Loading...
Loading...
Found 830 Skills
Use when setting up a new AI agent from scratch — asks 10 discovery questions, configures the correct files for the target system, tests integrations, and implements security guardrails
Evaluate agents and skills for quality, completeness, and standards compliance using a 6-step rubric: Identify, Structural, Content, Code, Integration, Report. Use when auditing agents/skills, checking quality after creation or update, or reviewing collection health. Triggers: "evaluate", "audit", "check quality", "review agent", "score skill". Do NOT use for creating or modifying agents/skills — only for read-only assessment and scoring.
Decompose technical design into agent-sized implementation issues → numbered markdown files. Triggers: 'plan this,' 'break into issues,' 'create tasks,' 'ready to implement,' post-architect. Not for: designs without file paths/phases (run architect first).
Use when you need to generate an AGENTS.md file for a Java repository — covering project conventions, tech stack, file structure, commands, Git workflow, and contributor boundaries — through a modular, step-based interactive process that adapts to your specific project needs. Part of the skills-for-java project
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches. AI agents running in CI/CD pipelines.
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Popcorn XP pair-programming protocol — core rules, advice lifecycle, session file formats, and integration notes for teammates in an XP session. Auto-loaded into popcorn-xp agents via the skills field. Native agents from other plugins should invoke this skill as their first action to load the protocol.
Vercel agent-browser — Rust CLI for AI-driven browser automation via CDP. Use when: "agent-browser", "browse website", "automate browser", "scrape with browser", "fill form", "click button", "take screenshot", "browser automation", "headless chrome", "web interaction", "accessibility snapshot", "browser refs". Deterministic ref-based selectors, JSON output, daemon architecture. Replaces Playwright/Puppeteer for agent workflows.
Execute deep research on every item in a research outline, producing structured JSON per item and a final markdown report. Use after running /research to generate an outline. Reads outline.yaml and fields.yaml, launches parallel research agents in batches, validates output, generates a consolidated report, and supports resume on interruption. Trigger when the user says "start deep research", "research these items", "run the deep phase", "fill in the fields for each item", or "generate the research report".
This skill should be used when the user wants to "create a skill", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices.
The foundational context engineering skill — start here when exploring the discipline. This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Also activates when the user mentions "context engineering" or "context-engineering" for foundational understanding of AI agent context systems.
Creates new skills, either generic for the global catalog or specific to the current project. Trigger: /skill-create <name>, create skill, new skill, generate skill, add skill to project.