NeVibeCode · 1,340 items
Skills for Security
Skills for Security: what each one does, an install command and example prompts.
git-guardrails-claude-code skill This skill adds a Claude Code hook that stops risky Git commands before they run. Use it when an agent must not push or discard working-tree changes.
499,069installs
ponytail-review skill ponytail-review reviews a change beyond the diff, checking connected code, bugs, risks, load, tests, speed, and unnecessary code. Use it for PRs and commits.
CX Codex +1
57,000installs
ponytail-audit skill It audits a repository and ranks bugs, risks, and redundant code in a one-shot report. Use it when you need a review without code changes.
CX Codex +1
45,400installs
security-audit skill Reviews codebases and APIs for vulnerabilities using safe sandboxing. Fits pre-release security reviews, pen-test triage, and architecture checks.
CX Codex +1
54,800installs
security-and-hardening skill Guides threat modeling and security checks for code that handles user input, authentication, sessions, or external services. Use it when building a feature that accepts untrusted data or reviewing code before release.
CX Codex +1
70,200installs
supabase
official skill Guides the agent through database configuration and strict RLS policies in Supabase.
CX Codex GP ChatGPT
8installs
doubt-driven-development skill This skill sends non-trivial decisions to a fresh-context reviewer looking for flaws. Use it before changes that are hard to undo or costly to debug later.
CX Codex +1
56,700installs
gws-shared
official skill This skill gives agents shared rules for gws CLI authentication, flags, and output formats. Use it when working with gws commands.
CX Codex +1
66,100installs
persona-it-admin
official skill A persona skill for IT admins: watches for suspicious logins, sets Drive sharing policies, and works through requests with gws.
CX Codex +1
30,100installs
gws-modelarmor
official skill Filters user prompts and model responses for safety using Google Model Armor templates. Useful for automated content sanitization via the gws CLI.
CX Codex +1
30,000installs
gws-modelarmor-create-template
official skill Creates Google Model Armor templates in GCP to filter user-generated content. Useful when configuring jailbreak defenses via the gws CLI.
CX Codex +1
29,900installs
gws-modelarmor-sanitize-prompt
official skill This skill sends a user prompt through a Google Model Armor template. Use it when an incoming prompt needs to pass through a configured Model Armor filter.
CX Codex +1
29,600installs
gws-modelarmor-sanitize-response
official skill This skill sends a model response to Google Model Armor for filtering with a template. Use it to check output before showing it to a user.
CX Codex +1
29,600installs
fix-security-vulnerabilities-with-strix skill This skill triages validated Strix findings, fixes their root causes, and runs Strix again to verify the result. Use it after a CLI or cloud scan.
CX Codex +1
15,700installs
improve skill Surveys any codebase in read-only mode and writes self-contained implementation plans for other models to execute. Helps audit bugs, tech debt, and security without touching code.
CX Codex +1
37,700installs
web-app-penetration-testing skill Runs a black-box web app pentest through Strix and validates findings with working PoCs. Use it for staging sites, live URLs, or local development servers.
CX Codex +1
12,700installs
owasp-top-10-testing skill Runs Strix AI agents to execute exploits across OWASP Top 10:2025 categories. Useful for verifying attack paths with concrete proofs-of-concept before audits.
CX Codex +1
12,800installs
api-security-testing skill This skill guides Strix through REST, GraphQL, or gRPC API security tests, then provides a request to reproduce each finding.
CX Codex +1
12,600installs
find-security-vulnerabilities-in-code skill The skill runs a white-box security review through Strix: agents read your source, model the data flow, then prove each finding with an exploit in a sandbox.
CX Codex +1
12,500installs
application-security-testing skill This skill selects tests for source code, a live web app, APIs, and CI, then turns confirmed findings into a ranked remediation plan. Use it for an AppSec review.
CX Codex +1
12,600installs
1password skill Configures 1Password CLI, handles authentication modes, and safely injects secrets into commands without leaking credentials into chat.
CX Codex +1
6,300installs
security-best-practices skill A skill that reviews code against security best practices for Python, JavaScript/TypeScript and Go, then suggests fixes.
CX Codex +1
358installs
healthcheck skill Audits OpenClaw host security, listening ports, SSH, and firewalls. Spots exposures and applies staged hardening without locking you out.
CX Codex +1
5,500installs
docker-expert skill A skill that turns your AI agent into a Docker reviewer for Dockerfiles, multi-stage builds and container security. Useful when images and Compose files need a second look.
CX Codex +1
27,300installs
java-springboot
official skill Gives GitHub Copilot Spring Boot development practices, from project layout to tests and security. Use it when writing or reviewing Java application code.
21,272installs
docker-patterns skill A skill with Dockerfile and Docker Compose patterns: local dev stacks, networking, volumes, container hardening.
CX Codex +1
6,400installs
google-cloud-recipe-auth
official skill This skill explains Google Cloud authentication and permissions. Use it when setting up IAM, ADC, or service accounts for local code and production workloads.
CX Codex
15,450installs
cloud-sql-basics
official skill This skill helps create and explain Cloud SQL resources for MySQL, PostgreSQL, and SQL Server. Use it when setting up a database in Google Cloud.
CX Codex
14,679installs
google-cloud-waf-security
official skill This skill reviews Google Cloud workloads against the security pillar of the Well-Architected Framework and suggests actions for IAM, networks, data, and operations.
CX Codex
14,620installs
code-review
official skill The skill reviews diffs and pull requests for security, performance and correctness. Useful when a change needs a look before merging.
CX Codex +1
9,900installs
laravel-security skill This skill reviews Laravel authentication, Eloquent safety, CSRF, XSS, APIs, and production settings. Use it for security reviews or deployment checks.
CX Codex +1
5,400installs
hook-development
official skill Guides the development of Claude Code plugin hooks to intercept tool calls, validate output, and enforce task completion checks.
7,028installs
forget skill Deletes selected durable memories from agentmemory after explicit confirmation. Useful when scrubbing secrets or obsolete notes.
CX Codex +1
13,900installs
mcp-integration
official skill This skill shows how to connect MCP servers to Claude Code plugins and expose their tools. Use it when a plugin needs access to an API, database, or file system.
6,994installs
writing-hookify-rules
official skill This skill guides you through writing hookify rules for Claude Code, from choosing an event to defining match conditions and the message shown when a rule triggers.
6,941installs
cloudflare-one skill Walks your agent through designing, configuring and troubleshooting Cloudflare One Zero Trust and SASE deployments. Useful when you need Access, Gateway or tunnel work done without digging through docs yourself.
CX Codex +1
93,100installs
turnstile-spin skill Sets up Cloudflare Turnstile bot verification across existing frontend and backend code, including widget embedding and server-side siteverify.
CX Codex +1
93,100installs
springboot-security skill Reviews security in Java Spring Boot services, covering authentication, authorization, input validation, CSRF, secrets, headers, and dependencies.
CX Codex +1
4,900installs
django-security skill A skill that feeds your agent Django security rules: production settings, auth, permissions, SQL injection and XSS prevention. Useful for reviews and deploys.
CX Codex +1
5,000installs
verification-loop skill Runs a session's work through six phases — build, types, lint, tests with coverage, secret grep, diff review — and prints a PASS/FAIL report.
CX Codex +1
5,000installs
1–40 of 1,340
