16 關免費主線已開放 · Skill 池內測期免費領取 從第一關開始
菜鸟skill
菜鸟skill
新手學AI
部署網站一條龍自媒體創作一條龍職場提效一條龍商業變現一條龍
Skills 定價
語言:
English 繁體中文 日本語 Español
真實產出 · 已記錄檢查 真實樣例 · Markdown
30 秒看完完整流程

TrailNote — launch checklist

Public fictional practice project (launch-a#/fixture). Project: TrailNote (launch-a#/project). Deadline: 2026-11-05 (launch-a#/deadline); time of day and timezone are unknown.

The recorded statuses and checks below come only from the consumed handoff. The underlying work has not been independently verified. Proposed actions remain pending and were not executed.

IDItemOwnerRecorded statusRecorded checkProposed next action (pending)Source
A1landing page copyeditorreadysource claims reviewedNone proposed from this recorded check.launch-a#/items/0
A2product screenshotsdesignerdraftmobile crop still requiredComplete the mobile crop.launch-a#/items/1
A3download packagebuilderreadyfiles compared with manifestNone proposed from this recorded check.launch-a#/items/2
A4checkoutbuildernot-testedno real payment test yetObtain a real payment-test result; no test was performed here.launch-a#/items/3

Unknowns: deadline time/timezone (launch-a#/deadline) and the real payment-test result (launch-a#/items/3/check). Neither is filled in or treated as completed. These unknowns do not prevent producing this checklist.

Provenance: consumed L:/project-folder-2/skillcube/studio/multi-agent/demo/output/worker-a/handoff-a.json; saved result L:/project-folder-2/skillcube/studio/multi-agent/demo/output/worker-b/checklist-a.md. This file records the checklist only; it is not launch approval or evidence that project work was executed.

樣例內容原樣呈現，僅做閱讀排版 下載完整樣例
運行方式 Codex 由你的 Agent 執行，模型用量由服務商計費
實測環境：
Codex · Windows
Agent／模型費用依供應商而定；額外服務與依賴詳見完整包。
Two Agent sessions or subagents

主線哪幾關用到它

Skill 是一把武器，配合新手主線實操，打通從「會玩」到「精通」的打怪升級全流程。

4-1 · 多个 agent 協作 →

帶著這次成果繼續: 連接外部世界（MCP） →

✓ 適合誰 (Good Fit)
  • 沿主線動手學習的 AI 新手
  • 從對應關卡開始；頁面瀏覽不會被當成任務完成。
⊗ 不適合誰 (Not For)
  • 超出本次任務的無人值守操作或未核准的帳號存取
✦ 你會得到 (What You Get)
  • 掌握任务拆分与交接物设计
  • 交接物有明确的名字、格式和完成標準
  • 下游没有追问就完成了任务

交付內容：完整 SKILL.md 規則文件 + 公開自測樣例。需要在你自己的 AI Agent 中運行。

怎麼開始？

Skill 是一份教 AI 完成任務的規則。

領取並安裝 ↑
1
提供手上的材料
把一个任务拆给两个 agent（或两个工作階段），用中间檔案交接完成。
2
讓 Agent 按規則完成
掌握任务拆分与交接物设计
3
打開並核對真實產出
交接物有明确的名字、格式和完成標準
發給你的 AI Agent

用 multi-agent 帶我完成這一關。缺少材料先問我，實際使用工具並儲存結果，再按關卡判據核對。

使用前了解 證據會標明實測範圍；模型與權限依你的 Agent 而異。解壓成功不等於已被 Agent 自動發現。 Agent／模型費用依供應商而定；額外服務與依賴詳見完整包。

從這裡開始使用

压缩包里是规则、参考库、脚本、真实产出和演示片，不只是一个提示词文件。

下載完整包（.zip） 下載 SKILL.md
  1. 打開 Codex 或 Claude Code，粘貼安裝提示詞。
  2. 讓 Agent 讀取並保存完整規則，確認安裝成功。
  3. 複製上方使用示例，換成你的素材開始運行。
手動安裝 · 查看完整 SKILL.md（81 行）

