Using Superpowers Tianjin

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Security Scan

The skill's stated purpose matches its instructions, but its mandatory, global rule to always invoke and follow other skills before any response creates a meaningful safety risk (prompt-injection chaining, unnecessary expansion of attack surface, and denial-of-service-like behavior).

Purpose & Capability

Name/description (enforce using skills before responding) aligns with the SKILL.md content: the file explicitly requires checking/invoking skills before any response. No unrelated binaries, env vars, or config paths are requested.

Instruction Scope

The instructions mandate invoking any possibly-relevant skill (even for clarifying questions) and to 'follow [invoked] skill exactly'. This increases risk of malicious or buggy downstream skills being followed blindly (prompt-injection/exfiltration risk), can cause excessive skill-chaining, and prevents the agent from asking initial clarifying questions before checking skills.

Install Mechanism

Instruction-only skill with no install spec and no code files, so nothing is written to disk and no third-party packages are pulled in.

Credentials

The skill requests no environment variables, credentials, or config paths. It does not itself ask for secrets or external tokens.

Persistence & Privilege

The skill is user-invocable and not marked 'always:true'. However, its behavioral mandate (always check skills first) can materially increase the platform's autonomous surface area when combined with other skills that do have credentials or broad access. This combination raises the effective privilege/risk even though the skill itself requests none.

What to consider before installing

This skill is coherent with its stated goal, but it's risky: it forces the agent to check and then follow other skills before any reply, including clarifying questions. That makes the agent more likely to execute or follow malicious skills (prompt-injection), to chain many skills unnecessarily, and to behave in confusing or unusable ways. Before installing: consider whether you truly want this global mandate; prefer restricting it to explicit situations or require user confirmation before invoking other skills; ensure the platform enforces sandboxing and consent for skill actions, and audit the set of installed skills (especially those that hold credentials). If you rely on this skill, monitor agent activity and limit autonomous invocation of high-privilege skills. If you can, obtain information about the skill's author/trust signals or platform-level mitigations; that information would reduce the concern.

<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. This is not optional. You cannot rationalize your way out of this. </EXTREMELY-IMPORTANT>

How to Access Skills

In Claude Code: Use the Skill tool. When you invoke a skill, its content is loaded and presented to you—follow it directly. Never use the Read tool on skill files.

In other environments: Check your platform's documentation for how skills are loaded.

Using Skills

The Rule

Invoke relevant or requested skills BEFORE any response or action. Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.

digraph skill_flow {
    "User message received" [shape=doublecircle];
    "Might any skill apply?" [shape=diamond];
    "Invoke Skill tool" [shape=box];
    "Announce: 'Using [skill] to [purpose]'" [shape=box];
    "Has checklist?" [shape=diamond];
    "Create TodoWrite todo per item" [shape=box];
    "Follow skill exactly" [shape=box];
    "Respond (including clarifications)" [shape=doublecircle];

    "User message received" -> "Might any skill apply?";
    "Might any skill apply?" -> "Invoke Skill tool" [label="yes, even 1%"];
    "Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
    "Invoke Skill tool" -> "Announce: 'Using [skill] to [purpose]'";
    "Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
    "Has checklist?" -> "Create TodoWrite todo per item" [label="yes"];
    "Has checklist?" -> "Follow skill exactly" [label="no"];
    "Create TodoWrite todo per item" -> "Follow skill exactly";
}

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.

Skill Priority

When multiple skills could apply, use this order:

1. Process skills first (brainstorming, debugging) - these determine HOW to approach the task
2. Implementation skills second (frontend-design, mcp-builder) - these guide execution

"Let's build X" → brainstorming first, then implementation skills. "Fix this bug" → debugging first, then domain-specific skills.

Skill Types

Rigid (TDD, debugging): Follow exactly. Don't adapt away discipline.

Flexible (patterns): Adapt principles to context.

The skill itself tells you which.

User Instructions

Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.