空指针、竞态条件、边界条件）
- [ ] 已检查代码规范（命名、结构、重复代码）
- [ ] 输出审查报告，每个问题标注：严重度 + 文件:行号 + 问题描述 + 修复建议

Constraints:
- 只读，不修改任何文件
- 只关注当前分支的改动，不审查已有代码

Context:
- 项目背景：Hive 是本地多 Agent 协作 runtime
- 设计 spec：docs/superpowers/spec.md

Example 2: UI redesign

User: "帮我写个 goal，重做这个页面"

Clarified:

• Task: 用 shadcn 组件库重做 OpsView 页面
• Done: 页面在 3 个断点下视觉一致，所有交互有 hover/focus/active 状态，通过 tsc 类型检查
• Constraints: 不改变现有 API 接口，使用项目已有的 Tailwind 配置
• Agent: Claude Code

Output:

Goal: 用 shadcn/ui 组件库重做 OpsView 页面

Completion criteria:
- [ ] 所有组件替换为 shadcn/ui 等价组件
- [ ] 页面在 375px / 768px / 1440px 断点下无溢出、无错位
- [ ] 所有可交互元素有 hover、focus、active 状态
- [ ] `tsc --noEmit` 0 errors
- [ ] 页面加载后无 console error

Constraints:
- 不修改 apps/web/src/api-client/ 下的任何文件
- 使用项目已有的 Tailwind 主题配置
- 不引入新的 npm 依赖（shadcn 除外）

Context:
- 当前页面：apps/web/src/views/OpsView.tsx
- UI 组件：apps/web/src/components/ui/index.tsx
- 样式：apps/web/src/styles.css

---

Special Rules

• Never skip Phase 1 question #3 in standalone mode. If the user can't define "done", the goal will fail. Help them brainstorm.
• Never re-interview in compiled-handoff mode. to-spec, to-tickets, or triage already owns clarification and product decisions; missing evidence means the source is not agent-ready.
• One verifiable condition per checkbox. Don't combine multiple conditions into one line.
• Constraints are your friend. They prevent the agent from "optimizing" unrelated files or introducing breaking changes.
• If the task is too large for one goal, suggest breaking it into 2-3 smaller goals with clear handoffs.
• For research/analysis goals (no code changes), the completion criterion is "output a report with specific sections".

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: tt-a1i
• Source: tt-a1i/matt-skills-with-to-goal
• License: MIT

Install and usage instructions live in the source repository linked above.