一笔好决策只需要三件事：时机对不对 (天时) / 公司行不行 (地利) / 自己有没有犯傻 (人和)。3 层 6 步分析引擎 + 多源数据采集 + FastAPI + Next.js 14，覆盖 A股 / 港股 / 基金。

Plug-and-play AI workflow that turns Claude Code, Cursor, Copilot or any AI agent into a senior SaaS engineer. Hexagonal architecture, multi-tenant by default, 31 skills + APEX workflow.

Supercharge BMAD with Claude Code Goal Mode, Auto Mode, and Auto Memory. Transform Epics into autonomous run-until-done workflows that plan, implement, test, validate, document, and continuously learn from project knowledge to accelerate software delivery.

A continuously evolving personal Agent Skill for reproducing lailai's writing, thinking, design, and working style.

AI agent skill for Godot 4.3+ GDScript game dev

English to Hungarian translation skill for Claude. Idiomatic, native Hungarian instead of literal calque, built on the most common EN to HU translation mistakes.

Agent skills by Titus Kirch — installable via skills.sh in Claude Code, Codex, Cursor, OpenCode and friends.

Claude Code skill for configuring and driving the WezTerm terminal emulator (Lua config, CLI, keybindings, multi-pane workflows, agent send-text/get-text loop)

搞钱学姐团队播客工作流：大纲、逐字稿剪辑、标题、宣发、ShowNote 与视觉风格 Skills

Ultra-low-noise professional communication mode for coding agents.

Strategic software design guidelines for AI coding agents. 15 behavioral rules + critique/audit commands based on A Philosophy of Software Design by John Ousterhout.

Official agent skills for the Clear Street API

🎓 保研/申研个性化套磁信生成器 | An AI agent skill for generating highly personalized cold emails for grad school applications. It automatically crawls professor profiles to match your background, ensuring sincere and relevant outreach.

Single-skill PM operating system: capture intent, diverge by PM domain, draft the smallest useful artifact, verify with an independent critic. 68 pm-skills frameworks folded into one skill, supergoal-style.

A multilingual Agent Skill Pack that turns AI agents into guided learning coaches.

A Claude Code skill that turns a mission into a self-maintaining, self-repairing agent harness.

AI coding agent skill for UI motion design. 111 production-ready effects across 13 categories — describe your product scenario, get CSS/JS code you can ship. Works with Claude Code, Codex, OpenClaw, and any SKILL.md-compatible agent.

Agent skill for pixel-grounded chart data extraction

13 Claude Code Agent Skills for Google Ads (research, planning, build, optimization, reporting) with a premium visual dashboard and a live example per skill.

Agent skill for turning YouTube videos, playlists, and search topics into timestamped context packs

A localized intelligent agent platform suitable for human-machine romance: cclaw (agent side) + eclaw (backend) + wclaw (frontend) + xCrab (AI gateway). 一个适合搞人机恋的本地化智能体（Agent）平台：cclaw（代理端）+ eclaw（后端）+ wclaw（前端）+ xCrab（AI 网关）。懂的都懂！

An opinionated agentic workflow to turn well-defined units of work into shippable code with minimal human input.

Turn real Agent failures into verifiable Skill boundaries and correct-layer fixes.

Free, open-source toolkit (Anthropic Agent Skill) for cancer patients, their caregivers, and anyone organizing treatment — runs the operational side around the doctors: documents, consultations, next steps, second opinions, cross-border care. Not an AI doctor.

Official Cursor plugin for Vertiso Memory: add the remote, user-owned memory MCP server plus the session skills in one step. Durable recall, hybrid search, and cross-session handoffs and checkpoints, with browser OAuth and no API key to paste.

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

A Codex skill for discovering, evaluating, and recommending open-source AI and software capabilities.

Evidence-first AI Agent Skills for growth marketing — multi-channel analytics (SEO, paid media, social, local search, CRM), secure account integration, AI evaluation, experimentation & approval-safe optimization for Claude Code.

