banana-claude
AI image generation skill for Claude Code where Claude acts as Creative Director using Google's Gemini Nano Banana models.
AI-powered cybersecurity code review skill for Claude Code. 8 specialist agents, OWASP 2025, CWE Top 25, MITRE ATT&CK, 11 languages, zero configuration.
$ npx -y skills add AgriciDaniel/claude-cybersecurity --agent claude-code
Run the curl in your terminal, the rest in Claude Code.
Repo: AgriciDaniel/claude-cybersecurity
What's inside
The most comprehensive AI-powered cybersecurity code review skill for Claude Code. Spawns 8 parallel specialist agents to audit your codebase across vulnerability detection, authorization verification, secret scanning, supply chain analysis, IaC security, threat intelligence (malware/C2/backdoor detection), AI-generated code patterns, and business logic flaws.
Complements GitHub Advanced Security by detecting what static tools architecturally cannot: missing security controls, business logic flaws, attack-path chaining, and obfuscated secrets โ with zero configuration.
git clone https://github.com/AgriciDaniel/claude-cybersecurity.git
cd claude-cybersecurity
bash install.sh
claude plugin install cybersecurity
curl -fsSL https://raw.githubusercontent.com/AgriciDaniel/claude-cybersecurity/main/install.sh | bash
# Full security audit of current project
/cybersecurity
# Quick scan (entry points + auth + secrets + deps only)
/cybersecurity --scope quick
# Review only changed files (PR review mode)
/cybersecurity --scope diff
# Deep dive into one dimension
/cybersecurity --focus threat
# With compliance mapping
/cybersecurity --compliance pci
| Capability | GHAS | This Skill |
|---|---|---|
| Business logic flaw detection | No | Yes |
| Authorization enforcement verification | Basic | Context-aware |
| Race condition detection | Very limited | Concurrency pattern analysis |
| Languages supported | 12 | 14 (pattern-based) + broader reasoning via LLM |
| IaC/Container/CI-CD scanning | No | Terraform, Docker, K8s, Actions |
| AI-generated code security | No | Specialized detection |
| Obfuscated secret detection | Regex only | Semantic context analysis |
| Threat intelligence (malware/C2) | No | MITRE ATT&CK mapped |
| Framework-aware false-positive suppression | No | 10 frameworks |
| Cost | $49/committer/month | Free (with Claude Code) |
skills/cybersecurity/
โโโ SKILL.md (~990 lines โ orchestrator)
โโโ references/
โ โโโ vulnerability-taxonomy.md (25 CWE categories)
โ โโโ scoring-rubric.md (formula + confidence system)
โ โโโ threat-intelligence.md (MITRE ATT&CK patterns)
โ โโโ compliance-matrix.md (5 frameworks)
โ โโโ false-positive-suppression.md (10 frameworks)
โ โโโ semgrep-patterns.md (8 detection patterns)
โ โโโ report-template.md (output format + worked example)
โ โโโ language-patterns/ (11 files)
โ โโโ iac-patterns/ (4 files)
Total: 23 files, 5,350 lines of security knowledge.
curl -fsSL https://raw.githubusercontent.com/AgriciDaniel/claude-cybersecurity/main/uninstall.sh | bash
Or manually:
rm -rf ~/.claude/skills/cybersecurity
MIT - AgriciDaniel 2026
.claude-plugin/
plugin.json
.github/
ISSUE_TEMPLATE/
config.yml
workflows/
ci.yml
.gitignore
assets/
agents-chart.svg
architecture.svg
banner-1-matrix.png
banner-2-blueprint.png
banner-3-terminal.png
banner-4-network.png
banner-5-minimal.png
banner-6-layered.png
banner-v2-01.png
banner-v2-03.png
banner-v2-04.png
banner-v2-05.png
banner-v2-06.png
banner-v2-07.png
banner-v2-08.png
banner-v2-10.png
banner.svg
banner.webp
coverage.svg
scoring.svg
CHANGELOG.md
checksums.sha256
CONTRIBUTING.md
install.sh
LICENSE
PRIVACY.md
README.md
research-prompt.md
SECURITY-AUDIT-2026-04-15.md
SECURITY.md
skills/
cybersecurity/
references/
compliance-matrix.md
false-positive-suppression.md
iac-patterns/
dockerfile.md
github-actions.md
kubernetes.md
terraform.md
language-patterns/
c-cpp.md
csharp.md
go.md
java.md
javascript-typescript.md
php.md
python.md
ruby.md
rust.md
shell-bash.md
swift-kotlin.md
report-template.md
scoring-rubric.md
semgrep-patterns.md
threat-intelligence.md
vulnerability-taxonomy.md
SKILL.md
SUPPORT.md
uninstall.shAI image generation skill for Claude Code where Claude acts as Creative Director using Google's Gemini Nano Banana models.
Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative. Based on Karpathy's LLM Wiki pattern.
Interactive longform-to-shortform video creator powered by Claude Code. Extracts viral-ready vertical clips from long videos using Claude as the intelligent orchestrator with Remotion-rendered premium animated captions.
FAQ
cybersecurity is a Claude Code plugin with 1 hand-picked skill for security work, indexed on Flowy. Install it with the command on its page. It includes cybersecurity. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.