基于 13 本投资经典的 AI 辅助投资决策系统，覆盖大盘扫描/行业跟踪/组合复盘/深度研究

Turn any AI agent into a negotiation coach that hands you the exact words to say.

Next.js to Postgres — build and ship a modern web app end to end.

Audit a GitHub repository for risk before integrating it into your stack. Seven-dimension framework with weighted scoring and ADOPT/EVALUATE/CAUTION/AVOID verdict.

Zhihu web automation skill for Codex and Claude Code: persistent sessions, content discovery, verified interaction, and Markdown answer/article publishing.

Claude Code agent skills for mobile game strategy research: methodology + Sensor Tower (BYOK) data fetch + consulting-style charts + Feishu doc editing

Professional development studio for Claude Code CLI

UGC Ad Creative Generator — AI-powered ugc ad creative generator

Yuheng's Claude Code skills marketplace

Claude Skill for Bengaluru real-estate brokers that turns raw property notes into accurate, locality-aware listings for property portals, WhatsApp, and social posts, reducing repetitive prompt-writing, speeding up listing creation, and avoiding invented claims.

GitHub-only and Linear-only Claude Code skills that port the jot CLI loop — capture brain-dumps into well-formed tracker issues, decide what to work on next, and keep the backlog tidy. Each skill is a single SKILL.md invoked from inside Claude Code.

Free Claude skill for writing honest, conversion-focused local service business pages.

A library of agent skills for developing with Pi in mind.

Claude Code skill that clears your issue backlog — dedupes by symptom, finds bugs already fixed on main, drafts the replies, ranks the five worth fixing next. Never posts anything without your approval. 🚑

A Claude Code skill that sends you to bed the way a mom sends naughty children: lovingly, briefly, and without accepting counter-offers. Saves your work into TOMORROW.md first.

Claude Code skills marketplace: domain-search + ssr-market-research (also usable as plain skill folders in Codex/Cursor)

Executable biomedical workflows for AI assistants — literature analysis, biomarker discovery, and Mendelian randomization through reproducible agent skills.

Open agent skills from InferHaven

Claude Code, Codex, OpenClaw and Ottili AI Skills - powered by Ottili ONE

Essential Claude Skills I Use

两个用于 AI Agent 的产品方法论 skill：true-demand（诊断方向该不该做、卡在哪）与 product-stagegate（按 Demo→MVP→PMF→GTM→MTU 五关推进）。Two product-methodology skills for AI agents.

Three Claude skills for keeping long projects coherent across chat sessions: verified handovers (session-close / session-open) and a canonical roadmap visualizer.

A Claude skill that rates any portfolio for alignment with the New Inflationary Era - the structural macro regime that began when the 40-year bond bull market ended.

LLM Skill для синтеза и распознавания аудио

AI documentation architecture skill for clear, non-duplicated, source-of-truth driven, token-efficient project documentation.

Kilo/agent skill for building OpenCode extensions, plugins, and integrations

Agile project management skill for AI agents — JQL search, sprint planning, issue lifecycle via mcp-jira

Autonomous supervisor → worker → critic loop for Claude Code — delegate one goal, an independent critic grades each round against a rubric, re-dispatch until done. 主Agent监督子Agent+独立评委，定验收标准反复迭代到完美，全程不问你。

A Claude Skill that reviews physician CVs for European residency & specialist-training applications like a real HR screener

Literature reviews, systematic reviews, citations, and policy briefs.

Turn any AI coding agent into a synthetic-biology research assistant. A $0 skill pack for Claude Code, Cursor, and OpenCode. Design-only, built for iGEM and student researchers.

Resume tailoring agents on Claude Code based on experience bank; renders LaTeX.

Skill that uses the standard Python ast module to build a deterministic "grep map" of any Python package from PyPI - giving agents a perfectly accurate way to efficiently explore any API

Engineering quality focused skills for AI coding agents that keep humans in the loop.

Claude Code skills for shipping: single PRs, parallel PR fan-out, multi-phase epics, and a ruthless pre-ship critic. One session chairs; context never splits.

Practical guides, prompts, and Python code for applying Anthropic's Claude Skills to data engineering and pipeline automation

A scoring harness for Claude Agent Skills. Each carded skill ships a Skill Card: a SkillSpector security scan and trigger evals, generated and gated in CI.

Execution topology selector for Claude: loop, fan-out, or graph — the simplest sufficient shape, benchmarked

Template for an AI-native job-search workflow built with Claude Code (skills + hooks). Fork and personalize.

Connect Claude Code to WeChat for terminal chat, with QR login and long-poll WeChat iLink Bot support

Grade your AI-agent repo. One command, one report card — scored, evidence-backed reviews (reliability, security, prompts, evals, token cost, UX, accessibility) for AI/LLM apps.

A Claude Code skill for running long, unattended, multi-goal work, the kind where a human isn't approving each step.

The One Person AI Agent Company. Build an entire startup with Startup OS. Entire team of agents taking you from idea to customer

My own configuration CLAUDE, Dev & Ops specialist and 100% educational.

Automate Claude Code Session using python SDK without API Cost

💻 Let your AI agent interact wth Hashmob.net

AI-powered Claude Code skill to structure messy folders into M&A-ready datarooms with intelligent classification, deduplication, version detection, and contextual missing-docs checklist. Multilingual FR/EN/DE/IT/ES.

Turn rough notes into a polished, schema-validated slide deck in any AI agent (Claude Code, Cursor, Codex, Gemini CLI, Copilot) — then export native, editable PowerPoint, Keynote & Google Slides. Skill + MCP server.

Frontend Design Kit for Claude Code — UI, UX, components, charts & animation. KokonutUI, Bklit UI, and Anime.js skills in one installable plugin.

Claude Code skill that investigates Chesterton's fence — point it at a weird line of code and it digs through blame, old commits, and PR archaeology to answer: why does this exist, and is it safe to delete? 🚧

Falsification-first investigation & invention for Claude Code + Grok: hypothesis ledgers, REFUTE-first verification.

Agent organizations as first-class persisted data

Default HTML-form variant of grill-with-docs: interactive decision form with FACTS, trade-offs, WHY panels, and mmdc-validated Before/After Mermaid diagrams.

My assortment of Claude Code skills

Стек-агностичный шаблон смысло-кодинга для Claude Code: бизнес-контекст в business/, планы фич, ретроспективы, правила и готовые промпты. Стек выбираешь на старте.

Multi-platform Chinese OCR skill — PaddleOCR/Baidu/Tencent/Alibaba/EasyOCR, all work in China

Loop Engineering 合規審查員 — 用 Addy Osmani《Loop Engineering》七條量尺審 AI 迴圈專案（agent/skill/cron），保留風格只修合規。Claude Code skill + subagent，中英雙語。

25 Claude Code subagents + 14 lifecycle skills + CLAUDE.md templates - build, ship, and monetize products with AI. Clone, run sync, done.