Agent Skills tools for opencode

by Jesse Vincent - A strong bundle of core competencies for software engineering, with good coverage of a large portion of the SDLC - from planning, reviewing, testing, debugging... Well written, well organized, and adaptable. The author refers to them as "superpowers", but many of them are just consolidating engineering best practices - which sometimes does feel like a superpower when working wit

Source for 17 Matt Pocock workflow skills - codebase design, TDD, bug diagnosis, triage, PRDs, issues, prototyping, handoff, teaching, and skill-writing guidance (MIT)

by Affaan Mustafa - Top-notch, well-written resources covering "just about everything" from core engineering domains. What's nice about this "everything-" store is most of the resources have significant standalone value and unlike some all-encompassing frameworks, although you can opt in to the author's own specific workflow patterns if you choose, the individual resources offer exemplary patterns

(67.0k ⭐) - AI coding assistant skill (Claude Code, Codex, OpenCode, OpenClaw, Factory Droid, Trae)

by tt-a1i - An Agent Skill for Claude Code that generates interactive architecture, workflow, sequence, data-flow, and lifecycle diagrams as standalone HTML. Typed JSON, local renderers, and delivery checks support source-linked node details, path tracing, themes, and export

(59.1k ⭐) - Claude Code skills that turn any codebase into an interactive knowledge graph you can explore, search, and ask questions about (Multi-platform e.g., Codex are supported)

AI-powered job search orchestrator built on Claude Code. 14-skill pipeline that evaluates jobs, generates ATS-tailored PDFs, and tracks applications. Local-first, MIT

Obsidian-focused skills for markdown, Bases, JSON Canvas, CLI workflows, and content cleanup

Arm Cloud Migration Assistant accelerates moving x86 workloads to Arm infrastructure. It scans the repository for architecture assumptions, portability issues, container base image and dependency incompatibilities, and recommends Arm-optimized changes. It can drive multi-arch container builds, validate performance, and guide optimization, enabling smooth cross-platform deployment directly inside G

(23.3k ⭐) - Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the $2B acquisition

Healthcare administration specialist with 51 sub-agents covering revenue cycle, compliance, quality, clinical ops, health IT, and payer relations

Claude Code / Codex / OpenCode agent skills for writing Chinese web novels (网文): 扫榜、拆文、写作、去AI味、封面全流程，长篇短篇都支持 | 14 skills for novel writing and long-form fiction with file-based continuity tracking. MIT.

Enterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for Codex Harness, DeepSeek Harness, and OpenCode, with unified plugins and Skills, multi-agent projects and tasks, and editable code, documents, presentations, design, and video.

(1.4k ⭐) - Agent Skill for natural-language mandates, delegated permissions, payments, escrow, and dispute resolution

by Oldcircle - An agent skill that geolocates a photo with no readable text. Single-purpose Python scripts search and rank candidates using OpenStreetMap geometry, elevation skylines, satellite imagery and street view. The answer comes with a camera position, heading, error radius and an evidence image. NOTE: Scripts involve contact with Baidu and Yandex

(4,854 ⭐) - Persistent memory for Claude Code and other agents in an Obsidian vault, with linked Markdown notes, semantic search, and a shared agent logbook

Qwen's official multimodal plugin suite packages vision, video, document, 3D, and CAD capabilities as portable skills and MCP servers across Claude Code, Codex, OpenCode, and other harnesses. It shows how to make a text-first coding harness multimodal-native without rebuilding the agent loop

Source for 18 delegation skills (delegate-setup + 17 implementer relays for Claude/Codex/Cursor/OpenCode and 13 more) — multi-agent delegation and fleet orchestration with Node built-ins only, relay never commits (MIT, docs-only — runtime not bundled)

(1.3k ⭐) - Structured deep research skill for Claude Code, OpenCode, and Codex, with human-in-the-loop controls for research workflows

