Platform-neutral Agent Skill for auditable Hong Kong pre-owned Rolex inventory monitoring.

Agent skill: no fix without a failing reproduction — evidence sweep, ranked hypotheses, minimal failing test, flaky-bug forcing protocol, and a repro dossier that hands the fixer a ready-made regression test

One canonical hub for your AI agents' skills, rules & memory — shared across Claude Code, Codex, Warp, Cursor, Gemini, Grok & OpenCode via symlinks. Single-command macOS setup.

An evidence-first, agent-neutral standard and skill for auditing software changes before merge or release.

A Claude Code plugin that installs the two-gate method for production AI agents: a design gate, a ship gate, and an incident-to-eval loop that turns failures into regression tests.

Three-tier activation for Claude Code skills, subagents, commands & workflows — keep a big library dormant, activate only what each project needs. Stdlib-only, security-audited, MIT.

A compact AI coding-agent skill for designing, implementing, and reviewing boringly reliable backend APIs.

Production-oriented frontend design Agent Skill with zh-Hant, true mobile UX, evidence-bounded model routing, and Playwright evals.

An operating system for engineering: durable, opinionated playbooks (Agent Skills) for software architecture, AI/agentic systems, product engineering, and technical leadership. Read by humans, loaded by any LLM/agent.

GitHub-distributed Codex plugin with practical, evidence-driven Agent Skills for software engineering and legacy project onboarding.

Hire an agent, not a prompt. Give it a business outcome; it diagnoses your system from real data, finds the constraint, and builds self-improving agents with evals and graduated autonomy. Runs in Claude Code and Codex.

Interviews you before you build. Structured, one decision at a time - from problem to architecture - before your coding agent's plan mode takes over.

A practical framework and AI skill for critiquing agentic experiences, oversight, trust, and consent.

A lightweight Agent Skill for initializing and maintaining AGENTS.md and repository docs.

8 AI学习诊断工具 — 卡在哪用哪个，不卡不用。Hermes/Claude Code/Codex/Cursor/Trae 五端兼容。

Agent skill: evidence-based feasibility + migration strategy for architecture transformations (language ports, standalone→SaaS, vanilla→framework) — dependency census, difficulty heatmap, GO/PARTIAL/NO-GO verdict, parity-gated roadmap

Open-source agent skills & tools from Growth Garage. First up: kb — a knowledge base for AI agents that maintains itself.

Agent skills for sourcing startup deals with Frontrun — pre-round signal from 1,000+ investor follow graphs on X. For Claude Code, Cursor, and any MCP-capable agent.

Local-first health and fitness Agent Skill for Hermes, WeChat, Google Health, and Excel

Evidence-backed Seedance 2.0 prompt engineering skill for Codex: Dreamina, BytePlus, Volcengine, Fal, multimodal references, editing, and prompt linting.

A Claude Agent Skill that sharpens rough prompts using Anthropic's own prompt-engineering guidance.

Lower LLM costs for coding agents: delegate implementation to cheaper models and reserve frontier-model tokens for evidence-backed final review.

An LLM wiki for Obsidian: a markdown knowledge base your AI agents compile and maintain under written law. 32 skills for Claude Code and Hermes, a zero-dependency Python CLI, and a vault template governed by an 11-law constitution.

Specification-Driven Development for AI agents — 7-role orchestrator with filesystem memory. Works in Cursor, Claude Code, Codex, and 69+ agents via skills.sh.

Agent Skill for Databricks data engineering best practices

A tool-agnostic Agent Skill for writing, reviewing, and refactoring Java unit tests with JUnit 5, AssertJ, and Mockito.

An open standard for making apps steerable, shipped with a reference runtime and a skill that lets a coding agent implement it in your codebase.

Diagnose Mac memory/battery drain; only kill PIDs you've vetted.

Playground rules for predictable AI builders: exact execution, defensive testing, debugging, alignment, and less bloat.

Warp agent skills for release engineering automation — cherry-picking fixes, cutting release candidates, tracking PR status, and posting Sentry/Slack digests.

PgBeam's agent skills

A bounded-delegation engineering workflow for Codex

Assemble and verify a TanStack Start SaaS from a PRD.

opencode plugin — Hermes-style self-improvement loop (port of UniM0cha/claude-self-improving-skills + okdk7788/skill-evolution). Distills learned skills after complex work + GEPA-style measured evolution.

A Claude skill that decides whether to build an agent or a workflow, before you build it. The design-time gate, with a deterministic verdict engine.

AI agent workflow template: AGENTS.md, playbooks, trace files, and just turn-test policy checks

PM-facing AI conversation trace eval skill: north-star metrics, 1-5 scores, red/yellow/green, per-turn quote review

Local OKF bundle generator: details file/line churn, change-coupling, and generates a banner for at-a-glance structural fingerprints.

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.

A reusable Agent Skill for keeping Claude Code and Codex aligned through durable project files, handoffs, and workflow memory.

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