open-pencil
Works with .fig files and the running OpenPencil editor to inspect structure, query nodes, analyze design tokens, and modify designs programmatically. Exports PNG, SVG, PDF, and JSX.
Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Works with .fig files and the running OpenPencil editor to inspect structure, query nodes, analyze design tokens, and modify designs programmatically. Exports PNG, SVG, PDF, and JSX.
Opens a PR from the current branch to main when explicitly requested. Commits if needed, ensures an Nx version plan exists, pushes the branch, and fills in the PR description and testing steps.
Interprets OpenProse workflows in-session using host primitives. Selects a state backend, assigns responsibilities, and persists run state under the selected OpenProse root; intended for reusable multi-agent orchestration.
Provides a playbook for open redirect vulnerabilities. Focuses on URL parameters, form actions, and JavaScript sinks that may send users to attacker-controlled destinations.
Identify Open Redirect vulnerabilities where applications route users to arbitrary external URLs based on unvalidated input. Prove maximum impact by chaining Open Redirects with OAuth token theft, SSRF, or Phishing, graduating this typically low-risk finding into a high-severity report.
Provides reference guidance for browser-use Agent, Browser, and Tools configuration in Python. Covers custom tools, lifecycle hooks, MCP setup, deployment, model support, prompting, observability, and sensitive data handling.
Provides a single entry point for open-websearch setup and focused live information retrieval. Prefers local CLI or daemon paths while supporting workspace-exposed MCP tools.
Authors, validates, tiers, and renders OpenAgent persona YAML files and shareable holo trading cards. Supports creating or updating an agent identity and provisioning a live teammate from a persona.
Supports development with the openai-agents Python package, including multi-agent handoffs, function tools, structured outputs, and session management. Covers streaming, tracing, guardrails, and Azure OpenAI access through LiteLLM.
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restric…
Batch-generate images via OpenAI Images API. Random prompt sampler + index.html gallery.
Symphony turns project work into isolated implementation runs performed autonomously by coding agents. It allows teams to manage work without directly supervising each agent.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name