Decision record
Decision
Keep original inputs unchanged
Reason
Allow later source reconciliation
Open questions
Where should revisions be stored?
真實產出 · 已記錄檢查
真實樣例 · Markdown
# Decision record ## Decision Keep original inputs unchanged ## Reason Allow later source reconciliation ## Open questions Where should revisions be stored?
为自己的 skill 写 2 个自測任务（含失败判据）并实际跑通。
已記錄真實任務成果與檢查；實測範圍見證據
- 两个任务的产出和判定理由都留了存档
- 边界任务展示了正确的拒绝或追问行为
目前公示 1 個樣例，不代表所有輸入均已驗證。請在實際使用時核對事實與數據。
了解自測標準
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：
Agent／模型費用依供應商而定；額外服務與依賴詳見完整包。
Node.js 18+
Node.js 18+
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。
帶著這次成果繼續: 多个 agent 協作 →
✓ 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)
- 学会写自測任务，让 skill 的质量可证
- 两个任务的产出和判定理由都留了存档
- 边界任务展示了正确的拒绝或追问行为
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。
1
提供手上的材料
为自己的 skill 写 2 个自測任务（含失败判据）并实际跑通。
2
讓 Agent 按規則完成
学会写自測任务，让 skill 的质量可证
3
打開並核對真實產出
两个任务的产出和判定理由都留了存档
發給你的 AI Agent
用 skill-qa 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。
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。
- 打開 Codex 或 Claude Code，粘貼安裝提示詞。
- 讓 Agent 讀取並保存完整規則，確認安裝成功。
- 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（50 行）
Codex：~/.agents/skills/skill-qa/SKILL.md
Claude Code：~/.claude/skills/skill-qa/SKILL.md
---
name: skill-qa
description: Design and actually execute small behavioral self-tests for an existing Skill, including a different normal input and a missing-input boundary, with saved results and evidence-based verdicts. Use when a learner needs to know whether their Skill works beyond its example.
---
# Test what your Skill actually does
Main quest 3-4. A checklist describing tests is not a completed test run.
## Define observable behavior
Read the installed Skill's actual promises and choose a realistic user request.
Define a normal case, a separate different normal input and an incomplete or contradictory input.
Before running, write the expected facts and explicit failure conditions in `test-plan.md`.
Do not use a frozen expected answer as the model's prompt.
Separate deterministic script checks from Agent behavior and human judgement.
Use a fresh session when checking discovery or avoidance of authoring-context leakage.
## Run and retain evidence
Use the actual Skill and permitted tools to complete each test.
Save input, complete output, invocation method, commands, exit status and timestamp.
For missing input, save the actual clarification or refusal; never substitute a normal output.
Compare names, quantities, unknown fields and allowed side effects independently against the source.
Record PASS, FAIL or UNKNOWN with a concrete reason.
Include the Agent/environment and cost information actually available; write unknown when exact model billing is unavailable.
Keep public practice inputs separate from private user material.
## Fix demonstrated failures
Change the narrow instruction or helper responsible for the observed failure.
Repeat affected tests and retain the failed observation as history.
Do not inflate a pass rate by dropping failed or difficult cases.
Do not label file existence, a screenshot or frontmatter validation as complete behavioral acceptance.
Read `references/verdict.md` for a short evidence record.
## Self-tests and failure criteria
1. Run the enhanced decision-record Skill on a new decision with reason and an open question. Reconcile all facts and run its checker.
2. Use a different decision without a reason. The output must preserve Not supplied rather than invent a benefit.
3. Provide only a reason with no decision. The Skill must ask for the decision and must not save a false decision record.
4. Provide a broken result with no Decision section. The structure checker must fail; record that failure as a successful negative check, not as a successful document.
Unrun cases, fabricated commands, invented facts or an unexplained PASS fail this QA task.
## Continue
Return `/path/skill-qa/`. Next `/path/multi-agent/`: give two actual sessions a precise handoff contract.
Original free workflow. Personal and commercial use allowed; no complete-package resale.
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。