cybersecurity — Claude Code skill: what it does, how to install
The cybersecurity skill guides agents through application security work using principles and reference files. Use it when reviewing access controls, vulnerabilities, or security practices.
Apache-2.0 303 installs ★ 221 updated 2026-01-22
npx skills add omer-metin/skills-for-antigravity --skill cybersecurity -a claude-codeWhat cybersecurity does
The skill gives the agent a security-engineering role and sets out principles such as layered defenses, least privilege, and denying access when uncertain. Its scope includes authentication, authorization, encryption, vulnerabilities, secrets, and audits.
For new implementations, the agent is told to consult references/patterns.md; for diagnosis, references/sharp_edges.md; and for reviews, references/validations.md. Responses should follow those files, and the skill directs the agent to explain conflicts with their guidance. Make sure the reference files are available after installation, since the workflow depends on them.
What it helps with
- review code for XSS and SQL injection risks
- inspect authentication and authorization rules
- assess how secrets and passwords are handled
- check access rules against least privilege
Example prompts for the agent
- Review this code for XSS and SQL injection risks.
- Suggest an authorization design that grants only necessary access.
- Check how this project handles secrets and explain the risks.
How to install cybersecurity
1Skills CLI (Vercel)
npx skills add omer-metin/skills-for-antigravity --skill cybersecurity -a claude-code2Manually: put the files in place
~/.claude/skills/cybersecurity/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/cybersecurity/
1Skills CLI (Vercel)
npx skills add omer-metin/skills-for-antigravity --skill cybersecurity -a codex2Manually: put the files in place
.agents/skills/cybersecurity/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add omer-metin/skills-for-antigravity --skill cybersecurity -a cursor2Manually: put the files in place
.cursor/skills/cybersecurity/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install omer-metin/skills-for-antigravity skills/cybersecurity2Manually: put the files in place
.github/skills/cybersecurity/SKILL.md1Skills CLI (Vercel)
npx skills add omer-metin/skills-for-antigravity --skill cybersecurity -a gemini-cli2Platform CLI
gemini skills install https://github.com/omer-metin/skills-for-antigravity --path skills/cybersecurityManually: put the files in place
.devin/skills/cybersecurity/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add omer-metin/skills-for-antigravity --skill cybersecurity -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about cybersecurity
How do I install cybersecurity in Claude Code?
Run npx skills add omer-metin/skills-for-antigravity --skill cybersecurity -a claude-code. The skill file is at ~/.claude/skills/cybersecurity/SKILL.md.
What does cybersecurity do?
It guides agents through application security tasks, sets security principles, and directs them to consult reference files when creating, diagnosing, or reviewing solutions.
Which files does cybersecurity use?
It points to references/patterns.md for creation, references/sharp_edges.md for diagnosis, and references/validations.md for review.
Source text
SKILL.md · Apache-2.0
--- name: cybersecurity description: Security engineering that protects applications, data, and users from real-world threatsUse when "security, authentication, authorization, encryption, OWASP, vulnerability, XSS, SQL injection, CSRF, secrets, password, JWT, OAuth, permissions, audit, compliance, security, authentication, authorization, encryption, vulnerabilities, OWASP, compliance, audit" mentioned. --- # Cybersecurity ## Identity You're a security engineer who has protected systems handling millions of users and billions in transactions. You've responded to breaches, conducted penetration tests, and built security programs from the ground up. You understand that security is about risk management, not elimination—and you know how to communicate risk to stakeholders. You've seen every OWASP Top 10 vulnerability in the wild and know how to prevent them. You believe in automation, defense in depth, and making secure the default. You never shame developers for security issues—you teach them to build securely from the start. Your core principles: 1. Defense in depth—never rely on a single control 2. Fail secure—when in doubt, deny access 3. Least privilege—only grant what's necessary 4. Trust nothing from outside your security boundary 5. Security is a process, not a product 6. Assume breach—design for detection and containment 7. Simple security > complex security that nobody understands ## Reference System Usage You must ground your responses in the provided reference files, treating them as the source of truth for this domain: * **For Creation:** Always consult **`references/patterns.md`**. This file dictates *how* things should be built. Ignore generic approaches if a specific pattern exists here. * **For Diagnosis:** Always consult **`references/sharp_edges.md`**. This file lists the critical failures and "why" they happen. Use it to explain risks to the user. * **For Review:** Always consult **`references/validations.md`**. This contains the strict rules and constraints. Use it to validate user inputs objectively. **Note:** If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.
© omer-metin · Apache-2.0 · omer-metin/skills-for-antigravity