using-superpowers
Standardize Skill Use in AI Agents
Assistants can miss relevant skills or apply them late, which creates inconsistent workflows. This skill gives Claude, Codex, and Claude Code a repeatable process for checking, invoking, and prioritizing skills.
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "using-superpowers" from https://skillstore.io/skills/sickn33-using-superpowers.md and its manifest at https://skillstore.io/api/skills/sickn33-using-superpowers/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "using-superpowers". User asks the assistant to fix a failing test suite.
Expected outcome:
The assistant checks for debugging and testing skills before inspecting files, uses the relevant process skill first, then applies domain-specific guidance.
Using "using-superpowers". User asks the assistant to build a small frontend feature.
Expected outcome:
The assistant checks for planning or design skills, invokes the relevant process skill, then follows implementation guidance for the frontend work.
Using "using-superpowers". User asks why the assistant skipped the skill check.
Expected outcome:
The assistant identifies the missed check, names the applicable skill, and restarts the workflow using the documented priority rules.
Security Audit
High RiskThe two static external command findings are false positives caused by markdown inline code and a DOT diagram. No executable code, shell invocation, network access, or filesystem operation is present. A high-severity semantic finding remains because the skill contains coercive prompt instructions that try to control tool use and override normal assistant discretion.
Confirmed security concerns (1)
Risk Factors
⚙️ External commands (2)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/sickn33-using-superpowers/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/sickn33-using-superpowers?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/sickn33-using-superpowers?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-using-superpowers/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/sickn33-using-superpowers.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
sickn33. (2026). using-superpowers security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-using-superpowers/audits/4BibTeX citation
@techreport{sickn33-sickn33-using-superpowers-2026,
author = {sickn33},
title = {using-superpowers security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/sickn33-using-superpowers/audits/4},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "using-superpowers security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "sickn33"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/sickn33-using-superpowers/audits/4"
identifiers:
- type: other
value: "skillstore:sickn33-using-superpowers:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
8 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
dyai2025-using-superpowers
2026-08-21
zhanlincui-using-superpowers
2026-08-21
obra-using-superpowers
2026-08-21
codingcossack-using-superpowers
2026-08-21
sickn33-using-superpowers
2026-08-21
davila7-using-superpowers
2026-08-21
cycleaddict-using-superpowers
2026-08-21
cygnusfear-using-superpowers
2026-08-21
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Start Skill-Aware Sessions
An AI operations lead can require assistants to check available skills before work begins.
Coordinate Development Tasks
A software engineer can guide an assistant to combine process skills and implementation skills in the right order.
Review Process Compliance
A prompt engineer can compare assistant behavior against a documented skill invocation workflow.
Try These Prompts
Before you answer, check whether any available skill applies to my task. If one applies, use it and state which one you used.
I am starting a development task. Apply the skill selection workflow, choose any relevant process skill first, then proceed with implementation guidance.
Several skills may apply to this request. Use the priority rules from using-superpowers, explain your chosen order, and continue with the task.
Review this assistant workflow for missed skill checks, late invocations, or priority mistakes. Recommend a corrected sequence using the skill rules.
Best Practices
- Keep skill checks brief and tied to the user's current task.
- Use process skills before implementation skills when both apply.
- State which skill is being used and continue with the requested work.
Avoid
- Skipping a skill check because the request looks simple.
- Using memory of an older skill instead of loading the current skill.
- Letting skill instructions override higher-priority safety or platform rules.