Agent skill: end-to-end app store release campaigns for Apple App Store, Google Play, and Huawei AppGallery — with the full China-market compliance chain (ICP App 备案 / 软著 / AI declaration / privacy labels)

An evidence-first skill that teaches coding agents when to patch, when to abstain, and how to prove the difference.

Claude Code skill + CLI to remove AI slop from generated web pages: push HTML to a visual editor, refine by hand, pull the changes back. 39 detectable AI-slop fingerprints.

Cross-agent skill for full-stack code-change impact analysis: trace every consumer, make the smallest complete fix, and verify regressions.

Portable Agent Skills for product architecture, research, storytelling, README writing, PRs, and growth.

Local, reversible context doctor for Codex, ChatGPT Desktop, Claude Code, and Agent Skills.

16 Agent Skills pour transformer une idée en résultat clarifié, construit, prouvé, révisé et livré.

Audited English datasheet PDF to page-aligned Chinese HTML workflow with Agent Skills, CLI, MCP, and fail-closed QA.

Free open-source Agent Skills for selectable 16-type AI communication styles

Unofficial, cross-platform Fable-inspired workflow skills for Claude Code and Codex, plus portable GPT prompt templates.

Guildshelf free funnel skills for Claude Code — Apache-2.0. Try before you subscribe: guildshelf.com

Premium academic PowerPoint redesign, template research, text audit and native animations for Codex.

Codex-native diagnostics and configuration hygiene with approval-gated fixes.

Groundledger: MIT agent skills for Claude Code, Cursor & Cowork — grounded blog SEO/AEO, PROBE site SEO, SAFE paid media, SPARK editorial, SNAP social, ORBIT discovery

Orquestre N agentes de código (Claude Code) em paralelo no terminal kitty — cada um na sua aba e na sua git worktree, com modelo, permission mode, effort e perfil configuráveis. Agent Skill + CLIs Python puro via kitty remote control, sem tmux.

ExportDou 官方 CLI 与 Agent Skill：导出公开抖音视频评论与回复

傅佩荣数字卦占卜 Agent Skill：三组三位数起卦，内置完整中文 64 卦与 384 爻数据库

Operational product-management skills and a /pm router for Codex and Claude.

Author and validate deliberately crafted 16x16 track icons for Yoto Player and Yoto Mini.

Two Claude Code skills — poc for fast clickable app mockups (mobile/web with side-by-side RWD preview), and kickstart for clean, scalable project setup.

Deterministic cowsay agent skill (kodexArg) — Python 3 stdlib renderer + SKILL.md

Portable Agent Skills for deploying apps, open models, and coding agents on app.nz

Codex workspace organizer: AGENTS.md, skills, hooks, custom subagents / Организация окружения Codex.

Own, verify, and explain AI-assisted software changes

🪨 The Stoic Caveman Upgrade — a Claude Code skill that protects step-by-step action explanations while cutting output-token filler, the gap upstream caveman skills don't cover.

Work-item lifecycle over a board — backend-agnostic CLI + Claude Code skills (GitHub Projects, Plane, ...)

Agent skill for discovering and safely adopting skills, plugins, libraries, MCP servers, and open-source projects.

Source-available Agent Skill for personal, non-commercial WorkBuddy skin design, DOM selector mapping, injection, testing, and packaging.

按城市查询中国 AI 创业补贴、算力券、产业园和孵化支持的本地 Agent Skill（preview）

Obsidian learning vault and portable Agent Skill for guided Java LeetCode practice.

Claude Code skills for code and security review of Go, Bash, Vue/TypeScript and PHP — human report plus a re-verifiable agent prompt block

Official Scrappycoco MCP plugin and portable agent skill

Evidence-based whole-repository review Agent Skill — development, validation, and deterministic release workbench

面向中文内容的去 AI 味 Agent Skill，支持事实保护和个人文风校准。

Reusable open-source Agent Skills for Pi and compatible agent systems

Portable agent skills for evidence-driven software engineering research

Validated, agent-friendly GitHub pull request reviews with inline, file, and suggestion threads.

输入A股名称、代码或脱敏截图，检查最近公告、财报、监管信息和重要日期

Your agent ships. You stay dangerous. A demanding code coach for Claude Code and Codex.

Repository-centered instructions, skills, memory conventions, client adapters, and lifecycle safeguards for consistent work across AI coding agents.

Cursor Skill: OneOS 证照管理按车牌批量导出

Product OS is v1 of a product modelling method developed across live founder work. It sits between a product idea and its implementation. It does not generate code, wireframes, screens, or user stories. It generates the model those things get built against. Runs on Claude and ChatGPT via the open Agent Skills standard.

Evidence-first QA Agent Skill for Codex and Claude Code

A context-aware writing skill that humanizes outward-facing prose without flattening voice or changing meaning.

Production-grade Agent Skills for Claude — reusable capability modules with tone rules, output contracts, eval suites, and CI validation.

Skills that automate the boring parts of shipping code.

Local-first relationship memory vault with a headless crm CLI and installable agent skill

Brutally evidence-led art direction for Codex + Claude Code. Ten categories. Fresh proof. 10/10 across the board—or STOP.

Hermes skill for realistic low-angle and high-angle wide portrait photography prompts.

Hidden, on-demand OpenCode subagent for Gentle-AI that orchestrates GitHub Issues, PR reviews, CI/CD diagnostics, traceability, evidence-based validation, and safe pre-merge decisions.

Safety-first Agent Skill for auditing and removing starter, boilerplate, template, and SaaS-kit residue with approval gates, external previews, backups, and rollback evidence.

Self-contained Apache ECharts runtime, Oracle APEX plug-in, PL/SQL API, and reusable agent skill.

Agent-first CLI and Skills for self-hosted SearXNG search and web research

Auditable AgentTeams multi-agent software delivery with contract-driven Skills.

Guarded x402 client for Solana transaction diagnosis, simulation, token risk, and budget-capped live priority fees.

Official WDYT skills for AI agents

taskforge-skills — an Agent Skills framework for the durable-Task AI engineering workflow: skills reason, a deterministic engine is the only writer of task state

Create, resume, validate, and render hand-drawn story videos as a mature Agent Skill.

Skills y herramientas para generar, validar y renderizar diagramas PlantUML

Claude Code / AI-agent skill: ask OpenEvidence via ego-lite, capture the thread, and mint a shareable HTML + Crossref-verified BibTeX / CSL-JSON / AMA bibliography. Evidence-based-medicine citation export. Install: npx skills add htlin222/ask-oe-with-ego-skill