Connectivity diagnostics and setup for AI agents using Breakdown

把 Agent Skill 从写了但不好使，变成写完就能用、经得起检查：新写、审查、优化、从对话提炼。触发更准、约束更强，让普通人也能写出专业级 skill。

用一个中央仓库和现代 TUI，统一查看与同步 Claude Code、Codex、Cursor、Antigravity 的 Skills 和 MCP。

Future-you interrogates today's architecture decision, then files the regret before you commit it.

A Claude Code skill that curates your auto-memory store — pruning and sharpening it, not just growing it.

Portable, reusable skills for agents and everyday workflows. Clank responsibly.

Переносимое ядро ship-max: адверсарные пайплайны Claude ↔ GPT (пишет одна модель, ревьюит другая) с установщиком, который обновляет проекты не теряя локальных адаптаций

Shell-based desktop automation for coding agents (not vision Computer Use)

Claude Code plugin: 12 NestJS best-practice skills (90 rules) grounded in the official NestJS docs

Playwright FieldKit: gives coding agents hands and eyes on the web — crawl, debug, record, and test live sites via deterministic scripts; portable Agent Skill for Codex, Claude Code, Antigravity, and Cline

From context to installable agent skills - research packs in, validated skills.sh-ready skills out. Scaffolding, eval-first authoring, validation, and deployment included.

기획-개발 핸드오프 표준 킷 — 편집형 기획서 템플릿(HTML), 작성 예시, 에이전트 스킬(handoff-spec)

Portable Agent Skills for test-first development, evidence-based debugging, code review, and reviewable Git history.

Skills + hooks for Claude Code: prompt-compile makes the agent write itself a high-quality task brief before building — define-do-verify, deterministic trigger, fresh-context execution.

Bilingual Agent Skills for evidence-driven content, search, and knowledge work.

Fan-out discipline for AI coding agents - scout, partition, wave, QC, single-writer apply, receipt. Bounds a swarm to the solo-cost budget; does not make models smarter. Zero-dependency, Phoenix-13. Part of TheColliery.

Local Skill center for Codex, Claude Code, Hermes, and Agent Skills-compatible workflows

One source of truth for AI coding agent instructions — scaffolds AGENTS.md, CLAUDE.md, GEMINI.md and a layered .agents/ structure, and updates them without clobbering hand-written rules.

Your project's second mind — a Claude Code skill that turns every session into structured, linked Obsidian notes your AI can reference.

Kill-tested guard skills for AI coding agents , self-invoking quality gates that catch AI failure modes in security, tests, docs, dependencies, and diffs before the agent says "done." Works with Claude Code, Codex, and Cursor.

Run Claude Code Workflows (CCW) on Grok: single install path plus a runtime translation layer

A portable Agent Skill that reverse-engineers any codebase into a reusable engineering constitution. Install: npx skills add 3bsalam-1/architecture-extractor

Pythurion helps coding agents write Python you’ll want to maintain: correct, minimal, and idiomatic

Agent Skills and hooks for maintaining high-quality open-source Python packages - an agentic engineering setup covering linting, testing, packaging, releases, and CI quality gates.

Agent skill that generates an interactive dependency map of your AI harness (skills, agents, commands, MCP servers)

Free Agent Skills that pressure-test AI project ideas and diagnose running systems. From the AI Problem Framing course.

Claude skill + drop-in code for hardening & auditing LLM features against prompt injection, privilege escalation, marker forgery, and data leaks

RSSHub route builder skill — generates complete, PR-ready RSSHub route code (namespace.ts + handler + Radar rules + PR checklist) from a target website

Two agent skills to keep a long-running AI agent from getting stuck: north-star (delivery-point self-correction hook) + moa (N+1 multi-model consultation).

Cross-harness Agent Skill: terminal & coding-agent orchestration via the forge PTY daemon — Claude Code, Codex, Gemini, OpenCode, and Amplifier, with an artifact-gated multi-agent relay controller

Frontier operating discipline for Claude on any model, plus loop and automation suggestions. An open-source Agent Skill.

Proven UX flows, user journeys, and app layout patterns packaged as agent skills for Claude Code, Codex, Gemini CLI, and any coding agent

Claude Code plugin: FastAPI best practices (41 rules, 13 categories) grounded in the official FastAPI docs

Scope-first agent design skill — ถามขอบเขตให้ชัด ก่อนสร้างเอเจน

Claude Fable 5 orchestrator for React Native/Expo — Grok 4.5 Heavy implements; Argent UI verify; STATUS + ledger multi-agent chains

Open a second coding agent in a herdr pane and have it review your diff — watchable, auto-approve, read-only. Ships a Claude Code skill for the autonomous review↔revise↔decide loop.

Stateful Goal mode skill for Codex, Claude Code, and AI agents with STATE.md memory, gates, and stop rules.

A job-search pipeline that runs on your machine — fetches postings, scores each against a rubric you wrote, and hands you a ranked worklist. It does not apply for you.

Turn technical incident RCAs into intuitive standalone HTML wikis for nondevelopers

Agent skill for OpenClip: turn long videos into captioned viral clips, transcribe, convert, and edit media from Claude, Cursor, OpenClaw, and any SKILL.md-compatible agent over MCP.

Agent Skill for packaging and distributing Salesforce Data Cloud (Data 360) Data Kits as managed 2GP packages

An Agent Skill that stress-tests plans one question at a time and turns decisions into an implementation-ready brief.

🧩 Curated, auditable agent skills for knowledge, mastery, career, and cross-system orchestration.

Beta Agent Skill for preparing deployment data from mixed-content folders for Microsoft 365 Copilot Agent Builder, with early-access support for Google Gemini Gems.

Cross-agent workflow for Seeed Studio XIAO ESP32 projects with PlatformIO, ESP-IDF, MkDocs, and Espressif MCP.

Agent Skills for maintaining high-quality open-source Node.js, TypeScript, Next.js, and React apps and packages - linting, type safety, testing, packaging and releases, and CI quality gates.

Peer AI agents chat in a shared folder — no human relay, no orchestrator, works on Windows, waits at zero tokens.

Agent skill: security audit & hardening for vibe-coded apps (5-phase loop: secrets, PII, pre-deploy, deep logic, attacker review).

Codex and Claude Code Agent Skill for generating illustrated Word/DOCX development documentation with Playwright screenshots and encoding-safe images.

Turn your AI agent into a medical-bill negotiation advocate — an open-source playbook of skills, letters, and verified patient rights. Pay what's fair, nothing more.

Agent skills for UX writing, conversion analytics, and A/B testing — built for coding agents

Public Codex skills, including skill-design-review and drawio-diagram-skill.

Reusable repository guidance, workflows, runbooks, and skills for people, Codex, and Claude Code.

PaperFlow｜文脉：把 PDF 精读、批注与知识网络组织成可追溯的论证，适用于 Codex 与 Claude Code。

Evidence-backed release review for AI agent harnesses.

Agent skill that checks every MCP server against the PolicyLayer registry before connecting - identity, risk grade, tool classifications and changes.

Audit your Claude Code skills: see which actually fire, which are dead weight eating context tokens, and slim them down. Local, zero-dependency, AI-free.

GPT Image 2 ecommerce Skill for product-preserving main images, white-background product photos, PDP prompts, and QA｜电商商品图 Agent 工作流