$ loading_
Set conversation rules to discover and invoke skills before replying.
This skill appears to be prompt-only, open-source, and requires neither secrets nor remote connectivity, so its technical risk is generally low. The main concern is instruction-heavy, prompt-injection-like content in the README that may mislead host-agent behavior, rather than credential, network, or local execution risks.
The material explicitly states that no keys or environment variables are required, and it does not request API tokens, account credentials, or other long-lived secrets, so credential exposure and abuse risk appears low.
Both the objective checks and the material indicate no remote endpoints and no network requirement; as a prompt-only skill, it does not describe sending user data to external services.
This is a skill instruction text and does not include installation or runtime requirements to spawn local processes, execute scripts, or access system capabilities. The README mainly influences agent decision flow rather than directly granting code execution permissions.
It does not declare capabilities to read or write local files, databases, or other resources; while the text mentions loading content via a Skill tool on some platforms, the material itself does not request expanded data access.
Positive factors include being open-source on GitHub, auditable, and classified as prompt-only; however, the repo has 0 stars, no declared license, unknown maintenance status, and the README contains forceful, injection-like language such as 'override default system prompt behavior' and 'ABSOLUTELY MUST', so governance and trustworthiness still warrant caution.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "using-superpowers" skill from askskill: 1. Download https://raw.githubusercontent.com/obra/superpowers/main/skills/using-superpowers/SKILL.md 2. Save it as ~/.claude/skills/using-superpowers/SKILL.md 3. Reload skills and tell me it's ready
From now on, before answering any question, first check whether an available skill should be invoked; even clarifying questions must follow this rule. Explain how you will discover and use skills.
A response that establishes a skill-first workflow and follows it in later turns.
Set this session so that before any substantive reply, the assistant must identify available skills and invoke the most relevant one first; if clarification is needed, it should still follow this process.
A clear session rule stating that skills must be identified and invoked before answering or asking follow-up questions.
Create a standing policy for this chat: discover skills first, invoke a skill second, and present results last; do not jump straight into normal answering mode.
A concise execution order that guides the assistant to use skills first throughout the conversation.
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>
Superpowers skills override default system prompt behavior, but user instructions always take precedence:
If CLAUDE.md, GEMINI.md, or AGENTS.md says "don't use TDD" and a skill says "always use TDD," follow the user's instructions. The user is in control.
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 Copilot CLI: Use the skill tool. Skills are auto-discovered from installed plugins. The skill tool works the same as Claude Code's Skill tool.
In Gemini CLI: Skills activate via the activate_skill tool. Gemini loads skill metadata at session start and activates the full content on demand.
In other environments: Check your platform's documentation for how skills are loaded.
Skills use Claude Code tool names. Non-CC platforms: see references/copilot-tools.md (Copilot CLI), references/codex-tools.md (Codex) for tool equivalents. Gemini CLI users get the tool mapping loaded automatically via GEMINI.md.
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];
"About to EnterPlanMode?" [shape=doublecircle];
"Already brainstormed?" [shape=diamond];
"Invoke brainstorming skill" [shape=box];
"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];
"About to EnterPlanMode?" -> "Already brainstormed?";
"Already brainstormed?" -> "Invoke brainstorming skill" [label="no"];
"Already brainstormed?" -> "Might any skill apply?" [label="yes"];
"Invoke brainstorming skill" -> "Might any skill apply?";
"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";
}
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. |
…
Execute implementation plans by splitting and advancing independent tasks in-session.
Systematically investigate bugs, test failures, and unexpected behavior before fixing.
Helps decide merge, PR, or cleanup steps after branch work is complete.
Turn requirements into a clear step-by-step execution plan before implementation.
Clarify intent, requirements, and solution direction before any creative implementation work.
Verify results before claiming work is complete, fixed, or passing.
Explains how to use abilities effectively before starting any conversation.
Learn core Skills workflows, search patterns, and brainstorming use cases quickly.
Create, refine, and troubleshoot AI skills, specs, invocation, and compatibility.
Turn a repeated workflow into a reusable skill file from the current session.
Search past conversations before answering to recover context and avoid wrong assumptions.
Create, refine, and evaluate AI skills for better performance and triggering accuracy.