Codex：~/.agents/skills/multi-agent/SKILL.md
Claude Code：~/.claude/skills/multi-agent/SKILL.md

--- name: multi-agent description: Split a concrete task between two explicitly authorized Agents or sessions, exchange a self-contained file handoff and verify the downstream result against the original source. Use for the multi-agent level of the newbieskill main quest. --- # Two Agents, one usable handoff This is main quest level 4-1. The goal is a finished task whose downstream worker can proceed from a clear handoff file. ## Required authorization and inputs Use two Agents only when the user has asked for or authorized that collaboration. Otherwise explain the two-session method without silently creating agents. Use the actual delegated tool when available; two shell processes are not evidence of two model sessions. Keep the task bounded to the user's materials and requested result. ## Define the shared result Write the desired final file, the source material and the checks before splitting work. Choose a dependency boundary: the first worker structures reliable source facts, and the second produces the requested deliverable from that structure. Do not parallelize a dependent operation before its required input exists. Independent tasks can run concurrently when the available tools and authorization permit it. ## Design a self-contained handoff Specify a named file and a stable format, such as JSON with a short explanatory note. Include the task, source identifiers, confirmed facts, unknowns, constraints, requested output and acceptance criteria. Each material fact must identify a source field or row. Do not assume the downstream Agent can see the first worker's chat history. Do not give the workers your intended answer as though it were source evidence. ## First worker Read the source directly and preserve its numbers, statuses and dates. Normalize the material into the agreed handoff. Mark missing information as unknown; do not turn a draft into a finished feature. Check that the handoff is valid and contains what the second worker needs. Save the file before telling the second worker to continue. ## Second worker Read the handoff and the task's constraints. Produce the requested result using those facts only. If an essential input is missing, state the blocker rather than inventing it. Do not contact the original user or another person without separate authorization. Record which input file was consumed and where the result was saved. ## Reconcile the final result The coordinator compares the downstream result with the original source, not only with the intermediate handoff. Check arithmetic, row counts, exact statuses and unsupported claims. Confirm the output includes the requested actions and identifies unknowns. Preserve the original input, both handoffs/results and the actual session/tool receipts. ## Failure handling - Only one Agent is available: explain that this is a single-session rehearsal, not a passed collaboration test. - Empty source: ask for the missing material; no fabricated handoff facts. - Incomplete handoff: return a specific list of missing fields to the first worker. - Conflicting edits: keep worker output directories separate and let the coordinator reconcile. - Downstream result contradicts a source: correct it and repeat the affected check before shipping. ## Self-test tasks 1. Give worker one `inputs/launch-a.json`; worker two uses its handoff to make a launch checklist without reading the original file. Reconcile both against the original. 2. Repeat with `inputs/launch-b.json`, which has different statuses and an unknown date. No deadline or completed feature may be invented. 3. Give worker one `inputs/empty.json`; it must request missing source material rather than generating achievements. Failure means a missing provenance record, an unsupported claim, no actual second session or an unexplained essential downstream question. File-format validation alone cannot prove Agent collaboration. ## Route Return: `/path/multi-agent/`. Next: `/path/mcp-outside/` — connect one explicitly permitted external capability and make a real call. Useful branches include task planning, review and controlled worktree collaboration when those capabilities are actually installed. ## Rights Original newbieskill workflow. Personal and commercial work is permitted; do not resell the complete package.

新手常問 (FAQ)

有疑惑？先看看這裡，買前明明白白，用時順順利利。

怎麼開始？ +
下載完整 ZIP，把安裝提示交給 Agent，保留腳本與參考檔案。模型費用另計。
主線 Skill 免費嗎？ +
這些基礎主線 Skill 免費；進階工作室商品沿用各自定價。
菜鸟skill 會員

讓每一種重複，
都有解法。

一個訂閱，解鎖全部工作室 Skills。只需要這一款？也可以單獨獲取。

比較完整方案
免費 多个 agent 協作
免費獲取