1,638 tagged opencode, measured the same way as everything else here.
Browse within: cursor 247skills 164prompt-engineering 120game-development 108godot 107oh-my-opencode 102cli 100dsh-plugin 94antigravity 92gemini 92deepseek-harness 89visual-editor 89agent 88opencode-plugin 83
Skill Claude CodeCodex
Handle event-triggered automations for Pipa. Use this whenever the user wants Pipa to run a workflow when an external event happens, such as a GitHub PR opening, a Linear issue being created, a Slack channel changing, a new ticket arriving, or asks to list, inspect, or delete existing event triggers. This skill owns…
Skill Claude Code
Quick user-centric interview to capture requirements from a time-poor stakeholder.
Vincent-A-Yang/karpathy-skills-anycoding
Skill Claude CodeCodex
Tool-agnostic behavioral guidelines for AI coding assistants. Use when writing, reviewing, debugging, or refactoring code to reduce overengineering, surface ambiguity, make surgical changes, and define verifiable success criteria.
Skill Claude CodeCodex
Use when operating VRChat MCP tools, especially auth, privacy-sensitive results, writes, stale cache, or resolving names to IDs.
Skill Claude CodeCodex
Use when fixing a bug, defect, issue, or unexpected behavior. Follows Goal-Driven Execution: reproduce with a test, implement the fix, verify no regressions.
Skill Codex
A skill for creating, editing, checking, and diagnosing Russian-language Turbo Gherkin `.feature` files for Vanessa Automation, a tool for testing 1C applications. It covers UI and export scenarios without MCP.
Skill Codex
Resolve credential identities, deliver secrets to a process, or administer entries through the MAINFRAME credential index and helper, without exposing values.
Skill Claude CodeCodex
Structured planning pipeline with 4 adaptive phases (Specify, Design, Tasks, Execute) and persistent knowledge accumulation for development teams. Auto-sizes depth by complexity from quick fixes to multi-component features. Commands: /explore (understand problem + map context), /plan (write spec → design → tasks)…
Skill OpenCode
Self-educating humanizer skill that keeps up with the latest LinkedIn AI slop patterns. Auto-detects channel, scores the original, returns a humanized rewrite with the patterns it fixed listed. TRIGGER on "humanize", "sounds like AI", "AI detection", "make it sound human", "rewrite in my voice", "voice check", "blog…
Skill Claude CodeCodex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Skill Claude Code
A toolkit for creating, testing, and improving skills for the opencode coding agent. A skill is a reusable set of instructions for a particular workflow.
Skill Claude CodeCodex
Search trusted local private or team Agent Skill collections when reusable instructions may exist outside the active skill catalog. Resolve only the selected SKILL.md instead of loading every skill into agent context.
Skill Claude CodeCodex
An image-description tool for coding agents whose main model cannot view images directly. It sends local images or image URLs to a separate vision model and returns descriptions.
Skill Codex
Operate and troubleshoot Bazzite OS systems with Bazzite-specific policy and workflow guidance. Use when Codex needs to choose the right Bazzite install tier, decide between host, container, and VM paths, diagnose services or desktop issues, set up development environments, or turn raw bazzite-mcp tool output into a…
Skill Claude CodeCodex
Create and maintain AGENTS.md files that provide AI coding agents with project context, commands, code style, and boundaries. Use when updating an existing AGENTS.md, creating a new AGENTS.md for a repository, or improving agent instructions for a codebase.
XMethues/clawchat-plugin-connect
Skill Codex
Use the locally connected ClawChat account for profile, friend, user-directory, group-leave, real mention, message-reaction, moment, and registered-app actions. Use when the user asks the agent to inspect or change its ClawChat profile, manage ClawChat friends, search users, leave a known group, mention or react in…
Skill Claude CodeCodex
Initializes the AGENTSYNC.md hub for AI agent coordination and task tracking.
Skill Claude CodeCodex
Turn-by-turn guided learning tutor. Use when the user asks to learn/explain a concept OR when they continue an ongoing lesson (answering the last question, asking for hints, saying “next”, choosing a branch). Teach in small chunks, keep a visible lesson TODO checklist, include a simple visual when useful, then end…
Skill Claude CodeCodex
Expert Ruby on Rails development with Rails 7/8 conventions, security hardening, and performance patterns.
Skill Claude CodeCodex
Write and edit clear, specific prose without formulaic AI phrasing. Use when drafting or revising text for people to read, including docs, PR descriptions, commit messages, comments, email and chat replies, essays, and social posts. Preserve facts, uncertainty, and the writer's voice.
Skill Claude CodeCodex
Portal-specialized ServiceNow skills — LLM execution blueprints with safety gates, sub-agent delegation, and context optimization.
Timmy6942025/opencode-builder-skill
Skill Claude CodeCodex
Use this skill when using the OpenCode JavaScript/TypeScript SDK (@opencode-ai/sdk) to programmatically control OpenCode, create sessions, send prompts, manage files, control the TUI, stream events, or build external integrations. Covers both full lifecycle (server+client) and client-only modes, all API methods…
Skill Claude Code
Create or revise backlog/docs/critical-areas.md, the project profile that names the areas where work always runs on the top tier. Use when the file is missing, the user asks for it, the project changed substantially, a misclassification caused a mistake, or sbl doctor reports the profile as provisional.
Skill Claude CodeCodex
An orchestrator mode that divides a large coding task into separate jobs and assigns them to worker agents that can run in parallel.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: