opencode skills

1,424 tagged opencode, measured the same way as everything else here.

Browse within: prompt-engineering 230opencode-plugin 83ai-coding-agent 721c-development 711c-enterprise 71bsl 71gemini-cli 67Orchestration 65plugin 56operations 51award-flights 48travel 48gemini 46ai-coding 45

vibeweaver-mini

313

logandoo/vibeweaver

Skill Claude CodeCodex

★ ALWAYS LOAD THIS SKILL BEFORE WRITING ANY CODE. MANDATORY for every coding task: implementing a feature, fixing a bug, writing a function, debugging, writing/running tests, building a frontend, starting a service, scaffolding a project, or modifying any codebase. If the task involves writing or changing code, load…

not rated 2 5d ago A 97 tokens original MIT

skillgrep

314

vrslev/skillgrep

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.

not rated 2 8d ago A 39 tokens original MIT

vision

315

TIanle-art/agent-vision-skill

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.

not rated 2 28d ago A 121 tokens original MIT

bazzite-operator

316

rolandreads/bazzite-mcp

Skill Claude CodeCodex

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…

not rated 2 6mo ago A 77 tokens original MIT

agents-md

317

adampoit/ai

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.

not rated 2 9d ago A 55 tokens original MIT

gh

318

adampoit/ai

Skill Claude CodeCodex

Use the GitHub CLI (gh) for repository operations including PR and issue inspection, GitHub search, checks, and API calls. Use when a user asks for GitHub URLs, PR metadata, issue details, checks, or repository automation.

not rated 2 9d ago A 51 tokens original MIT

jj

319

adampoit/ai

Skill Claude CodeCodex

Use Jujutsu (jj) for version control operations including status, history, diffs, commits, rebases, splits, squashes, and Git interop. Use when a repository is initialized for jj or the user asks for jj/Jujutsu workflows.

not rated 2 9d ago A 55 tokens original MIT

clawchat-connect-qa

320

XMethues/clawchat-plugin-connect

Skill Claude CodeCodex

Run evidence-based acceptance tests against the real ClawChat Android debug app on clawlingdev:5558, the locally installed ClawChat Connect service, Connect Client, Agent Bindings, group intake, commands, Runtime interactions, attachments, ClawChat tools, and Liveware. Use when validating a local Connect build end to…

not rated 2 7d ago A 102 tokens original MIT

clawchat-core

321

XMethues/clawchat-plugin-connect

Skill Claude CodeCodex

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…

not rated 2 7d ago A 100 tokens original MIT

clawchat-liveware

322

XMethues/clawchat-plugin-connect

Skill Claude CodeCodex

Deploy a local web service as a new Liveware app and register it directly in ClawChat through the bound ClawChat Connect agent. Use only for explicit Liveware or ClawChat App creation, inspection, access-policy, tunneling, deletion, and deployment requests; do not trigger for generic web development or generic…

not rated 2 7d ago A 72 tokens original MIT

init-agent-sync

323

Hadi99K/AGENT_SKILLS

Skill Claude CodeCodex

Initializes the AGENTSYNC.md hub for AI agent coordination and task tracking.

not rated 2 4mo ago A 20 tokens original MIT

wrap-phase

324

Hadi99K/AGENT_SKILLS

Skill Claude CodeCodex

Wraps up a development phase by cleaning AGENTSYNC.md, summarizing work, and committing changes.

not rated 2 4mo ago A 24 tokens original MIT

guided-learning

325

static-var/guided-learning

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…

not rated 2 6mo ago A 78 tokens original MIT

cloudflare

326

andresquirogadev/skillsense

Skill Claude CodeCodex

You are working with Cloudflare Workers / Pages. Apply these conventions.

not rated 2 4mo ago A 0 tokens original MIT

rails

327

andresquirogadev/skillsense

Skill Claude CodeCodex

Expert Ruby on Rails development with Rails 7/8 conventions, security hardening, and performance patterns.

not rated 2 4mo ago A 0 tokens original MIT

ruby

328

andresquirogadev/skillsense

Skill Claude CodeCodex

Expert Ruby development with modern idioms, performance patterns, and testing best practices.

not rated 2 4mo ago A 0 tokens original MIT

anti-slopper

329

marcelolebre/anti-slopper

Skill Claude CodeCodex

Write like a human and avoid AI slop. Use this skill whenever you are producing prose for a person to read: PR descriptions, commit messages, docs, READMEs, comments, design notes, Slack/email replies, blog posts, tweets and X/LinkedIn posts, launch announcements, release notes, or any explanatory text. It gives…

not rated 2 2mo ago A 183 tokens original MIT

bugfix

330

fco3lho/unlazier-ai

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.

not rated 2 2mo ago A 38 tokens original MIT

code-review

331

fco3lho/unlazier-ai

Skill Claude CodeCodex

Use when reviewing code for quality, best practices, bugs, or adherence to coding standards. Checks against Simplicity First, Completeness, Structure, Style, Correctness, Naming, Performance, Testability, and Async rules.

not rated 2 2mo ago A 49 tokens original MIT

refactoring

332

fco3lho/unlazier-ai

Skill Claude CodeCodex

Use when refactoring, simplifying, or restructuring code. Follows Surgical Changes and Simplicity First: touch only what's needed, avoid scope creep, keep it simple.

not rated 2 2mo ago A 37 tokens original MIT

andrejkaxz/Vanessa_for_AI

Skill Claude CodeCodex

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.

not rated 2 7d ago A 105 tokens

andrejkaxz/Vanessa_for_AI

Skill Claude CodeCodex

A skill for planning the structure of a new or empty Vanessa Automation project, including its `.feature` files, scenario folders, and library folders. Vanessa Automation is a tool for testing 1C applications.

not rated 2 7d ago A 74 tokens

jadatorin/tradingview-opencode-agent

Skill Claude CodeCodex

TradingView Desktop AI assistant via MCP. Dispatcher a 5 sub-skills especializadas: chart-analysis, pine-develop, replay-practice, multi-symbol-scan, strategy-report.

not rated 2 1mo ago A 44 tokens original MIT

pine-develop

336

jadatorin/tradingview-opencode-agent

Skill Claude CodeCodex

Full Pine Script development loop — write code, compile, fix errors, iterate. Use when building a new indicator or strategy in TradingView.

not rated 2 1mo ago A 32 tokens original MIT

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: