creating-opencode-agents
Expert guidance and configuration standards for creating specialized OpenCode AI agents, including YAML frontmatter, tool permissions, and operational modes.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
270 skills found
Expert guidance and configuration standards for creating specialized OpenCode AI agents, including YAML frontmatter, tool permissions, and operational modes.
Enforces Sentry-style conventional commits, branch safety checks, and structured issue referencing for AI coding agents.
Expert guidance for Google Ads Script development including AdsApp API, campaign management, keyword bidding, automated rules, performance reporting, and spend optimization.
Automated CI/CD incident response, failure analysis, and remediation for GitHub Actions pipelines. Resolves build and test failures with safety guardrails.
Analyze Kubernetes controller code to generate contract-compliant dependency graph artifacts for the Kamera coverage strategy.
Manage screenpipe pipes (AI-driven automations) and integrations via CLI. Create, run, schedule, and debug local agents to automate tasks based on your computer activity.
Perform deep security analysis on codebases using CodeQL for interprocedural data flow, taint tracking, and automated vulnerability detection across multiple languages.
Foundational guidelines for context engineering: optimizing token budgets, attention mechanics, and system architecture for AI agents.
Bayesian modeling and probabilistic programming with PyMC. Build hierarchical models, perform MCMC sampling (NUTS), variational inference, and conduct rigorous model comparison using LOO and WAIC.
Extract specific fields from YAML files efficiently without reading entire files, saving 80-95% of context window usage.
React composition patterns for scalable codebases. Refactor complex components, build flexible libraries, and implement compound components or React 19 architecture patterns.
Automates the documentation of solved technical issues using YAML frontmatter, categorized directories, and institutional knowledge indexing for JUCE plugin development.