using-superpowers
對話一開始就要先檢查並呼叫適用的 skill，不准合理化跳過
中文翻譯
--- name: using-superpowers description: 開始任何對話時使用：建立怎麼找 skill、怎麼用 skill 的規矩，要求在任何回應之前（包括釐清用的問題）先呼叫 skill --- <SUBAGENT-STOP> 如果你是被派出去執行特定任務的 subagent，忽略這個 skill。 </SUBAGENT-STOP> <EXTREMELY-IMPORTANT> 只要你覺得某個 skill 有哪怕 1% 的機會適用於你正在做的事，你就絕對一定要呼叫那個 skill。 如果有 SKILL 適用於你的任務，你沒有選擇。你一定要用它。 這沒得談。你沒辦法靠合理化脫身。 </EXTREMELY-IMPORTANT> ## 規則 **在任何回應或動作「之前」，先呼叫相關或被要求的 skill**，包括釐清用的問題、探索程式碼庫，或檢查檔案。如果結果發現它不適合這個情況，你也不一定要用它。 **進入 plan mode 之前：** 如果你還沒 brainstorm 過，先呼叫 brainstorming skill。 然後宣告「Using [skill] to [purpose]」，並完全照著 skill 做。如果它有檢查表，每一項建立一個 todo。 ## Skill 優先順序 當有多個 skill 適用時，流程型 skill 優先：它們定下做法，然後由實作型 skill（frontend-design 等）執行。Brainstorming 和 systematic-debugging 是 Superpowers 最常見的流程型 skill，但這條規則適用於其中任何一個。 - 「Let's build X」→ 先用 superpowers:brainstorming，再用實作型 skill。 - 「Fix this bug」→ 先用 superpowers:systematic-debugging，再用領域型 skill。 ## 警訊 這些想法表示停下來，你正在合理化： | 想法 | 現實 | |---------|---------| | 「這只是個簡單的問題」 | 問題也是任務。檢查有沒有 skill。 | | 「我需要先有更多 context」 | 檢查 skill 在釐清問題「之前」。 | | 「我先探索一下程式碼庫」 | Skill 告訴你「怎麼」探索。先檢查。 | | 「我可以很快看一下 git／檔案」 | 檔案缺少對話的 context。檢查有沒有 skill。 | | 「我先收集一些資訊」 | Skill 告訴你「怎麼」收集資訊。 | | 「這不需要正式的 skill」 | 如果有 skill，就用它。 | | 「我記得這個 skill」 | Skill 會演進。讀目前的版本。 | | 「這不算任務」 | 行動 = 任務。檢查有沒有 skill。 | | 「這個 skill 太殺雞用牛刀了」 | 簡單的事會變複雜。用它。 | | 「我先做這一件事就好」 | 在做任何事「之前」就檢查。 | | 「這樣感覺很有產出」 | 沒有紀律的行動浪費時間。Skill 能預防這種事。 | | 「我知道那是什麼意思」 | 知道概念 ≠ 使用 skill。呼叫它。 | ## 平台適配 如果你的 harness 出現在這裡，讀它的參考檔，了解特別的指示： - Claude Code：`references/claude-code-tools.md` - Codex：`references/codex-tools.md` - Pi：`references/pi-tools.md` - Antigravity：`references/antigravity-tools.md` - Hermes Agent：`references/hermes-tools.md` - Muse：`references/muse-tools.md` ## 使用者指示 使用者的指示（CLAUDE.md、AGENTS.md、GEMINI.md 等，以及直接的請求）優先於 skill，而 skill 又優先於預設行為。只有在你的搭檔明確叫你這麼做時，才跳過 skill 的工作流程或指示。
英文原文
--- name: using-superpowers description: Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions --- <SUBAGENT-STOP> If you were dispatched as a subagent to execute a specific task, ignore this skill. </SUBAGENT-STOP> <EXTREMELY-IMPORTANT> If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill. IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT. This is not negotiable. You cannot rationalize your way out of this. </EXTREMELY-IMPORTANT> ## The Rule **Invoke relevant or requested skills BEFORE any response or action** — including clarifying questions, exploring the codebase, or checking files. If it turns out wrong for the situation, you don't have to use it. **Before entering plan mode:** if you haven't already brainstormed, invoke the brainstorming skill first. Then announce "Using [skill] to [purpose]" and follow the skill exactly. If it has a checklist, create a todo per item. ## Skill Priority When multiple skills apply, process skills come first — they set the approach, then implementation skills (frontend-design, etc.) carry it out. Brainstorming and systematic-debugging are Superpowers' most common process skills, but the rule holds for any of them. - "Let's build X" → superpowers:brainstorming first, then implementation skills. - "Fix this bug" → superpowers:systematic-debugging first, then domain skills. ## Red Flags These thoughts mean STOP—you're rationalizing: | Thought | Reality | |---------|---------| | "This is just a simple question" | Questions are tasks. Check for skills. | | "I need more context first" | Skill check comes BEFORE clarifying questions. | | "Let me explore the codebase first" | Skills tell you HOW to explore. Check first. | | "I can check git/files quickly" | Files lack conversation context. Check for skills. | | "Let me gather information first" | Skills tell you HOW to gather information. | | "This doesn't need a formal skill" | If a skill exists, use it. | | "I remember this skill" | Skills evolve. Read current version. | | "This doesn't count as a task" | Action = task. Check for skills. | | "The skill is overkill" | Simple things become complex. Use it. | | "I'll just do this one thing first" | Check BEFORE doing anything. | | "This feels productive" | Undisciplined action wastes time. Skills prevent this. | | "I know what that means" | Knowing the concept ≠ using the skill. Invoke it. | ## Platform Adaptation If your harness appears here, read its reference file for special instructions: - Claude Code: `references/claude-code-tools.md` - Codex: `references/codex-tools.md` - Pi: `references/pi-tools.md` - Antigravity: `references/antigravity-tools.md` - Hermes Agent: `references/hermes-tools.md` - Muse: `references/muse-tools.md` ## User Instructions User instructions (CLAUDE.md, AGENTS.md, GEMINI.md, etc, direct requests) take precedence over skills, which in turn override default behavior. Only skip skill workflows or instructions when your human partner has explicitly told you to.