craft-goal
協助撰寫、縮短、驗證、整理可交給下一個 agent session(Claude Code 或 Codex)執行的 handoff prompt,含 Codex app 的 `/goal`。當使用者要寫 `/goal`、準備 handoff prompt、把模糊任務整理成可執行 goal、要依任務性質與剩餘…
Skill by ChiTienHsieh
Chalk Labs
Need help deploying craft-goal?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/chitienhsieh-craft-goal
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, research, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/craft-goal
What's inside
- Skill name
craft-goal- Description
- 協助撰寫、縮短、驗證、整理可交給下一個 agent session(Claude Code 或 Codex)執行的 handoff prompt,含 Codex app 的 `/goal`。當使用者要寫 `/goal`、準備 handoff prompt、把模糊任務整理成可執行 goal、要依任務性質與剩餘 quota 決定交給 CC 還是 Codex、需要 clarification、research、task spec file、side-effect boundary、或 quick smoke test 時使用。
- License
- unknown
- Instructions
- 145 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (3)
- SKILL.md
- openai.yaml · agents/
- check_goal_prompt.py · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from ChiTienHsieh/dotfiles
- 0.598score
html-artifacts
ChiTienHsieh
Create self-contained HTML artifacts for plans, reviews, reports, research syntheses, diagrams, prototypes, dashboards, custom editors, and other work…
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
fetch-known-url
ChiTienHsieh
把白名單內、已支援的網址抓下來,解析成 AI agent 讀得懂的檔案。使用者要抓取、閱讀、封存、擷取、摘要已支援的網址,或把它轉成可讀檔案時使用。支援 ChatGPT 與 claude.ai 的分享對話網址,以及 YouTube 字幕(附明確的反爬蟲退路規則);X / Twitter 網址轉給 gu-log 的…
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
level-up
ChiTienHsieh
使用者要求分關教學、逐題推進或 level-up 教練時使用;也負責實作前 preflight、實作後 debrief、合併前測驗與決策教練。中大型任務、不熟的任務,或改到資料模型、架構、使用者看得到的行為、guardrail/SSOT 檔案時,自行先跑 preflight(見…
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
tmux-orchestration
ChiTienHsieh
Use only when the current human explicitly asks the agent to use tmux or explicitly requests a visible interactive CLI session inside tmux.
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
delegate
ChiTienHsieh
規劃或把實作、研究、review 委派給另一個 agent 時使用:決定交給哪個 provider 或 worker、回答 quota / rate-limit / usage-reset 問題,或以 headless 方式跑 codex、grok、claude CLI(codex exec、grok…
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
chill
ChiTienHsieh
Run the chill workflow when the user explicitly asks for chill mode, `/chill`, proofreading, a vibe check, softer wording, or a more relaxed zh-TW…
SkillAFreshness: A★ 2Claude Code +9 - 0.592score
learn-my-voice
ChiTienHsieh
使用者明確呼叫時,透過持續共同編輯 Markdown、探索分支的階段性版本與 Git 追蹤紀錄,學習並套用使用者的寫作聲音。
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
trim
ChiTienHsieh
精簡 skill、prompt、playbook、AGENTS.md/CLAUDE.md 等 agent 指令:刪掉沒作用的句子,把難讀的句子改寫成白話。程式碼改用 `/simplify`。
SkillAFreshness: A★ 2Claude Code +9 - 0.554score
playwright-cli
ChiTienHsieh
Use for browser automation: navigate pages, click, type, fill forms, take screenshots, test web apps, or extract page data.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
wife-pdf
ChiTienHsieh
Create plain zh-TW Typst/PDF decision documents for non-technical family readers.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
daily-loop
ChiTienHsieh
Mine recent Claude Code and Codex transcripts, identify durable workflow improvements, and ask the user which proposals to apply.
SkillBFreshness: B★ 2Claude Code +9 - 0.554score
tidy-workspace
ChiTienHsieh
Tidy and synchronize Git workspaces without ending the session.
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 5
- Last commit (this folder)
- Oct 5, 2026 (25 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/ChiTienHsieh/dotfiles
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ChiTienHsieh
- 0.598score
html-artifacts
ChiTienHsieh
Create self-contained HTML artifacts for plans, reviews, reports, research syntheses, diagrams, prototypes, dashboards, custom editors, and other work…
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
fetch-known-url
ChiTienHsieh
把白名單內、已支援的網址抓下來,解析成 AI agent 讀得懂的檔案。使用者要抓取、閱讀、封存、擷取、摘要已支援的網址,或把它轉成可讀檔案時使用。支援 ChatGPT 與 claude.ai 的分享對話網址,以及 YouTube 字幕(附明確的反爬蟲退路規則);X / Twitter 網址轉給 gu-log 的…
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
level-up
ChiTienHsieh
使用者要求分關教學、逐題推進或 level-up 教練時使用;也負責實作前 preflight、實作後 debrief、合併前測驗與決策教練。中大型任務、不熟的任務,或改到資料模型、架構、使用者看得到的行為、guardrail/SSOT 檔案時,自行先跑 preflight(見…
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
tmux-orchestration
ChiTienHsieh
Use only when the current human explicitly asks the agent to use tmux or explicitly requests a visible interactive CLI session inside tmux.
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
delegate
ChiTienHsieh
規劃或把實作、研究、review 委派給另一個 agent 時使用:決定交給哪個 provider 或 worker、回答 quota / rate-limit / usage-reset 問題,或以 headless 方式跑 codex、grok、claude CLI(codex exec、grok…
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
chill
ChiTienHsieh
Run the chill workflow when the user explicitly asks for chill mode, `/chill`, proofreading, a vibe check, softer wording, or a more relaxed zh-TW…
SkillAFreshness: A★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get craft-goal running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
craft-goal skill. Agent Mart. https://agentmart.dev/skills/chitienhsieh-craft-goal (last updated 2026-10-24)