# Apply Skills Before Agent Work

AI assistants can miss useful workflow guidance when tasks begin. This skill asks the agent to check available skills before acting.

## Install

```bash
npx skillstore add zhanlincui/using-superpowers
```

## Metadata

- Status: approved
- Slug: zhanlincui-using-superpowers
- Skillstore revision: r1
- Version status: missing
- Tree hash: 11b58012deac7f51df13b695d94bba7c0e05f88a71f90053dc4ef4a90e6fdb4e
- Author: ZhanlinCui
- GitHub username: ZhanlinCui
- License: MIT
- Repository: https://github.com/ZhanlinCui/Ultimate-Agent-Skills-Collection/tree/main/using-superpowers
- Ref: 88a205c7f635a966e31156313b590d59007c5caa
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: confirmation\_required
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands
- Quality score: 38
- Quality tier: warning
- Public page: https://skillstore.pages.dev/skills/zhanlincui-using-superpowers
- Manifest: https://skillstore.pages.dev/api/skills/zhanlincui-using-superpowers/manifest

## Capabilities

- Defines when agents should invoke relevant or requested skills.
- Explains skill access expectations for Claude Code and other environments.
- Provides a DOT flowchart for the skill selection sequence.
- Lists common rationalizations that should trigger a skill check.
- Describes priority order for process and implementation skills.
- Distinguishes rigid skills from flexible pattern skills.

## Use Cases

- Standardize Agent Startup: Create a repeatable first step for checking whether a task needs specialized workflow guidance.
- Train Skill Selection Habits: Teach assistants to consider process, debugging, and implementation skills before they begin work.
- Document Invocation Order: Give teams a shared reference for choosing process skills before implementation skills.

## Prompt Templates

### Check Relevant Skills

```
Use the using-superpowers skill to decide whether any available skill applies before you answer my request.
```

### Explain Skill Choice

```
Before starting, identify which skill applies, explain why it applies, and then follow its workflow.
```

### Prioritize Multiple Skills

```
If multiple skills could apply, choose the process skill first, then choose the implementation skill needed for the task.
```

### Audit Skill Discipline

```
Review this agent response and identify whether it checked applicable skills before acting. Suggest a corrected workflow if needed.
```

## Limitations

- It does not include executable automation or integrations.
- It does not list the specific skills available in an environment.
- Its absolute wording can conflict with higher-priority instructions.
- It depends on host support for loading and invoking skills.

## Best Practices

- Keep skill guidance subordinate to system, developer, and user instructions.
- Use the skill only where the host environment supports skill discovery.
- State the selected skill and purpose before substantial work begins.

## Anti Patterns

- Do not use absolute skill instructions to override platform security rules.
- Do not skip required clarification when no relevant skill exists.
- Do not block file review or audit commands required by the task.

## Security Audit

- Audited at: 2026-07-08T16:23:34.722\+00:00
- Summary: The two static external-command findings are false positives caused by inline Markdown backticks and a DOT diagram fence, not executable shell use. The skill does contain strong prompt-injection style instructions that try to override normal agent behavior and discourage reading skill files, so a semantic high-severity finding was added.

## Stats

- Views: 292
- Downloads: 584
- Favorites: 2
- Popularity score: 0