One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
zebbernSkillzebbern/termstack/.github/skills/rce-poc/SKILL.md
Exploit OS Command Injection vulnerabilities to achieve Remote Code Execution (RCE). Command injection occurs when user input is passed unsafely to system shell commands, allowing attackers to execute arbitrary commands…
zebbernAGENTS.mdzebbern/termstack/.github/skills/react-best-practices/AGENTS.md
Version 1.0.0 Vercel Engineering January 2026 Note: This document is mainly for agents and LLMs to follow when maintaining, generating, or refactoring React and Next.js codebases. Humans may also find…
zebbernSkillzebbern/termstack/.github/skills/react-best-practices/SKILL.md
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Often used withdep-refsvercel-composition-patternsarchitecture-governance
zebbernAGENTS.mdzebbern/termstack/.github/skills/react-native-skills/AGENTS.md
Version 1.0.0 Engineering January 2026 Note: This document is mainly for agents and LLMs to follow when maintaining, generating, or refactoring React Native codebases. Humans may also find it useful,…
55 projects use a version of this
zebbernSkillzebbern/termstack/.github/skills/react-native-skills/SKILL.md
Comprehensive best practices for React Native and Expo applications. Contains rules across multiple categories covering performance, animations, UI patterns, and platform-specific optimizations. Reference these guidelines when:
Often used withvercel-cli-with-tokensdeploy-to-vercelui-ux-pro-max
zebbernSkillzebbern/termstack/.github/skills/scope-check/SKILL.md
Validate targets against bug bounty program scope, verify domain/IP ownership, check wildcard rules, and identify out-of-scope exclusions. Use when validating new targets, checking discovered assets, or before testing any endpoint.
Often used withteam-polishasset-specteam-audio
zebbernSkillzebbern/termstack/.github/skills/skill-creator/SKILL.md
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Often used withtaskflow-inbox-triagemermaid-diagram-generatorcommunity-led-growth
zebbernSkillzebbern/termstack/.github/skills/slack-gif-creator/SKILL.md
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack.
Often used withacademy-guideskill-shareraffle-winner-picker
zebbernSkillzebbern/termstack/.github/skills/sqli-poc/SKILL.md
Detect and exploit SQL injection vulnerabilities using automated and manual techniques. Use when testing for SQL injection, when parameters appear injectable, when database enumeration is needed, or when proving SQL injection impact.
zebbernSkillzebbern/termstack/.github/skills/ssl-check/SKILL.md
Analyze SSL/TLS configurations for security weaknesses and compliance. Use when testing HTTPS endpoints, when checking for TLS vulnerabilities, when validating certificates, or when auditing cipher suite configurations.
zebbernSkillzebbern/termstack/.github/skills/state-persistence/SKILL.md
Provides patterns for reading, writing, and recovering AgLoop state from state.json and plan.yaml. Includes checkpoint management and corruption recovery. Use when implementing state management logic or hook scripts.
zebbernSkillzebbern/termstack/.github/skills/subdomain-enum/SKILL.md
Enumerate subdomains for a target domain using passive and active reconnaissance techniques. Use when starting reconnaissance on a new target, when you need to discover the attack surface, when expanding scope from a root domain, or when the user provides a domain to investigate.
zebbernSkillzebbern/termstack/.github/skills/synack-report/SKILL.md
Generate professional vulnerability reports following Synack Red Team (SRT) format and standards. Synack operates differently from traditional bug bounty programs - it's an elite, vetted researcher community with higher quality…
zebbernSkillzebbern/termstack/.github/skills/task-planning/SKILL.md
Guides agents through DAG task decomposition, dependency analysis, effort estimation, and pre-mortem failure analysis. Use when creating or revising implementation plans from feature requirements.
zebbernSkillzebbern/termstack/.github/skills/tech-fingerprint/SKILL.md
Identify technologies, frameworks, and software versions running on web targets. Use when you need to discover the technology stack of a website, when mapping attack surface for known CVEs, when identifying CMS or framework versions, or when the user asks about what technologies a site is running.
zebbernSkillzebbern/termstack/.github/skills/theme-factory/SKILL.md
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
Often used withskill-sharecontext7-efficientacademy-guide
zebbernSkillzebbern/termstack/.github/skills/triage-findings/SKILL.md
Deduplicate, prioritize, and rank vulnerability findings using CVSS, EPSS, and business context. Use when processing scan results, correlating multiple findings, determining remediation priority, or when the agent needs to organize discovered vulnerabilities.
zebbernSkillzebbern/termstack/.github/skills/ui-avoid/SKILL.md
Use when building or refactoring React and Tailwind UI that keeps drifting into generic AI-dashboard styling and needs a repeatable visual audit loop.
zebbernSkillzebbern/termstack/.github/skills/waf-bypass-hunter/SKILL.md
Bypass a Coraza WAF protecting a vulnerable Next.js 16 backend. Analyze parser differentials between Go (WAF) and Node.js (backend) to find bypasses.
zebbernSkillzebbern/termstack/.github/skills/webapp-testing/SKILL.md
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Often used withacademy-guideskill-shareintelligent-routing
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
