Pi skills for recognizing knowledge-base opportunities and deciding what belongs

Open agent skills for the skills.sh ecosystem — browser, docs, mail, media, security, networking, orchestration, and more.

Portable agent workflow framework for Codex, Claude Code, and OpenCode—shared project context, focused skills, independent review, and safe updates.

Portable Codex skills for writing source-grounded MEC and UAV-MEC papers

Mine Codex session feedback into reviewable, scoped AGENTS.md improvements.

⚔️⚽ AgentDuel — two AI agents stake real USDC on opposing World Cup picks via Injective x402; deterministic settlement that replays hash-identical, pays exactly once. Injective Global Cup 2026.

Open problem validation: public evidence database and installable agent skill.

Agent skill for Claude Code and Codex: idempotently replace-or-append a Markdown section without corrupting code fences - fence-aware heading scans, fixed-marker boundaries, and an apply-twice-diff-zero verification recipe, with a tested reference implementation.

Project-agnostic skills for governed Agent-assisted product and UI design

Agent Skill + stdlib-only CLI to stream multi-GB Excel dumps into SQLite with flat memory

Agent skill for Solana Native Subscriptions and Allowances

Open-source agent skills for OpenAgent — plug Claude Code, Cursor, and other MCP-capable agents into your workspace.

Model-agnostic realistic video prompt design, preflight, and explicit executor handoff for AI agents

Convert PDF files to editable Word documents while preserving original layouts for AI agent workflows.

Evidence-first Agent Skills for reliable software maintenance: risk mapping, bounded audits, test-first fixes, and persistent quality memory.

A portable, receipt-backed execution loop skill for Codex and Claude Code.

Machine-checkable control contracts between agent harnesses and repeated agent loops

Agent Skill routing GitHub bounties, CI failures, Actions logs, agent readiness, and MCP schema drift to six paid read-only x402 tools

Portable, tested skills for reasoning and software delivery across AI agents

Trim Claude Code system-prompt bloat: measure with a logging proxy, then deny unused tool definitions and disable features via settings.json. Method from aihero.dev, packaged as a skill.

Personal AI Agent Skills collection for Cursor and Claude Code

Agent skill: one security incident mapped across EU reporting regimes (NIS2, GDPR, DORA, CRA) — duties, authorities, deadlines, cited live via the Ansvar Gateway MCP connector

An Agent Skill that teaches your coding agent to design other (sub)agents well.

Claude Code 5-step dev pipeline skills: requirements, architecture, backend-first, frontend, integration & docs (contract-driven)

Evidence-aware AI workflow sample for software bug triage by CodeCurrent Studio

Evidence-gated Agent Skill for deep, invariant-first bug-bounty research, source-code auditing, duplicate analysis, and report readiness.

Portable orchestrator/worker harness kit for AI-assisted development

Reusable Codex and agent skills with safe multi-agent orchestration

Configuração global do Cursor: user rules, agent skills, slash commands e hooks com scripts de instalação.

Local-first lint checks for agent automation runbooks

Codex skill plugin for safe Korean stock research and GitHub Actions paper-trading automation

Codex plugin for governing large software projects from discovery through release and operations.

Open-source-ready factory owner skill suite for Codex

GitHub CLI extension to link project-local Agent Skills to explicit, versioned GitHub sources on macOS and Linux.

Difficulty-based model & reasoning-effort auto-routing skill for AI coding agents (Claude Code, Codex, Agent Skills standard). BYOK.

Agent Skills for designing and implementing Model Context Protocol (MCP) servers - server architecture, tools, resources, prompts, transports, authorization, testing, and deployment.

Skills for creating polished screen-recording walkthrough and tutorial videos of web apps, with smooth scripted mouse movements, zoom effects, and explanation cards.

Agent skill: server-enforced STRIDE + LINDDUN threat modeling with cited EU security-obligations mapping via the Ansvar Gateway MCP connector

Evidence-backed, decision-scoped project handoffs for Codex

Stop coding agents from shipping generic UI with 800,000+ real web and iOS screens and a hard finish gate.

Divan — vibe coder vezirler kurulu. Claude Code / Cursor / Codex skill paketleri: Sadrazam (uctan uca orkestrator), planlama, TDD, debugging, UI/UX, React.

An Agent Skill for dependency-aware parallel work with clear ownership, coordination, integration, and independent verification.

Claude Code implementation routing through Codex CLI, with Claude-owned specification, review, and verification.

Agent Skill: teach AI coding agents to deploy HTML/static sites to Cloudflare Pages the right way（把網頁部署到 CF Pages 的標準作法）

A portable agent skill for daily Threads content, weekly audits, and engagement strategy.

Claude Code skill: exploratory smoke-sweep + deploy verification for running/deployed web apps. Catches bugs that pass typecheck and return 200 but are wrong (dead DB columns, silent query failures, fake stats).

Switch AI coding agents without losing project memory — verified handoffs, Git-aware checkpoints, and resumable repository state.

Open-source Claude Agent Skills for DevOps engineers, by DevOps Daily — https://devops-daily.com

Seven x402 decision APIs and installable agent skills for GitHub bounties, CI, skill security, and MCP drift

Portable /graph agent skill for Claude Code and OpenAI Codex — drafts agent graphs (nodes, checkpoints, routes: a state machine) for the jobs you run every week, validated mechanically

Agent skill for Claude Code and Codex: a documentation framework for multi-session, multi-agent development - REQUIREMENTS / as-built ARCHITECTURE / REPORT / living HANDOFF split, START_HERE kickoff files, canonical-source discipline, and task ledgers that double as delegation specs. Bilingual (EN/JA) templates.

Version-controlled agent skills and cross-platform installers

Git-backed SSOT and immutable skill projections for Codex, Claude, Pi, and other agents

🔒⚽ LineLock — pay-per-pick World Cup edge API on Injective x402: the USDC receipt IS the pre-kickoff timestamp; free public CLV ledger, losses included. Injective Global Cup 2026.

Model orchestration doctrine for Claude Code — route tasks across Opus 4.8 / Sonnet 5 / Haiku 4.5 / Fable 5, dispatch parallel subagents, and verify what they report back.

Agent skill for Claude Code and Codex: create PRs from a temporary git worktree off origin's default branch when the main checkout is dirty, behind, or shared with other agents - with merge-mode-aware cleanup guards.

Portable Agent Skills for non-RAPP systems and launchpads for single-file RAPP agents

World Cup sideline AI agent on Injective — CCTP, x402, MCP, Agent Skills, and binary options in one workflow.

Agent Skill for evidence-backed memory, reusable procedures, and daily feedback governance inspired by Engineering Cybernetics.