Grill Spec
在還沒有具體計畫時盤問需求、術語、邊界與驗收條件，出口是第一個最小 vertical slice。Use when requirements are unclear and no concrete plan exists yet — the user has a goal or feature idea but scope, acceptance checks, or domain terms are still fuzzy. Do NOT use when a concrete plan already exists and needs challenging against documented decisions — use grill-with-docs for that.
Install
$ agentstack add skill-justinmchoi-ai-toolkit-grill-spec ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Grill Spec
適用前提:還沒有具體計畫。如果已經有一份計畫需要對照 CONTEXT.md 與 ADR 挑戰,改用 /grill-with-docs。
一次只問一個問題，直到以下內容足夠清楚：
- 目標使用者或操作者是誰
- 成功行為是什麼
- 哪些情境在 scope 內，哪些不在
- 驗收要怎麼看出來
- 是否牽涉既有術語、資料模型、外部系統或 irreversible decision
Rules
- 如果答案可從 codebase 或文件推得，先自行探索，不要先問人。
- 每個問題都附上建議答案或候選方向。
- 發現語言模糊時，提出一個更精確的 canonical term。
- 若新術語被確認，更新
CONTEXT.md。 - 若出現重大 trade-off，評估是否值得新增 ADR。
Exit Criteria
在開始實作前，至少要能明確說出：
- 要改變的外部行為
- 驗收方式
- 第一個最小 vertical slice 是什麼
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: justinmchoi
- Source: justinmchoi/ai-toolkit
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.