Agent skill: structured, resumable domain-elicitation interviews that emit an OKF knowledge bundle (glossary, tri-temporal events, rules, context map)

Seedance2.5 AI video production skill: short videos, marketing videos, product demos, talking-head B-roll, storyboards, prompts, and continuity QA.

One Lark/Feishu agent skill instead of 27 lark-cli domain skills.

Portable Agent Skill for bean-specific xBloom Studio recipes and guarded local BLE control

A community collection of AI-agent skills for MLatom.

A Codex skill for publication-ready scientific figures, editable SVGs, multi-panel layouts, and figure quality assurance

Frontend design skill for Claude Code & OpenCode: interfaces that look designed, not generated. Anti-cliché catalog, font tiers, seeded variation, pass/fail self-review.

Professional Airtable skill for AI agents to design, audit, document, and troubleshoot Airtable bases, schemas, automations, interfaces, integrations, and operational workflows.

Local-first visual workspace for discovering, organizing, and managing AI agents and skills. Scans AGENTS.md/SKILL.md, renders a kanban board + relationship graph.

Approval-first Codex workflow for reviewing completed Notion work and turning useful takeaways into reusable records.

Turn public competitor channels into a traceable dataset and evidence-backed strategy report — an agent skill with a zero-dependency demo.

曹PRO AI 原创：检查短视频脚本、文案、封面和60秒内视频，按六项内容指标评分、说明证据并直接改好。

Evidence-first Elixir & OTP debugging layer for Claude Code CLI and Codex CLI.

Cross-agent frontend design skill for Claude Code and Codex CLI: seeded aesthetic variance, evidence-derived anti-slop rules, and a measured QA gate with bounded self-correction.

Source-grounded, NotebookLM-style research notebook over any local folder of documents — grounded Q&A with verifiable citations, plus study guides, briefing docs, mind maps, podcast scripts and more.

Native iPhone cards and notifications for live project state and AI agent events.

Программная реализация паттерна LLM Wiki (А. Карпаты). ВКР СПбГЭТУ "ЛЭТИ" 2026

AI documentary automation CLI with source-grounded narration, voice synthesis, non-repeating footage matching, Docker, and reusable Agent Skills.

Evidence-first Agent Skills for researching, designing, writing, building, testing, and red-teaming exceptional landing pages.

Journal-aware, review-first Agent Skill for Codex, Claude Code, and compatible hosts, with adaptive 5–6-agent peer review, citation verification, revision gates, and manuscript formatting checks.

Official Agent Skills for SuperToken.

Compact evidence-driven development workflow skills for Codex CLI and Claude Code

A stack of skills for your AI agent, made for people starting from zero. 103 skills and 149 project briefs — load one into Codex, Claude Code, Copilot, Gemini, or Cursor and do the thing.

Codex-native, spec-driven AI Agent workflow with Claude Code compatibility, independent review, QA, fixes, and refactors.

把真实项目经验整理成可安装、可检查、可追溯的 Agent Skills｜PDF、视频、文档、项目收口与视觉审美工作流

AI Agent Skill：UI/UX设计师方案产出指南，自动识别 5 类设计场景，按清单产出交互设计/设计系统/组件规范/无障碍方案等完整交付物。兼容 WorkBuddy / Codex / Trae / Cursor。

A reusable Agent Skill for turning a personal knowledge vault into a source-preserving capture-to-output system.

Agent Skill for long-running AI coding projects: maintain one source of truth, reconcile docs with code, track decisions, archive stale plans, and resume after context loss.

Practical open-source agent skills with working examples, validation, and guides for first-time users and technical operators

Image and PDF to Markdown OCR for AI agents: portable skill + ocr CLI (DeepSeek-OCR-2), stdio only, no MCP

The ultimate optimization of any entity is its absence — the best code is the code that does not exist. An always-on Existence Ladder skill for AI agents.

A tiny phase gate for coding agents: your shell checks decide pass/fail (never the LLM), your workflow routes the agent — advance, retry, escalate, done. Claude Code drives; headsign holds the state.