Safer agent skills

Generate or improve a company-specific data analysis skill by extracting tribal knowledge from analysts.

Score basis：Clear source · Risk needs review · Claude

A lightweight, powerful framework for multi-agent workflows and voice agents Topics: agents, openai, openai-api, realtime-api, typescript.

Score basis：Clear source · Low risk signals · Universal

Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers Topics: ai, apps, mcp, mcp-apps, modelcontextprotocol, ui.

Score basis：Clear source · Low risk signals · Universal

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent",

Score basis：Clear source · High risk signals · Claude

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, o

Score basis：Clear source · High risk signals · Claude

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent",

Score basis：Clear source · High risk signals · Claude

Comprehensive Vercel ecosystem plugin — relational knowledge graph, skills for every major product, specialized agents, and Vercel conventions.

Score basis：Clear source · Low risk signals · Universal

Triages GitHub issues by routing to oncall teams, applying labels, and closing questions.

Score basis：Clear source · Low risk signals · Claude

This skill applies consistent corporate branding and styling to all generated documents including colors, fonts, layouts, and messaging

Score basis：Clear source · Low risk signals · Claude

This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions

Score basis：Clear source · Low risk signals · Claude

This skill calculates key financial ratios and metrics from financial statement data for investment analysis

Score basis：Clear source · Low risk signals · Claude

Audit an Anthropic Cookbook notebook based on a rubric.

Score basis：Clear source · Low risk signals · Claude

Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository.

Score basis：Clear source · Low risk signals · Claude

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.

Score basis：Clear source · Low risk signals · Claude

Manage issues, projects & team workflows in Linear.

Score basis：Clear source · Low risk signals · Claude

Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking.

Score basis：Clear source · Low risk signals · Claude

Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.

Score basis：Clear source · Low risk signals · Claude

Guide users through creating Agent Skills for Claude Code.

Score basis：Clear source · Risk needs review · Claude

Write Metal/MPS kernels for PyTorch operators.

Score basis：Clear source · Risk needs review · Claude

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui).

Score basis：Clear source · Risk needs review · Claude

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use.

Score basis：Clear source · Risk needs review · Claude

This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settin

Score basis：Clear source · Risk needs review · Claude

This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.

Score basis：Clear source · Risk needs review · Claude

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5.

Score basis：Clear source · High risk signals · Claude