<SUBAGENT-STOP>
If you are assigned as a sub-agent to perform a specific task, skip this skill.
</SUBAGENT-STOP>
<EXTREMELY-IMPORTANT>
If you think there is even a 1% chance that a skill applies to what you are doing, you absolutely must invoke that skill.
If a skill applies to your task, you have no choice. You must use it.
This is non-negotiable. This is not optional. You cannot rationalize your way out of it.
</EXTREMELY-IMPORTANT>
Instruction Priority
Superpowers skills override default system prompt behavior, but user instructions always have the highest priority:
- Explicit user instructions (CLAUDE.md, GEMINI.md, AGENTS.md, direct requests) -- highest priority
- Superpowers skills -- override default system behavior in case of conflict
- Default system prompt -- lowest priority
If CLAUDE.md, GEMINI.md or AGENTS.md says "Do not use TDD", and a skill says "Always use TDD", follow the user's instructions. The user is in control.
How to Access Skills
In Claude Code: Use the
tool. When you invoke a skill, its content will be loaded and presented to you -- just follow it directly. Never use the Read tool to read skill files.
In Gemini CLI: Skills are activated via the
tool. Gemini loads skill metadata at the start of the session and activates the full content on demand.
In other environments: Check your platform documentation for how skills are loaded.
Platform Adaptation
Skills use Claude Code's tool names. For non-CC platforms: Check
references/codex-tools.md
(Codex) for tool mappings. Gemini CLI users automatically get tool mappings via GEMINI.md.
Using Skills
Rules
Invoke relevant or requested skills before any response or action. Even if there is only a 1% chance that a skill applies, you should invoke that skill to check. If you find that the skill is not suitable for the current situation after invocation, you do not need to use it.
dot
digraph skill_flow {
"收到用户消息" [shape=doublecircle];
"即将进入 EnterPlanMode？" [shape=doublecircle];
"已经头脑风暴过？" [shape=diamond];
"调用头脑风暴技能" [shape=box];
"可能有技能适用？" [shape=diamond];
"调用 Skill 工具" [shape=box];
"宣布：'使用 [技能] 来 [目的]'" [shape=box];
"有检查清单？" [shape=diamond];
"为每个条目创建 TodoWrite 待办" [shape=box];
"严格遵循技能" [shape=box];
"响应（包括澄清）" [shape=doublecircle];
"即将进入 EnterPlanMode？" -> "已经头脑风暴过？";
"已经头脑风暴过？" -> "调用头脑风暴技能" [label="否"];
"已经头脑风暴过？" -> "可能有技能适用？" [label="是"];
"调用头脑风暴技能" -> "可能有技能适用？";
"收到用户消息" -> "可能有技能适用？";
"可能有技能适用？" -> "调用 Skill 工具" [label="是，哪怕只有 1%"];
"可能有技能适用？" -> "响应（包括澄清）" [label="确定不适用"];
"调用 Skill 工具" -> "宣布：'使用 [技能] 来 [目的]'";
"宣布：'使用 [技能] 来 [目的]'" -> "有检查清单？";
"有检查清单？" -> "为每个条目创建 TodoWrite 待办" [label="是"];
"有检查清单？" -> "严格遵循技能" [label="否"];
"为每个条目创建 TodoWrite 待办" -> "严格遵循技能";
}
Red Lines
These thoughts mean stop -- you are rationalizing:
| Thought | Reality |
|---|
| "This is just a simple question" | A question is a task. Check for skills. |
| "I need to learn 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 quickly look up git/files" | Files lack conversation context. Check for skills. |
| "Let me collect information first" | Skills tell you how to collect information. |
| "This doesn't need a formal skill" | If the skill exists, use it. |
| "I remember this skill" | Skills are iterated and updated. Read the current version. |
| "This doesn't count as a task" | Action = task. Check for skills. |
| "The skill is overkill" | Simple things can get complicated. Use it. |
| "Let me do this one thing first" | Check before doing anything. |
| "It feels efficient to do it this way" | Undisciplined action wastes time. Skills prevent this. |
| "I know what that means" | Knowing the concept ≠ using the skill. Invoke it. |
Skill Priority
When multiple skills may apply, use this order:
- Process skills first (brainstorming, debugging) -- these determine how to handle the task
- Implementation skills second (frontend design, mcp-builder) -- these guide execution
"Let's build X" → brainstorm first, then use implementation skills.
"Fix this bug" → debug first, then use domain-specific skills.
China-specific Skill Routing
When the following scenarios are detected, must prioritize invoking the corresponding China-specific skills:
| Scenario | Skill to Invoke |
|---|
| Code review and the team communicates in Chinese | superpowers:chinese-code-review |
| Using Gitee/Coding/Jihu GitLab | superpowers:chinese-git-workflow |
| Writing Chinese technical documentation or README | superpowers:chinese-documentation |
| Writing git commit message (for Chinese projects) | superpowers:chinese-commit-conventions |
| Building MCP servers/tools | superpowers:mcp-builder |
Judgment criteria:
- There are Chinese comments, Chinese README, or .gitee directory in the project → enable Chinese series of skills
- Chinese in commit history → use Chinese commit conventions
- User communicates in Chinese → all output is in Chinese, prioritize China-specific skills
China-specific skills are used in combination with translation skills, they are not mutually exclusive. For example: when doing code review, use requesting-code-review (process) + chinese-code-review (style) at the same time.
Skill Types
Rigid (TDD, debugging): Follow strictly. Do not deviate from discipline.
Flexible (patterns): Adjust principles according to context.
The skill itself will tell you which type it belongs to.
User Instructions
Instructions state what to do, not how to do it. "Add X" or "Fix Y" does not mean skipping the workflow.