New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Goal Crafter

by tt-a1i in tt-a1i/matt-skills-with-to-goal

Craft verifiable, tight goal prompts for AI coding agents (Claude Code /goal, Codex Automations, Pi), either from a standalone task interview or from an already-approved to-goal handoff.

MITAuto-check passed

Install Goal Crafter

skills CLI
$ npx skills add tt-a1i/matt-skills-with-to-goal --skill goal-crafter -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install tt-a1i/matt-skills-with-to-goal goal-crafter --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/tt-a1i/matt-skills-with-to-goal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/engineering/goal-crafter .claude/skills/goal-crafter && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
goal-crafter
GitHub stars
184
Token cost
~1.8k tokens
SKILL.md length
748 words
Files
4
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Craft verifiable, tight goal prompts for AI coding agents (Claude Code /goal, Codex Automations, Pi), either from a standalone task interview or from an already-approved to-goal handoff.

  • Works in 4 steps: Clarify the task → Draft the goal → Verify the goal → …
  • The user says 给我一个 goal 提示词
  • SKILL.md covers Invocation modes, Process, Examples and Special Rules
  • Calls tsc, npm and git

What it does

Goal Crafter is an agent skill from tt-a1i/matt-skills-with-to-goal. Craft verifiable, tight goal prompts for AI coding agents (Claude Code /goal, Codex Automations, Pi), either from a standalone task interview or from an already-approved to-goal handoff. Use when the user says "给我一个 goal 提示词", "帮我写个 goal", "设置一个自动化任务", "我想让 agent 自动做 X", or asks to turn a task into a self-running loop. Ensures every goal has a checkable completion criterion so the agent knows when it's done.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `README.md` and `agents/openai.yaml`).

The repository describes itself as: Planning → verifiable goals → fresh-session implementation for AI coding agents. Based on mattpocock/skills v1.1. The licence is MIT.

When your agent uses it

  • The user says 给我一个 goal 提示词
  • 我想让 agent 自动做 X
  • Asks to turn a task into a self-running loop

Example prompts

  • “给我一个 goal 提示词”
  • “帮我写个 goal”
  • “设置一个自动化任务”
  • “/goal-crafter”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Clarify the task
  2. Draft the goal
  3. Verify the goal
  4. Deliver

What it can do on your machine

Read from SKILL.md and the folder at commit d09351e. 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

    Shell commands in SKILL.md call:

    • tsc
    • npm
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use npm and git, which can reach the network depending on how they are called.

    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

Goal Crafter loads about 1.8k tokens when it runs. Until then it costs about 106 tokens; SKILL.md has 748 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~106
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from tt-a1i/matt-skills-with-to-goal at commit d09351e, republished under its MIT licence (© tt-a1i). 748 words, ~1,770 tokens.

Download SKILL.mdSave it as .claude/skills/goal-crafter/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
goal-crafter
description
Craft verifiable, tight goal prompts for AI coding agents (Claude Code /goal, Codex Automations, Pi), either from a standalone task interview or from an already-approved to-goal handoff. Use when the user says "给我一个 goal 提示词", "帮我写个 goal", "设置一个自动化任务", "我想让 agent 自动做 X", or asks to turn a task into a self-running loop. Ensures every goal has a checkable completion criterion so the agent knows when it's done.

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: approved planning evidence already supplies the answers. Do not interview the user again. Apply only this skill's verifiability rules and target-harness formatting. The evidence may come from a conversation, spec, issue, document, or another skill.

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, in this shape (standalone interview only — keep compiled-handoff mode emoji-free):

❓ **QN** - **<short title>**
<body>

💡 <your recommended answer, when you have one>

Walk these five in order:

  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.

  2. Where does it run? Which project / repo / workspace? Is there a specific branch or file area?

  3. 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 < 2.5s"

  4. Any constraints? Don't touch certain files? Must use specific tools? Budget limit? Time limit?

  5. What agent / harness? Claude Code (/goal), Codex (Automations), Pi, or generic?

Phase 1 complete when you have answers to all 5 questions. If the user can't answer #3, help them brainstorm verifiable conditions — this is the most common failure point.

