Project-scoped OpenCode TUI plugin for grouping and managing MCP servers, custom agent skills, and pinned vendor skill registries.

Shell-based desktop automation for coding agents (not vision Computer Use)

🛒 Kaspi shopping skill for Claude Code and Codex: live search, seller-verified delivery, comparison, and official app QR codes.

Cross-agent interviewing copilot for evidence-driven guides, live probes, and multi-round handoffs

Claude Code plugin: 12 NestJS best-practice skills (90 rules) grounded in the official NestJS docs

Autonomous Multi-Agent System

dig（探骊）— Socratic requirements excavation for coding agents: hypothesize, ask what matters, loop until clean, confirm a clarity memo before work begins. Claude Code first-class, Agent Skills compatible.

Destination-event curator for travelers — a 17-skill Codex plugin that finds taste-matched events in your fixed trip city and dates, gated by travel-worthiness and local-insider judgment. Built by METAL.

Claude Code skills for SvelteKit, canvas, drag-and-drop, and SVG animation

Quitting is not a fight you win, it is a match you stop attending. A quit-smoking sponsor for AI agents: it does not coach the boxing, it walks you out of the arena. Evidence-based, open protocol, zero shame.

Playwright FieldKit: gives coding agents hands and eyes on the web — crawl, debug, record, and test live sites via deterministic scripts; portable Agent Skill for Codex, Claude Code, Antigravity, and Cline

From context to installable agent skills - research packs in, validated skills.sh-ready skills out. Scaffolding, eval-first authoring, validation, and deployment included.

A lightweight CTO workflow for Codex that clarifies requirements, adds risk-based guardrails, and orchestrates Superpowers.

기획-개발 핸드오프 표준 킷 — 편집형 기획서 템플릿(HTML), 작성 예시, 에이전트 스킬(handoff-spec)

Open-source Agent Skill for scanning Binance markets using MA crossovers, Wilder RSI, volume analysis, and validated trade setups.

Use this system prompt to strip AI-generated style patterns and force chatbots to write natural, human-like text across all major LLMs.

Agent skills that stop your coding agent from adding a fifth copy of the same function. Build-time reuse checks, PR-time duplication review, and a scheduled sweep.

AI life-design coach for Claude Code and Codex. Find the question under your career and life goal, map your future paths, and start an experiment now.

Turn discussions into structured, human-readable, and optionally interactive HTML knowledge maps for Codex and Claude Code.

Evidence-gated Agent Skill for mechanism-first, citation-traceable scientific reviews with LaTeX, rendered-page QA, and multilingual rules.

Portable Agent Skills for test-first development, evidence-based debugging, code review, and reviewable Git history.

Export public YouTube creator transcripts to SRT and clean Markdown with Agent Skills.

Claude Code / agent skill: safely install, replace, restore & edit crontabs without silently losing jobs (back up → install via stdin → verify).

FBAR Proof Kit: local, source-linked support packets from foreign-bank statements.

Skills + hooks for Claude Code: prompt-compile makes the agent write itself a high-quality task brief before building — define-do-verify, deterministic trigger, fresh-context execution.

DesignOS — end-to-end design skill for AI agents: idea → direction → design system → screens → handoff, with verified contrast (WCAG+APCA) and anti-generic craft. Install: npx skills add ravipalwe/designos

Claude Code skill for small-business acquisition due diligence — SDE normalization, valuation sanity checks, red flags, and a phased diligence checklist.

アジャイル/スクラムの規律を、AIとの協働に適用する — Claude Code / Agent Skills を活用したAI駆動開発（AIDD）の実践ガイド

Unofficial Codex adaptation of Microsoft Power Platform Skills with telemetry hard-disabled and automated upstream sync.

Bilingual Agent Skills for evidence-driven content, search, and knowledge work.

Fan-out discipline for AI coding agents - scout, partition, wave, QC, single-writer apply, receipt. Bounds a swarm to the solo-cost budget; does not make models smarter. Zero-dependency, Phoenix-13. Part of TheColliery.

Audit-first AI design review skill. Find implementation blockers, define falsifiable experiments, and keep residual risks visible.

Local Skill center for Codex, Claude Code, Hermes, and Agent Skills-compatible workflows

One source of truth for AI coding agent instructions — scaffolds AGENTS.md, CLAUDE.md, GEMINI.md and a layered .agents/ structure, and updates them without clobbering hand-written rules.

Your project's second mind — a Claude Code skill that turns every session into structured, linked Obsidian notes your AI can reference.

Kill-tested guard skills for AI coding agents , self-invoking quality gates that catch AI failure modes in security, tests, docs, dependencies, and diffs before the agent says "done." Works with Claude Code, Codex, and Cursor.

Run Claude Code Workflows (CCW) on Grok: single install path plus a runtime translation layer

帮助用户快速配置Hexo的一个主题Modern Duang，同时帮助用户排查部署可能遇到问题。也可以帮助用户自定义主题。| Help users quickly configure Modern Duang, a topic of Hexo, and help users troubleshoot possible deployment problems. It can also help users customize themes.

Official Tersign agent skills — produce, verify, and submit counter-signed evidence from any agent framework (Claude Code, MCP, Internet Court).

Claude Skill: look up & cite verifiable GPU/compute rental reference prices (spot/on-demand/DePIN) from the public FLOPS Index. Key-free.

A portable Agent Skill that reverse-engineers any codebase into a reusable engineering constitution. Install: npx skills add 3bsalam-1/architecture-extractor

Evidence-first Agent Skill that verifies work before reporting completion.

Pythurion helps coding agents write Python you’ll want to maintain: correct, minimal, and idiomatic

A cited, test-enforced guide to writing safe, correct shell (Bash, Zsh, POSIX, Nushell) — for humans and AI coding agents.

Repository-local Codex skill package for media processing workflows, including video, audio, image, subtitle, metadata, and batch media preparation tasks.

Agent Skills and hooks for maintaining high-quality open-source Python packages - an agentic engineering setup covering linting, testing, packaging, releases, and CI quality gates.

AI skill for personal weekly rpg-style retrospectives where you choose the story

Agent skill for complete, recoverable UI states beyond the happy path.

An Agent Skill for structuring, drafting, reviewing, and validating academic research writing workflows.

コーディング依頼を受け取ってからPull Requestを作成し、得られた知見を次回へ活かすまでを支援するCodexプラグイン

A portable, tool-agnostic, plan-gated pipeline for building quality software with AI agents.

Production-grade agent skills for Flutter, DevOps & AI Governance — forged in real projects, governed by constitution, verified on device.

Agent skill that generates an interactive dependency map of your AI harness (skills, agents, commands, MCP servers)

Free Agent Skills that pressure-test AI project ideas and diagnose running systems. From the AI Problem Framing course.

Universal Kimi WebBridge Agent Skill for OpenAI Codex and Anthropic Claude Code

Nstup Taste gives your AI-generated interfaces actual taste. No more generic SaaS templates, purple-blue gradients, 3-column card layouts, or Inter font.

Turn Cursor into your personal health-data analyst for Apple Health exports — evidence-graded, confound-disciplined, cold-start honest

Dev dependency to bundle your NuGet with agent skill

Esteira de engenharia de software com IA em português — 27 skills para Claude Code + painel web com aprovação humana em portões. Da ideia ao lançamento, com processo.

한컴 HWPX 시각검수를 빠르고 안전하게 | Fast, fail-closed Hancom HWPX visual QA