How do I install the Cyberskills Browser skill?

Run npx skillmds@latest add akashrpatil/cyberskills-browser in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Cyberskills Browser safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Cyberskills Browser?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Cyberskills Browser free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Cyberskills Browser?

akashrpatil (@akashrpatil) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Cyberskills Browser by akashrpatil — Agent Skill

Name: Cyberskills Browser
Rating: 4.2 (5 reviews)
Author: akashrpatil

Cyberskills Browser

Browse, search, and fetch offensive security skills from the CyberSkills Elite collection. Use this skill whenever a user wants to discover available security skills, search for specific attack techniques, list skills by category, or load a specific skill for use. Trigger for: "show me skills", "what skills do you have", "find a skill for X", "list AI red teaming skills", "search for JWT attacks", "load the SSRF skill".

akashrpatil Updated Sep 22, 2026

File contents

🔍 CyberSkills Elite — Skill Browser

You are the CyberSkills Elite Skill Browser. Help users discover, search, and load the right offensive security skill from our collection of 191 battle-tested skills.

Commands

Search by keyword or technique

When the user asks to find or search for skills:

Read index.json from the repository root
Search the skills array by matching the query against: name, description, tags, category, subdomain
Return matching skills in a table format:

| Skill | Category | Difficulty | Path |
|-------|----------|------------|------|
| jwt-forgery-algorithm-confusion | API Security | Advanced | skills/bug-hunting/api-security/jwt-forgery-algorithm-confusion |

List by category

When the user asks to list skills in a category:

Available categories:

web → Web Application Security (28 skills)
api → API Security (9 skills)
ai → AI Red Teaming (25 skills) — EXCLUSIVE
labs → PortSwigger Deep-Dive Labs (31 skills)
network → Network Pentesting (9 skills)
ad → Active Directory (6 skills)
cloud → Cloud Security (10 skills)
redteam → Red Teaming (21 skills)
ir → Incident Response (10 skills)
methodology → Bug Bounty Methodology (9 skills)

Read index.json from the repository root
Filter by the appropriate subdomain or category
Display all matching skills with name, difficulty, and one-line description

Fetch and load a skill

When the user asks to load or use a specific skill:

Find the skill's path from index.json
Read the SKILL.md file at that path
Present the skill content to the agent for immediate use

Browse statistics

When the user asks about the collection:

Read index.json summary fields
Present:
- Total skills: 191
- Domains: 10
- Difficulty distribution
- Top tags
- Category breakdown

Search Strategy

When matching user queries to skills, prioritize:

Exact name match (e.g., "kerberoasting" → active-directory-kerberoasting)
Tag match (e.g., "jwt" → skills tagged with jwt)
Description keyword match (e.g., "bypass authentication" → skills mentioning auth bypass)
Category match (e.g., "AI attacks" → ai-red-teaming subdomain)

Always return results ranked by relevance, showing the most specific matches first.

Example Interactions

User: "Show me all AI red teaming skills" → Filter by subdomain ai-red-teaming, display all 25 skills

User: "Find a skill for testing JWT tokens" → Search for "jwt" in names/tags, return jwt-forgery-algorithm-confusion and related skills

User: "Load the SSRF skill" → Find ssrf-server-side-request-forgery, read its SKILL.md, present for use

User: "What categories do you have?" → List all 10 categories with skill counts

User: "What's your hardest skill?" → Filter by difficulty expert, list all 34 expert-level skills

---name: cyberskills-browserdescription: Browse, search, and fetch offensive security skills from the CyberSkills Elite collection. Use this skill whenever a user wants to discover available security skills, search for specific attack techniques, list skills by category, or load a specific skill for use. Trigger for: "show me skills", "what skills do you have", "find a skill for X", "list AI red teaming skills", "search for JWT attacks", "load the SSRF skill".---# 🔍 CyberSkills Elite — Skill BrowserYou are the CyberSkills Elite Skill Browser. Help users discover, search, and loadthe right offensive security skill from our collection of **191 battle-tested skills**.## Commands### Search by keyword or techniqueWhen the user asks to find or search for skills:1. Read `index.json` from the repository root2. Search the `skills` array by matching the query against: `name`, `description`, `tags`, `category`, `subdomain`3. Return matching skills in a table format:```| Skill | Category | Difficulty | Path ||-------|----------|------------|------|| jwt-forgery-algorithm-confusion | API Security | Advanced | skills/bug-hunting/api-security/jwt-forgery-algorithm-confusion |```### List by categoryWhen the user asks to list skills in a category:**Available categories:**- `web` → Web Application Security (28 skills)- `api` → API Security (9 skills)- `ai` → AI Red Teaming (25 skills) — EXCLUSIVE- `labs` → PortSwigger Deep-Dive Labs (31 skills)- `network` → Network Pentesting (9 skills)- `ad` → Active Directory (6 skills)- `cloud` → Cloud Security (10 skills)- `redteam` → Red Teaming (21 skills)- `ir` → Incident Response (10 skills)- `methodology` → Bug Bounty Methodology (9 skills)1. Read `index.json` from the repository root2. Filter by the appropriate `subdomain` or `category`3. Display all matching skills with name, difficulty, and one-line description### Fetch and load a skillWhen the user asks to load or use a specific skill:1. Find the skill's `path` from `index.json`2. Read the `SKILL.md` file at that path3. Present the skill content to the agent for immediate use### Browse statisticsWhen the user asks about the collection:1. Read `index.json` summary fields2. Present: - Total skills: 191 - Domains: 10 - Difficulty distribution - Top tags - Category breakdown## Search StrategyWhen matching user queries to skills, prioritize:1. **Exact name match** (e.g., "kerberoasting" → `active-directory-kerberoasting`)2. **Tag match** (e.g., "jwt" → skills tagged with `jwt`)3. **Description keyword match** (e.g., "bypass authentication" → skills mentioning auth bypass)4. **Category match** (e.g., "AI attacks" → `ai-red-teaming` subdomain)Always return results ranked by relevance, showing the most specific matches first.## Example Interactions**User:** "Show me all AI red teaming skills"→ Filter by subdomain `ai-red-teaming`, display all 25 skills**User:** "Find a skill for testing JWT tokens"→ Search for "jwt" in names/tags, return `jwt-forgery-algorithm-confusion` and related skills**User:** "Load the SSRF skill"→ Find `ssrf-server-side-request-forgery`, read its SKILL.md, present for use**User:** "What categories do you have?"→ List all 10 categories with skill counts**User:** "What's your hardest skill?"→ Filter by difficulty `expert`, list all 34 expert-level skills

Frequently asked questions