Casky.AI
ApproachPathsCurriculumBlogAboutCommunity
Sign inGet Access
5 Learning Paths · Early access — Join the waitlist to access the Playground
6.0k stars·825 forksfeatured in★awesome-agent-skills·SkillsLLM·OpenflowsApache 2.0·Open source

AI-Powered Cyber Skills

Security skills
forged with AI.

Five structured learning paths to become a next-generation AI Security Engineer — Cloud, Network, Web & App, SOC, and Pentesting. Each path combines 754 Claude skills with Claude's extended reasoning model, progressing from Simulation → Evidence → Actual so you build real expertise, not just certifications.

Get Playground AccessView learning paths
5
Learning paths
754
AI-powered skills
Free
Early access
claude-agent · OWASP A03: Injection
running
mapped to
MITRE ATT&CK14 tactics · 291 techniques
NIST CSF 2.06 functions · full lifecycle
OWASP Top 102025 edition
Claude Sonnet 4.6Anthropic · Agentic AI

The approach

The path to becoming a
next-gen AI Security Engineer

Traditional training teaches you what tools exist. Casky teaches you how to think with Claude's reasoning model — the way the next generation of security engineers already works.

Reasoning Model

Claude's extended thinking doesn't just run tools — it reasons through problems the way a senior practitioner does. You learn by watching and directing that reasoning, not reading about it.

vs. passive video courses

Framework-Native

Every skill maps to MITRE ATT&CK tactics, NIST CSF functions, and OWASP categories. You always know exactly where your knowledge sits in the industry map.

vs. random skill tutorials

5 learning paths · 754 skills · 12 domains

What you'll master

Follow a structured path to your target role, or explore any domain freely. Every skill is powered by Claude's reasoning model and mapped to the frameworks employers care about.

OSINT & Recon
0 skills
TA0043NIST ID
Web App & API Security
70 skills
OWASP A01–A10

Career-mapped training

Five paths to AI Security expertise

Each path takes you from foundational skills (101) to advanced practitioner (201) to a shareable Casky certificate — using Claude's reasoning model at every step.

Cloud Security Engineer

AWS · Azure · GCP hardening with Claude AI

101→
201→
Cert
TA0004NIST PR

The workflow

How Casky works

01

Choose a framework, tactic, or skill

Navigate the registry by MITRE ATT&CK tactic, NIST CSF function, or OWASP category. Each skill ships with learning objectives, prerequisites, and a sample target ready to go.

02

Run a Claude agent against a live target

Enter a URL, IP range, log file, or scenario brief and hit run. Claude takes the skill's methodology and applies it live — reasoning, investigating, reporting in real time through your browser.

03

Review structured findings

Every run produces CVSS-scored findings tagged to MITRE techniques. Your findings board becomes a portfolio of real security analysis — not hypothetical exercises.

04

The platform

See it in action

A real look at the Casky Playground.

Your mission control — runs, findings, and activity at a glance
Dashboard
Your mission control — runs, findings, and activity at a glance
Real-time overview of your security work
Dashboard
Real-time overview of your security work
Pick a skill, set your target, run a Claude agent
Skills Lab
Pick a skill, set your target, run a Claude agent
Navigate the curriculum by MITRE, NIST, or OWASP
Learning Path
Navigate the curriculum by MITRE, NIST, or OWASP
Track every agent run directly from your dashboard
Dashboard — Runs
Track every agent run directly from your dashboard
All your CVSS-scored findings in one view
Dashboard — Findings
All your CVSS-scored findings in one view
From agent run to structured security finding
Runs & Findings
From agent run to structured security finding
Detailed run output with linked findings
Runs & Findings
Detailed run output with linked findings
Claude reasoning live through a security problem
Skills Run
Claude reasoning live through a security problem
Full run history with status, target, and timing
Runs
Full run history with status, target, and timing
Stream Claude's agent reasoning in real time
Run Detail
Stream Claude's agent reasoning in real time
From findings to a professional assessment report
Reports & Findings
From findings to a professional assessment report
Export full reports — executive summary, findings, remediation
Reports
Export full reports — executive summary, findings, remediation
754 skills mapped to MITRE ATT&CK, NIST CSF, and OWASP
Skills Registry
754 skills mapped to MITRE ATT&CK, NIST CSF, and OWASP
CVSS-scored findings tagged to MITRE techniques
Findings
CVSS-scored findings tagged to MITRE techniques

Who Casky is built for

CS & Engineering Students

Follow a structured learning path from 101 to certification before you graduate. Walk out as an AI Security Engineer with a portfolio of real findings, not just a transcript.