Portable .agent/ folder that externalizes memory, skills, and protocols from any specific coding agent into a cross-tool harness layer. Adapters translate the same configuration into Claude Code's CLAUDE.md, Cursor's rules, OpenCode's AGENTS.md, and more — the first practical answer to harness vendor lock-in at the configuration level

by Max Ritter - Professional development environment for Claude Code with spec-driven workflow, TDD enforcement, cross-session memory, semantic search, quality hooks, and modular rules integration. A bit "heavyweight" but feature-packed and has wide coverage

Spec-driven development workflow that transforms prompts into production-ready implementations through structured planning, architecture design, and LLM-as-a-Judge based quality gates

(1.2k ⭐) - Portable skill toolkit for installing, translating, and sharing skills across Claude Code, Cursor, Codex, Copilot, and other coding agents

为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

(1.2k ⭐) - Codex, Claude Code, and OpenCode skill for image-first PowerPoint workflows

(502 ⭐) - Agent skill for turning books into animated, narrated, interactive web experiences

Cuts token use with terse answers, smallest-code-that-works rules and tool-output compression

CLI that turns agent skill verification into repeatable unit tests: it generates task and grader pairs from a SKILL.md, runs multi-trial evals against Claude, Codex, Gemini, or OpenCode, and reports pass rates with a CI-ready threshold. Fills the gap between shipping a skill and knowing an agent actually discovers and invokes it correctly

Local-first RAG knowledge vault and MCP server. Compiles raw sources (books, notes, transcripts, exports, datasets, slide decks, files, URLs, code) into a durable markdown wiki with a knowledge graph and a hybrid SQLite FTS plus embeddings index. The bundled MCP server (npx -y @swarmvaultai/cli mcp) gives Claude Code, Codex, OpenCode, and any MCP client page search, page reads, source listing, que

138 bilingual AI marketing skills (69 VN + 69 Global) for Claude Code, OpenCode, Codex, VS Code. Four role SOP packs — content, design, performance, leader ops — plus strategy, personal brand, AI avatar, dropshipping, design master, knowledge library. 4 regions (US/EU/SEA/LATAM) + Vietnam 2025-2026. Companion: opa-kit.

55 rigorous skills for Claude Code, Codex, OpenCode 1 and 2, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more.

Adversarial AI bug hunter with auto-fix - multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs

A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser. Anti-hallucination by design. Self-hosted, free, unlimited.

Matt Pocock 技能集的中文翻译版 — 地道中文，原汁原味的技术术语。基于 mattpocock/skills 复刻。每日中午12点钟同步

(1.2k ⭐) - Precision PPT design skill for OpenCode, Claude Code, and Codex, with 40,000+ styles, Build Mode control, AI image generation, and fully editable PPTX output

Re-explains the assistant's last reply or pasted text in plain language

Mines your local Claude Code, Codex, and Cursor session logs into a you.md working profile your agent loads before every task: what you reject, what "done" means to you, when you ask for proof, how you actually work. Local-first, MIT, one command: npx skills add ohad6k/ditto

by Continuum AI - Records a Claude Code run through a local proxy and replays it offline, reproducing it byte-for-byte with the network off, or forking it from any checkpoint onto a different model. Capture happens below the harness, so shell exit codes, per-turn file changes and MCP calls land on the same timeline as the model traffic. (NB: Status: "Early")

X API & Twitter scraper skill for AI coding agents -- tweet search, user lookup, follower extraction, engagement metrics, giveaway draws, trending topics, account monitoring, and 19 extraction tools

MIT-licensed local-browser social research agent where a Jev-compatible choice server selects bounded socai CLI search and inspection operations, retaining source posts and comments beside the report; supports loopback Kev and Simple Jev backends

Local-first TUI and report generator for AI coding-agent session logs. Tracks cost, tokens, latency, tool failures, health, diffs, and CI gates across Claude Code, Codex CLI, Gemini CLI, Qwen Code, Cline, Cursor exports, Aider, OpenCode/OpenClaw, Kimi CLI, and generic JSON/JSONL traces

Realtime and batch video workflows: capture screen/audio, ingest URLs/YouTube/RTSP, transcribe, index, search, generate subtitles, edit timelines, and stream HLS output

