Portable Codex and Claude skill for cross-functional delivery, independent review, and evidence-backed acceptance.

J-Lens-informed reasoning observability skill for OpenClaw, Claude, Codex, and AI harnesses

Codex skill for reviewing agent failures, avoiding rule bloat, and choosing the smallest verified improvement.

Eval harness for groundwork agent skills: deterministic scoring + LLM-as-judge, hallucination traps, regression gate across Codex/Claude/custom CLIs

Governed multi-agent engineering for Codex. Bootstrap the bundled ai runtime and initialize each target workspace; empty workspaces are supported.

An evidence-driven Agent Skills suite for GPGPU performance engineering, from kernels and compilers to memory, resource, and runtime-state management.

Portable AI-agent skills for Claude Code, Codex, OpenCode, and Grok: Fan Solo — multi-agent orchestration, processes, and durable state for Solo (SoloTerm) — plus WebAuthn/passkey browser testing for Stellar smart accounts

Evidence-driven, risk-ranked deep code review skill for Codex and Claude Code

focused workflows for building and maintaining aiogram bots

Local-first project context, verification gates, and repo-scoped MCP for coding agents.

Agent Skill for deploying an AI-powered paper research radar for any academic field

The Cohesivity agent skill: on-the-fly backend infrastructure for AI agents. Install with: npx skills add cohesivity-org/cohesivity-skill

1:1 WorkBuddy port of oh-my-codex — 46 catalog-driven skills (30 active + 16 deprecated), bilingual docs.

Point your coding agent at a website codebase: it writes user stories into Excel, tests them with Playwright, and writes the bugs back. Works with Claude Code, Codex, Kilo Code, OpenCode and GitHub Copilot CLI.

Governed SolarWinds Orion + PRTG ops: canned SWQL, alert rollup, 31 MCP tools (preview)

Operational-hardening playbook for driving codex / opencode / agy headlessly and in parallel — the stdin deadlocks, silent empty reads, SQLite races, and truncated outputs the vendor docs never warn about, each with the one-line fix.

Evidence-first process skills for coding agents: codebase analysis, solution design, minimal implementation plans

Cursor agent skill: evidence-backed 5-year survival & moat forecast for any codebase — Durable/Eroding/At Risk/Terminal verdicts + PDF.

A self-improving AI Agent Skill that rewrites vague prompts into senior-level specs before building.

An Agent Skill that converts rough software requests into precise, execution-ready coding-agent prompts.

Mine your coding-agent session history (Claude Code, Codex, opencode, pi) to discover and build the skills you or your team should create

A Claude skill that turns a production AI agent incident into a golden eval case. The loop that feeds the two gates.

A Claude Code skill to audit and sync project context (CLAUDE.md, skills, project memory, and settings). Keeps your AI assistant fully aligned with the codebase at the start of new sessions or after major changes.

바이브 코딩에 규율을 입히는 에이전트 스킬 모음 · Agent skills that bring discipline to vibe coding. Install: npx skills add sjsylee/skills-hub

Agent Skills for safe local Numera workbook automation.

Agent Skill that turns terse intent into structured, verifiable prompts

Official MailKite skills for coding agents — npx skills add mailkite/agent-skills. Email for every product you ship: receive as a webhook, send over a verified domain, give an agent its own inbox.

One memory. Every AI. Agent skill + Claude Code plugin that teaches AI agents to use the user's MemoryPlugin long-term memory automatically.

Agent skill for bounded multi-agent strategy selection, dispatch, durable state, review gates, and recovery.

Agent skill: safe re-initialization of project agent knowledge — salvage-verify old docs, backup-gated deletion, fresh codebase read, direction interview, rebuild cited AGENTS.md/ARCHITECTURE.md/ROADMAP.md

See what your AI agent actually knows — an interactive map of your plugins, skills, hooks, and MCP servers, what references what, and what fires on a prompt. Zero dependencies.

Public agent skills for Jira-backed development workflows

Battle-tested skills for Claude Code and other coding agents — distilled from a real production automation setup

HeyEddi Cursor Agent Skills hub — 20 skills, agent eval suite, git subtree distribution

Bilingual Codex skill for AI product idea brainstorming, adversarial pressure testing, validation, and concept briefs.

The working discipline of Claude Fable 5 as installable skills — method, taste, and judgment for any Claude model, with a built-in eval suite that measures the delta.

Open-source factory for generating, validating, and publishing reusable Agent Skills

Engineer production-ready Codex skills with behavior contracts, quality lint, and forward testing / 将 Skill 构建从 vibe prompting 变成工程化流程

PASS/STOP pre-action receipts for Codex and AI coding agents before edits, handoffs, commits, or publish steps.

Cross-platform agent-to-agent comms: an append-only in-repo mailbox where AI coding sessions coordinate — and grill each other's handoffs for evidence.

Agent Skills

Portable agent skills featuring Agent Workflow 1.0: native parallel teams, evidence-based review, and fresh-context verification.

netriage — 先分诊、后开方：给 AI agent（Claude Code / Codex）用的 Linux VPS TCP/网络循证调优 Skill。Evidence-based VPS TCP tuning: question, inspect, test, recommend, apply only after approval.

Production-grade Expo / React Native foundation as a portable Agent Skill (Claude Code + OpenCode): architecture, config, patterns, testing, and Expo gotchas.

Agent Skill for delegating work through named real-world expert personas

Five narrowly scoped Codex engineering skills that preserve native model judgment.

开源 AI PPT 大纲与演示叙事 Skill：生成故事线、逐页标题、证据、视觉形式和讲者过渡。

Claude Code skill: deep web research offloaded to Codex (GPT-5.5). Claude orchestrates; Codex searches.

Convert OpenAPI/Swagger into Agent Skills–compatible packages (SKILL.md + scripts + reference) for Claude, Cursor, and other skill hosts — .NET NuGet CLI with auth-aware dispatcher.

Three agent skills to set up, ingest into, and lint a Karpathy-style agent-maintained wiki in your repo

A lightweight Customer Relationship Management (CRM) application and automated B2B lead generation pipeline custom-optimized for localized business outreach within Kenya.

AI tools, hooks, skills, and prompts I actually use day to day — each with a what/why/how write-up

Offline, evidence-backed audits for portable Agent Skills across Codex and GitHub Copilot.

Agent skill: query Postgres/MySQL/MongoDB in plain English, safe read-only SQL, database alerts and dashboards via the AI for Database API. Works with Claude Code, OpenClaw, Codex.

Coordinates parallel coding agents with worktree isolation: one writer per worktree, bounded task contracts, and merge receipts.

Portable AI-agent skills (SKILL.md) for accommodation search, availability, pricing, cross-OTA comparison & reviews via StayingAPI. Works with Claude, MCP and more. MIT-0.

Map the unknowns of a task before you build it. A five-stage interview that hands you a four-quadrant map you keep.

AI agent skills for Claude Code, Cursor, and Codex — built for AI architects. Install: npx skills add frankxai/skills

Local acceptance gate for coding-agent changes — skills-only plugin for Claude Code and Codex