Phase 2 — Draft the goal

Write the goal in the target agent's format. Follow these rules:

The three shapes below are the formats this skill deliberately maintains for the harnesses it is most often pointed at. They are a snapshot, not a standard: when the target harness documents a different shape, follow the harness and treat the block here as the fallback. Any harness not listed uses the generic block.

For Claude Code /goal:

Goal: [one-line task description]

Completion criteria:
- [ ] [checkable condition 1]
- [ ] [checkable condition 2]
- [ ] [checkable condition 3]

Constraints:
- [file/area restrictions]
- [tool/approach restrictions]
- [budget/time limits]

Context:
- [key files to read first]
- [relevant docs/specs]
- [related issues/PRs]

For Codex Automations:

Task: [one-line description]
Frequency: [once / on push / on schedule]
Verification: [checkable condition]
Workspace: [project path]

For Pi / generic:

任务：[一句话]
完成标准：
- [ ] [可验证条件 1]
- [ ] [可验证条件 2]
限制：[约束条件]
Show full SKILL.md (314 more words)Show less
Phase 3 — Verify the goal

Before presenting the final goal, self-check:

  • Can an agent read the completion criteria and unambiguously decide "done" vs "not done"?
  • Is every criterion observable without human judgment? (No "looks good", "feels right")
  • Are the constraints specific enough to prevent scope creep?
  • Is the context sufficient for the agent to start working without asking "where" or "how"?

If any check fails in standalone mode, go back to Phase 1 and ask the user to clarify that specific point. In compiled-handoff mode, report the source as not agent-ready and name the missing evidence instead of asking a new planning question.

Phase 4 — Deliver

In standalone mode, present the final goal and end with:

🎯 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

下面两个示例里的仓库名、目录结构和文件路径都是占位符，不代表任何真实项目的约定。真正产出的 goal 必须写目标仓库当前的真实路径，不要照抄这里的形状。

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: 当前工作仓库
  • 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：<一句话说明这个仓库是什么>
- 设计 spec：<仓库内的设计文档>
Example 2: UI redesign

User: "帮我写个 goal，重做这个页面"

Clarified:

  • Task: 用 shadcn 组件库重做目标页面
  • 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 组件库重做目标页面

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 API 客户端目录下的任何文件
- 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：<页面组件文件>
- UI 组件：<组件库入口文件>
- 样式：<全局样式入口>

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. Approved evidence 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".

© tt-a1i, 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 3 other files in skills/engineering/goal-crafter of tt-a1i/matt-skills-with-to-goal.

  • SKILL.md
  • .gitignore
  • README.md
  • agents/openai.yaml

Open the folder on GitHubat commit d09351e

Compare with similar skills

Goal Crafter next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Goal Crafter compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Goal Crafter this skilltt-a1i/matt-skills-with-to-goal184—~1.8kAutomated safety check: PassMIT
Verifyasgeirtj/system_prompts_leaks69k—~3kAutomated safety check: PassCC0-1.0
Goalscodewhale-hq/Codewhale41k—~273Automated safety check: PassMIT
Verify Thiscursor/plugins11k2 repos~693Automated safety check: PassNone
Verify Releaseopenclaw/openclaw392k—~2.4kAutomated safety check: PassMIT
Verifycodewhale-hq/Codewhale41k—~156Automated safety check: PassMIT

Similar skills

  • Verify

    asgeirtj/system_prompts_leaks

    Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck.

    69k GitHub stars~3k tokensUpdated yesterday
    Testing & QAAuto-check passed

  • Goals

    codewhale-hq/Codewhale

    Set, review, and update the user's goals. An agent skill from codewhale-hq/Codewhale.

    41k GitHub stars~273 tokensUpdated today
    Auto-check passed

  • Verify This

    cursor/plugins

    Official

    Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.

    11k GitHub starsUsed in 2 repos~693 tokens
    Auto-check passed

  • Verify Release

    openclaw/openclaw

    Verify regular or extended-stable OpenClaw releases against the exact publication surfaces, workflow identities, package provenance, smoke tests, and live Gateway behavior expected for that release…

    392k GitHub stars~2.4k tokensUpdated today
    Testing & QAAuto-check passed

  • Verify

    codewhale-hq/Codewhale

    Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.

