- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add paperclipai/paperclip --skill qa-acceptance -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add paperclipai/paperclip --skill qa-acceptance -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add paperclipai/paperclip --skill qa-acceptance -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add paperclipai/paperclip --skill qa-acceptance -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/paperclipai/paperclip/tree/HEAD/packages/skills-catalog/catalog/bundled/quality/qa-acceptance來自發布者
Write acceptance criteria that a reviewer can run against the running app and decide pass or fail without asking the author. The criteria are the contract — automated tests cover correctness, QA covers feature-level behavior.
Each criterion is a single, independently-verifiable statement:
- **Given** <starting state>, **when** <action>, **then** <observable outcome>.
Example:
- **Given** a CSV export with 0 rows, **when** the user clicks Export, **then** the file downloads with only the header row and the UI shows "Exported 0 rows".
Avoid criteria that combine multiple whens or thens. Split them.
If a section is genuinely not applicable, write "N/A: " — do not silently omit.
Each criterion needs evidence on the verification pass:
"Looks good to me" without evidence is not a pass.
Return the validation plan with three sections:
The author owns turning failures into either fixes or accepted deferrals.
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
---name: qa-acceptancedescription: Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases…---# packages/skills-catalog/catalog/bundled/quality/qa-acceptance/SKILL.md常見問題
從發布者下載 packages/skills-catalog/catalog/bundled/quality/qa-acceptance/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/paperclipai/paperclip。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。