Loading...
Loading...
Found 7,116 Skills
Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when you need to generate code for calling Gemini or OpenMaaS models, authenticate with GenAI SDK, OpenAI SDK, or legacy Agent Platform SDK, configure base URLs and global/regional endpoints, or troubleshoot 429 Resource Exhausted (DSQ), 400 User Validation, or 404 Not Found errors. Don't use for deploying models to endpoints or for running model evaluations.
Apply when sequencing an addition, refactor, or rewrite. Remove dead weight, redundant validators, and stub references first, then build on the simpler base.
Track Washington State K-12 education legislation using committee-based discovery via SOAP API. Gets ALL bills from education committees - no keyword filtering that might miss bills. Use when: checking legislature, tracking bills, legislative updates, morning briefing legislative section.
Entry P1 category router for injection testing. Use when routing between XSS, SQLi, SSRF, XXE, SSTI, command injection, and NoSQL injection workflows based on how attacker-controlled input is consumed.
Run a reusable JavaScript supply-chain security baseline with pnpm-first hardening, release-age gating, lifecycle-script controls, exotic dependency checks, CI install checks, and optional incident IOC profiles.
This skill should be used when the user intends to repurpose content, such as requesting to "generate long-form article", "generate short-form post", "convert to WeChat Official Account article", "create versions for Moments/Twitter/Jike", or "generate other formats based on this script". It applies when the user wants to repurpose a finalized video script into a long-form article or short posts. Call li-writer to generate long-form articles (for WeChat Official Account) or short-form posts (for Moments/Twitter/Jike) based on confirmed short video scripts. Even if the user only mentions "create long-form article" or "create short-form post" without specifying the source script, proactively retrieve available scripts for the user to select from. Do NOT trigger the following: generating original scripts (use li-writer), optimizing openings (use li-opening), generating covers (use li-cover).
Stands up a production-ready Sent v3 integration in an existing codebase — SDK selection and client construction, x-api-key configuration, idempotent sends, retry and rate-limit handling, the 46-code error catalog, sandbox verification, and a verified webhook receiver. Use when adding Sent to an app for the first time, choosing an SDK or framework wiring, handling 429 or 409 responses, deciding what to log, or hardening an integration before launch.
Find similar files, detect duplicates, and analyze code similarity across a codebase. Use when the user asks to find duplicate code, similar files, or wants to understand code overlap.
Use this skill to bridge tokens, cross-chain swap/transfer, move assets between chains, get cross-chain quotes, compare bridge fees, find the cheapest/fastest route, build bridge calldata, check bridge status, track a cross-chain transaction, list supported chains or bridge protocols, or when the user mentions bridging ETH/USDC/tokens from one chain (Ethereum, BSC, Polygon, Arbitrum, Base, Optimism, Solana, etc.) to another. Routes through multiple bridge protocols (Stargate, Across, Relay, Gas.zip) for optimal execution. Supports fee comparison, destination address specification, approval management, and full lifecycle status tracking until fund arrival.
Create Pydantic models following the multi-model pattern with Base, Create, Update, Response, and InDB variants. Use when defining API request/response schemas, database models, or data validation in Python applications using Pydantic v2.
Create a consistent spacing system based on a base unit with contextual application rules.
Use when user asks about fixing security vulnerabilities, composer audit failures, vulnerable Drupal packages, or CVE advisories in a Drupal codebase.