    41k GitHub stars~156 tokensUpdated today
    Testing & QAAuto-check passed

  • Verify Before Completion

    Yeachan-Heo/oh-my-claudecode

    Has the agent prove that a feature, fix or refactor works, using existing tests first, then narrow commands and manual checks, and report only what was actually verified.

    40k GitHub stars~277 tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

More from tt-a1i/matt-skills-with-to-goal

  • Roundtable

    tt-a1i/matt-skills-with-to-goal

    Convene a roundtable of sub-agents that debate a decision or proposal from opposing perspectives — parallel independent statements, anonymous cross-review, then a chaired verdict reporting consensus…

    184 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

  • Spec Executor

    tt-a1i/matt-skills-with-to-goal

    Execute approved, bounded work in an isolated implementation conversation and return a structured evidence receipt.

    184 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

  • To Goal

    tt-a1i/matt-skills-with-to-goal

    Turn approved planning evidence or partially completed work into a portable, verifiable execution goal.

    184 GitHub stars~2.7k tokensUpdated yesterday
    Auto-check passed

  • Execute Spec In Fork

    tt-a1i/matt-skills-with-to-goal

    Orchestrate approved, bounded work through a same-directory Codex App fork: create and name the execution task, ask it to run spec-executor, route decisions through Codex Task Messenger, validate…

    184 GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

  • Handoff

    tt-a1i/matt-skills-with-to-goal

    Compact the current conversation into a portable handoff document, with an optional live clarification path for compatible Codex tasks.

    184 GitHub stars~504 tokensUpdated yesterday
    Auto-check passed

Questions about Goal Crafter

What does Goal Crafter do?

Craft verifiable, tight goal prompts for AI coding agents (Claude Code /goal, Codex Automations, Pi), either from a standalone task interview or from an already-approved to-goal handoff. Goal Crafter is an agent skill from tt-a1i/matt-skills-with-to-goal. Craft verifiable, tight goal prompts for AI coding agents (Claude Code /goal, Codex Automations, Pi), either from a standalone task interview or from an already-approved to-goal handoff.

When should I use Goal Crafter?

Goal Crafter fits situations like: the user says 给我一个 goal 提示词; 我想让 agent 自动做 X; asks to turn a task into a self-running loop.

How do I install Goal Crafter in Claude Code?

Run `npx skills add tt-a1i/matt-skills-with-to-goal --skill goal-crafter -a claude-code`. Or copy the skill folder (skills/engineering/goal-crafter in tt-a1i/matt-skills-with-to-goal) into .claude/skills/goal-crafter in your project. Claude Code loads it when a task matches its description.

How do I install Goal Crafter in Codex?

Run `npx skills add tt-a1i/matt-skills-with-to-goal --skill goal-crafter -a codex`. Or copy the skill folder (skills/engineering/goal-crafter in tt-a1i/matt-skills-with-to-goal) into .agents/skills/goal-crafter in your project. Codex loads it when a task matches its description.

Can I use Goal Crafter in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tt-a1i/matt-skills-with-to-goal --skill goal-crafter -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/goal-crafter, .gemini/skills/goal-crafter, .github/skills/goal-crafter and .opencode/skills/goal-crafter in your project.

What does Goal Crafter need to run?

Going by SKILL.md and its folder, Goal Crafter needs the command-line tools its instructions call (tsc, npm and git).

Does Goal Crafter access the network?

SKILL.md contains no URLs. Its commands use npm and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Goal Crafter safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Goal Crafter use?

Goal Crafter is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Goal Crafter use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Goal Crafter?

Skills that share tags, products or a category with Goal Crafter: Verify (asgeirtj/system_prompts_leaks, 69k stars), Goals (codewhale-hq/Codewhale, 41k stars), Verify This (cursor/plugins, 11k stars) and Verify Release (openclaw/openclaw, 392k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Goal Crafter?

tt-a1i (a GitHub user) maintains it in tt-a1i/matt-skills-with-to-goal, which has 184 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 10, 2026.

Source: tt-a1i/matt-skills-with-to-goal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.