Apple-authored SwiftUI and platform guidance extracted from Xcode

Source for the ax-extract-workflow skill - reconstruct workflow behind past coding-agent artifacts using local ax sessions, commits, skills, and tool traces (AGPL-3.0-only)

Drive your real, logged-in Chrome via CDP from Claude Code, Codex, or Gemini CLI: semantic snapshots, real mouse clicks, human handoff for captchas and logins, HAR capture and replay

Deterministic QA for web pages, with a Gemini CLI skill. assay opens the page in Chromium with Playwright, drives every control, and reports where the page contradicts itself, with no LLM and the same result on every run. The skill tells Gemini CLI to run assay after it changes a page and report what it found. Install with pip install assay-ui, then add the skill file. MIT

Official UIZZE source for the free anti-ui-slop skill—product-specific UI references, design contracts, required states, and a hard finish gate grounded in 800,000+ real web and iOS screens (MIT)

Turns a topic into a themed HTML slide deck; exports to PowerPoint and PDF

Local service orchestrator with a stdio MCP server for inspecting and controlling development services, logs, ports, actions and run history across live project runtimes

Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini CLI, OpenCode, OpenClaw, Windsurf, Aider, Copilot, and AGENTS.md-compatible agents

15 writing-style skills: 8 measurable frameworks (plain language, ASD-STE100, AP journalism, GOV.UK, business BLUF) and 7 character voices, each with a verify checklist

Source for the open-dynamic-workflows skill - open-source dynamic multi-agent workflow engine that plans, orchestrates, and adversarially verifies parallel AI coding agents across OpenCode, Codex, Antigravity, and VS Code (MIT)

Source of the meteora-dlmm-pool-screening skill - read-only screening and ranking of Meteora DLMM pools from public APIs (MIT)

Cross-agent long-term project memory via .memory-bank/ for Claude Code, Cursor, Windsurf, Cline, Kilo, OpenCode, Pi Code, Codex — bundles TDD / SOLID / Clean Architecture / FSD rules and 18 dev-toolkit commands

Let OpenCode ring your iPhone, read you a question and return your spoken answer

several models review the same code, one merged report

Source for the unship skill - local workflow for comparing AI-generated UI variants in a real app, then keeping one option and cleaning up temporary alternatives (MIT)

AI Agent Skill that deploys any application to Kubernetes from Claude Code, Cursor, OpenCode, and 30+ AI coding tools. Analyzes codebases, creates Dockerfiles for 12+ frameworks, provisions databases, deploys via CLI+API or Terraform, and auto-fixes deployment failures. Install: curl -fsSL https://skill.qovery.com/install.sh | bash

Source for the FlowHunt automation discovery audit skill - workflow intake, tool-by-tool audit, and opportunity prioritization for productivity automation

Full-cycle software development skill — plans, builds, tests, lints, fixes bugs, and writes production-grade docs. Auto-detects project state and adapts its 8-phase pipeline. Works on 9 AI coding agent platforms (Apache 2.0)

Self-improving control kernel (DAGx AGI Kernel): hard approval stops for irreversible actions, evidence-gated completion, and a self-learning playbook with drift governance. Behaviorally evaluated; works across Claude Code, Codex, Hermes, and OpenCode

Enforces 100% test coverage for any JavaScript/TypeScript project. Works with Vitest, Jest, react-scripts, and more

Decomposes complex requests into structured, AI-friendly task sequences

Source for the browser-extension-launch skill - end-to-end Chrome extension product design, implementation, real-browser acceptance, packaging, and store-launch workflow (MIT)

Source for opencode behavior, permission, skill-suggestion, and smart Git automation skills

Source for the agents-generator skill - project-specific AGENTS.md and companion rule generation with package-manager detection, monorepo handling, dry-run/update modes, backups, and validated commands (MIT)

Source for the sshepherd skill - credential-isolated SSH operations, service control, logs, configuration changes, Postgres introspection, and declarative deploys through preconfigured aliases (MIT)

Reviews plans, code, and commits with multiple coding CLIs

Source for usage-engineer

Source for the workorai skill — agent kit workflows (MIT)