Security Professionals

Add Claude's reasoning model to your toolkit and get ahead of the shift from tool-runner to AI-augmented analyst. The next generation of practitioners is already working this way.

Career Switchers

Coming from SWE, DevOps, or IT? Pick the path that matches your target role — Cloud Engineer, SOC Analyst, Pentester — and follow it step by step with AI as your guide.

Early access — Playground waitlist now open

Start your path to
AI Security Engineer.

Pick a learning path, run 754 Claude-powered skills against live targets, and earn your Casky certificate. Simulation → Evidence → Actual. Free for early members.

We'll email you when the Playground opens. No spam. Unsubscribe anytime.

754
Skills in Playground
Free
For early members
Async
Learn at your pace
Casky.AI, Inc.· AI-Powered Cyber Skills
AboutEnterpriseCommunityContributeSign inContact
XInstagramLinkedIn
01▶ target: demo.testfire.net
02 loading: SQL Injection Detection
03 mapping: MITRE T1190 · OWASP A03
04 probing /login — testing 8 vectors
05⚠ anomalous response on: username
06 testing boolean-based blind inject...
07✗ CONFIRMED: Blind SQLi at /login
08 estimating blast radius...
09✓ report_finding("SQL Injection", "critical")
10 CVSS: 9.8 · CWE-89 · T1190
11 generating remediation guidance ▌

Three Progressive Modes

Start in Simulation — safe, guided, zero infrastructure. Move to Evidence mode for real structured findings. Graduate to Actual mode running Claude on your own live targets.

Simulation → Evidence → Actual

Skill
Typical bootcamp
Casky
Attacker mindset
✗ Theoretical
✓ Live agent runs
Framework mapping
~ Partial
✓ MITRE + NIST + OWASP
Real target analysis
✗ Sandboxed VMs
✓ Claude on live targets
Professional reports
✗ Not covered
✓ Auto-generated
CVSS-scored findings
✗ Manual notes
✓ Structured + tagged
Learn at your pace
~ Fixed schedule
✓ Async, self-paced
Malware Analysis
39 skills
TA0002NIST DE
Cloud & Infrastructure
63 skills
TA0004NIST PR
Digital Forensics & IR
63 skills
TA0040NIST RS
Network Security
43 skills
TA0011NIST DE
Identity & Access
50 skills
TA0006NIST PR
Red Teaming
44 skills
AllNIST ID
DevSecOps
17 skills
NIST PROWASP A03,A08
Threat Intelligence
106 skills
TA0043NIST ID
SOC Operations
33 skills
NIST DE/RS
Container Security
29 skills
NIST PROWASP A05,A06

Network Security Engineer

Traffic analysis, detection, and response

101→
201→
Cert
TA0011NIST DE

Web & App Security Engineer

OWASP Top 10, API security, secure code review

101→
201→
Cert
OWASP A01–A10

SOC Analyst

Threat detection, triage, incident response

101→
201→
Cert
TA0040NIST DE/RS

Penetration Tester

Full attack lifecycle — recon to report

101→
201→
Cert
AllNIST ID
Coming soon

Live Cohort Courses on Maven

Structured 6-week cohorts with Casky founders and expert tutors. Real-time sessions, live labs, and peer cohorts — for practitioners who want guided, accountable training.

Progressive learning modes

01

Simulation

Safe, guided practice against demo targets. Zero infrastructure required. Master the skill before you apply it.

02

Evidence

Real targets, structured findings. CVSS-scored, MITRE-tagged, ready for your portfolio. Prove what you can do.

03

Actual

Run Claude on your own infrastructure. Enterprise-grade AI security analysis — the way practitioners actually work.

Generate a professional report

Select completed runs and generate a full assessment report — executive summary, technical findings, remediation roadmap. Download as Markdown. The exact format used in real engagements.

TikTok

© 2026 Casky.AI, Inc. · AI-Powered Cyber Skills