Total 31,796 skills
Showing 12 of 31796 skills
MUST READ before setting up observability for ADK agents or when analyzing production traffic, debugging agent behavior, or improving agent performance. ADK observability guide — Cloud Trace, prompt-response logging, BigQuery Agent Analytics, third-party integrations, and troubleshooting. Use when configuring monitoring, tracing, or logging for agents, or when understanding how a deployed agent handles real traffic.
MUST READ before running any ADK evaluation. ADK evaluation methodology — eval metrics, evalset schema, LLM-as-judge, tool trajectory scoring, and common failure causes. Use when evaluating agent quality, running adk eval, or debugging eval results. Do NOT use for API code patterns (use adk-cheatsheet), deployment (use adk-deploy-guide), or project scaffolding (use adk-scaffold).
Run headless Chrome in Next.js serverless functions using @sparticuz/chromium + puppeteer-core. Use when the user needs browser automation from a Next.js app, wants to take screenshots or snapshots from server actions or API routes, or is building a Next.js app that needs headless Chrome. Triggers include "screenshot from Next.js", "headless Chrome in serverless", "browser automation in Next.js", "puppeteer on Vercel", or any task requiring Chrome in a Next.js server context.
LOAD THIS SKILL when: creating PRs, pushing changes, creating branches, fixing PR review comments, syncing branches, user mentions 'pr', 'push', 'branch', 'pr-fix-comments', 'sync-branches'. Covers git workflow automation with CI monitoring, PR lifecycle, and branch management.
Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.
DingTalk knowledge base and document management operations. This skill is used when users mention "DingTalk Docs", "knowledge base", "create new document", "view document directory", "read document content", "write to document", "update document", "document members", "dingtalk doc", "knowledge base". It supports all document-related operations including creating knowledge bases, querying knowledge base lists, creating new documents/folders, reading/writing document body content, and managing member permissions.
Generate high-quality images via MCP (Gemini models or compatible services) using structured prompts, ratios, and validation for marketing, UI, or presentations.
Python toolkit for computational biology. Use when asked to "parse FASTA", "read GenBank", "query NCBI", "run BLAST", "analyze protein structure", "build phylogenetic tree", or work with biological sequences. Handles sequence I/O, database access, alignments, structure analysis, and phylogenetics.
Python bioinformatics library for sequence manipulation, alignments, phylogenetics, diversity metrics (Shannon, UniFrac), ordination (PCoA, CCA), statistical tests (PERMANOVA, Mantel), and biological file format I/O.
Query the ChEMBL database for bioactive compounds, drug targets, and bioactivity data. Use this skill when searching for small molecules, finding inhibitors for protein targets, or analyzing drug mechanisms of action.
Foundation skill for autonomous protein engineering via the Amina CLI. Use at session start or after conversation compacting when working with AminoAnalytica's Amina CLI or when you need help using the Amina CLI to do protein engineering tasks like: protein design, structure prediction, binder design, docking, molecular dynamics, enzyme engineering, or any mention of Amina/amina-cli.
Python cheminformatics library for molecular manipulation and analysis. Parse SMILES/SDF/MOL formats, compute descriptors (MW, LogP, TPSA), generate fingerprints (Morgan, MACCS), perform substructure queries with SMARTS, create 2D/3D geometries, calculate similarity, and run chemical reactions.