A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

Calibrated decision measurement skills for AI agents.

A Claude Code plugin that installs the two-gate method for production AI agents: a design gate, a ship gate, and an incident-to-eval loop that turns failures into regression tests.

8 AI学习诊断工具 — 卡在哪用哪个，不卡不用。Hermes/Claude Code/Codex/Cursor/Trae 五端兼容。

Evidence-backed Seedance 2.0 prompt engineering skill for Codex: Dreamina, BytePlus, Volcengine, Fal, multimodal references, editing, and prompt linting.

A Claude Agent Skill that sharpens rough prompts using Anthropic's own prompt-engineering guidance.

Creator-lane agent skills from Agentic Creator OS. Install: npx skills add frankxai/creator-skills

Creator-lane agent skills from Agentic Creator OS. Install: npx skills add frankxai/creator-skills

opencode plugin — Hermes-style self-improvement loop (port of UniM0cha/claude-self-improving-skills + okdk7788/skill-evolution). Distills learned skills after complex work + GEPA-style measured evolution.

A Claude skill that decides whether to build an agent or a workflow, before you build it. The design-time gate, with a deterministic verdict engine.

Cross-agent SKILL.md workflows for product architecture, UX audits, prompt clarity, work synthesis, and hands-on practice.

Claude Code skills for creating, judging, evaluating, and updating skills and agents

One engineering workflow across Claude Code, Codex, Copilot, and Gemini CLI. A portable persona canon, process skills, and safety guardrails, kept in sync by design.

Model-agnostic realistic video prompt design, preflight, and explicit executor handoff for AI agents

Trim Claude Code system-prompt bloat: measure with a logging proxy, then deny unused tool definitions and disable features via settings.json. Method from aihero.dev, packaged as a skill.

Personal AI Agent Skills collection for Cursor and Claude Code

Find broken and risky Codex or Claude Code skills locally

Docs-first project incubation with 34 composable AI Agent skills—from idea and requirements to architecture, acceptance, and implementation handoff.

Agent Skills for prompt optimization - tune prompts for the latest frontier models like Fable 5 and GPT 5.6, write effective goals and success criteria, and engineer agentic loops that converge.

Measured prompt iteration with train/test dual-gate scoring and anti-overfit rails. Agent Skill (SKILL.md).

Moved to IchenDEV/prompt-optimizer-plugins. Historical Fable 5 v1.0.0 repository.

A first-principles Vibe Coding prompt workflow for AI agents and chat models.

Open GEO agent skills + zero-dep MCP for AgentGEO — turn real AI answers (ChatGPT, Perplexity, Gemini, Google AI, Copilot) into GEO decisions, agent-side.

Reusable agent skills from Dead Pixel Design, starting with an agent-agnostic Codex prompt compiler.

Skills for diagnosing prompt failures, compressing context, testing prompts, and reviewing system instructions.

Skills for diagnosing prompt failures, compressing context, testing prompts, and reviewing system instructions.

Skills for diagnosing prompt failures, compressing context, testing prompts, and reviewing system instructions.

Portable agent skills for desktop apps, programming, UI, and web design - Codex, Claude, Cursor, Grok. English SKILL.md playbooks (Photino, Inno, CI, landings).

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

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

将任意输入改写为保真、紧凑、可执行且可验证的提示词｜Codex Skill + Plugin

75 production-grade agent skills for Hermes Agent + Paperclip — research, write, organize, earn, and run an AI workforce. Every skill passes a QA gate with hard safety rails. Built by Gen AI Hub.

A skill library for AI coding agents with a CI quality gate: 38 skills, four-target sync, and an 18-check eval harness that fails the build on malformed skills.

Open-source GEO/AEO/SEO agent skills and plugins for the AutoXEO China-market workflow.

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

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

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

MCP server for AI-enhanced prompt engineering and request conversion.

The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...

An MCP server that enables AI agents to ask users clarifying questions via pop-up terminal windows.

Claude Desktop reminders for Windows. Survives MSIX boundary; persists across restarts. Zero deps.

Cloudflare Workers MCP server: ai-prompt-optimizer

Multi-model AI gateway — 8 providers plus local models, no system prompt injection.

Decision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.

The best AI image prompt library online. Latest trending prompts copy & paste for GPT image 2,

Scores, compiles & optimizes prompts for any LLM. Zero AI calls inside. Freemium.

Compare-first local MCP sidecar for browser AI workflows.