Loopkit for Claude Code - guardrails, hooks, and two loop modes that won't let a task "finish" until it's actually done.

AI agent skills and evidence-backed workflows for understanding unfamiliar codebases, assessing change impact, and growing developers into confident maintainers.

An open-source Codex skill for creating English hand-drawn wisdom videos from fables, Chinese idioms, historical anecdotes, and the Thirty-Six Stratagems.

Evidence-based Agent Skill for project viva preparation and mock questioning.

漫画书名一报，剩下的，有请老赵。自动研究、判断、写作并交付网页漫画书评的 Codex Skill。

Agent Skill for the Octopus Deploy CLI — works in Claude Code, Codex, Copilot, Gemini CLI and Cursor: releases, deployments, runbooks, task logs, plus the REST escape hatch for what the CLI has no command for

Seven tiny agent skills that burn down the gap between your prompt and reality — through one shared unknowns ledger

A playful, modular design workflow for building thoughtful websites with Codex and Claude Code.

Agent Skill + CLI for competitive content gap analysis — sitemap research, content strategy reports, and competitor gaps

面向 Codex、Claude Code、Gemini CLI 与 Grok Build 的完整中文学术论文解析 Agent Skill

Private, read-only escalation for coding agents: consult Codex GPT-5.6 Sol Max, preserve exact follow-up threads, and isolate history per caller conversation.

Evidence-first academic writing, citation integrity, revision, peer review, and bilingual scholarly style for AI coding agents.

Make Chinese and mixed Chinese-English text sound more natural by removing formulaic GPT-style phrasing.

逐题规划AI短剧路线，生成第一集制作包、赚钱验证路径与正推倒推进度表

Evidence-backed, resumable skill ecosystem auditing for the Codex app and CLI.

Portable AI skill: senior tech copywriter for SaaS, dev tools, fintech & Web3. English + Mexican Spanish. Works with Claude, Claude Code, OpenClaw and any agent framework.

Portable Markdown workflows for AI coding agents — session handoffs, project audits, and product discovery.

An interactive Codex skill for reading research papers stage by stage and maintaining evidence-aware Markdown notes.

A decision-making skill for coding agents. Point it at a vague decision and it separates facts from assumptions, hunts blind spots, and gives one straight recommendation. No AI slop.

Write friendly SQL, compile it to genuine ASYCUDA World (SYDONIA) customs SQL you can run read-only. A fully-sourced PostgreSQL reference model + query compiler + docs + Agent Skills for customs analytics, ML & selectivity.

Socratic tutor skill. Helps humans to learn new topics fast and optimize understanding.

从一个声音，看见自己、认识自己：非临床 Agent Skill，用于审计内化规则并安全测试新的选择。

Read-only Interactive Brokers (IBKR) diagnostics as portable AI-agent skills: account health, positions, daily P&L, trade history, dividends, options Greeks, and a P0–P3 graded portfolio report. Never places orders.

AMOS 结构方程一条龙工作流 Agent Skill：数据清洗 → 8道达标预检验 → 自动绘图插件 → 脚本化分析 → 中介/调节 → APA撰写。含可运行的预检验脚本与 AMOS 自动绘图插件。

Human-led, evidence-gated full-cycle research execution for Codex and Claude Code · 人类主导的科研全流程辅助工具

Local-first developer workbench for Open Knowledge Format bundles

A Claude Code skill that checks the current session for loose threads and tells you whether it's safe to close: STOP or CONTINUE.

Scan an AI agent skill for prompt injection, hidden Unicode, dangerous commands, and leaked secrets before you install it.

An Agent Skill for profile-derived persona simulation and constraint scoring.

A privacy-first Codex skill for safely organizing, renaming, and archiving files with approval gates.

德尔菲法（Delphi Method）全流程方法学 Agent Skill：专家遴选、四大系数、界值法/变异系数-均值法指标筛选、收敛判定、方法章写作与答辩应对。

a headless retrieval backend. Serves traditional RAG via a tool server or OpenAI shim, drive it from agents over MCP, CLI, or skills, run autonomous research subagents, and rate and compare each pipeline build step in an optional frontend

Evidence-first Agent Skill for reliable software engineering: reproduce, verify, root-cause, and document every change.

Curated Claude Code agent skills — local business lead prospecting and cold-email outreach (bring your own API keys).

Claude Agent Skill — turn N items to review into one self-contained clickable HTML: keep/review/drop toggles, notes, deep links, copy-selection. Human-in-the-loop.

Agent skill for sourced brand traffic, AOV, MRR, and ARR reporting

Agent Skills for root-cause debugging and regression-safe repair.

Stress-test reports, proposals, and executive decisions with a five-lens AI review council. Agent Skills compatible.

Let AI coding agents work with the Azure Cosmos DB vNext emulator

ruff for SKILL.md: catch bad triggers, token bloat, and structural mistakes before you publish a skill.

Audit how often Claude Code stopped for your input, trace each stop to the config that caused it, and knight your Claude with ready-to-apply fixes. Run the Jedi Trials.

Agent skills for Clics: privacy-friendly, cookieless web analytics. MCP server and CLI for AI assistants.

An agent control plane for governed, replayable execution.

Open-source e-commerce agent skills for the SKU.io API — authored once, generated for Claude, OpenAI, and Gemini.

Research GitHub repositories and turn verified findings into Chinese podcast episodes with an installable Agent Skill.

Let Him Grill: autonomous Codex decision workflow with compact and interactive visual modes

Architect high-reliability, logic-driven AI agents for production.

Evidence-backed release review for Agent Skills.

Reusable Agent Skills for Codex and Claude Code, focused on safe Git workflows and repository QA.

Agent Skill for teaching learners how their existing code actually works.

Claude Code plugin: represent a project as a tree of documented modules with boundary contracts, so an agent stays oriented in large codebases and makes boundary changes a deliberate preserve-vs-cascade decision.

Web search for Claude Code — one plugin bundling the official CLIs and Agent Skills of Exa, Tavily, Perplexity, Firecrawl, and Valyu. Guided setup, per-provider opt-in, always on the vendors' latest releases.

A systems-engineering Agent Skill for evolving messy AI prototypes and agent workflows into structured, validated AI-native systems.

Internal motivation skill for AI agents: stay on task, resist easy detours, and keep trying with evidence 💪

⚡ Zero-dependency Bun CLI for GitLab issues: create from markdown, edit any field, track time, bulk-edit with one command. 🤖 Ships with an Agent Skill for Claude Code & Cursor.

tests for your agent skills — lint free, behavioral runs against the real agent

Experimental library for discovering, validating, and sharing reusable Agent Skills / 用于发现、验证和共享可复用 Agent Skills 的实验仓库

Agent-agnostic skill for writing lean, outcome-led GPT-5.6 prompts across coding agents.

Cloud-based agent skills for creating AI avatar talking-head videos and short-form reels (skills.sh format)

Tool-agnostic SDLC orchestrator skill for coding agents: one lifecycle loop with mandatory CI, review, and quality gates, a 13-slot tooling map bound per project via an onboarding interview, and area skills that grow from real work.