build-graph
Builds or updates the knowledge graph used for code review. Supports initial setup and automatic updates maintained by hooks.
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."..." for exact phrases · Try typography, debugging or spreadsheetBuilds or updates the knowledge graph used for code review. Supports initial setup and automatic updates maintained by hooks.
Plans link building campaigns through prospect identification, asset creation, and outreach strategy. Covers backlink acquisition, digital PR, guest posting, and domain authority goals.
Implements, connects, and debugs backend-driven Unity game features such as progression, cloud saves, leaderboards, matchmaking, and virtual economies. Covers server authority, anti-cheat, authentication, remote configuration, analytics, experimentation, and cloud resource deployment.
Executes feature prompts or plan tasks using Claude Code, reviews changes, and resolves discovered issues. Adds security review for sensitive areas and verifies features end to end until all planned tasks are complete.
Executes feature prompts or plan tasks using Codex CLI and reviews uncommitted changes. Fixes review and testing issues, verifies features end to end, and continues until all planned tasks are complete.
Executes feature prompts or plan tasks using Cursor and runs its review workflow. Fixes discovered issues, tests features end to end, and repeats until all planned tasks are complete.
Creates inline MCP interfaces such as forms, pickers, dashboards, and confirmation dialogs. Applies after the server deployment model is settled or when the user already knows they need UI widgets.
Serves as the entry point for MCP server development and API integrations that expose tools to Claude. Determines whether remote HTTP, MCPB, or local stdio fits the use case, then hands off to specialized skills.
Bundles and distributes local MCP servers as .mcpb files, optionally including Node or Python runtimes. Supports servers that interact with local filesystems, desktop applications, or operating systems.
Builds Cog projects with model input and output definitions, weight loading, Docker images, and local prediction or serving. Covers GPU and CUDA setup, fast weight downloads, async batching, streaming outputs, and cold-start optimization across image, video, audio, and language models.
Uses product requirements, roadmap, vision, and design documents to implement an entire MVP in task order. Tests and verifies each task, updates progress, validates the core experience end to end, and initializes Git with an initial commit.
Investigates builds that underuse CPU cores or fail to benefit from parallel execution. Covers critical dependency paths, graph builds, BuildInParallel, solution filters, and max CPU count configuration.
A growing collection of real, public skills. Descriptions and instructions indexed 25 Sept 2026.
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