Claude Skills by opencue

Safe refactoring workflow using trace-mcp — assess risk, find candidates, check impact, and rename symbols across all files without missing import sites or cross-file references.

Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash. Activate whenever the agent needs to explore, understand, or modify a codebase that has trace-mcp indexed.

AI image, video, and music generation. Flux, Veo 3.1, Suno V5.

Text-to-speech conversion using GLM-TTS service via the `uvx zai-tts` command for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, podcast, driving, cooking). (3) Using pre-cloned voices for speech.

Audit your AWS bill with Claude. An executable, evidence-first AWS cost-optimization skill that verifies prices live and never deletes without proof.

Connect AI coding agents to the PrintKK API to automate image management, design creation, order fulfillment, and product catalog lookups.

A Claude Code skill to check, reconcile & file leave on Orisoft ESSNet HRMS — drives your real signed-in browser over CDP, finds unfiled days from Teams.

AI-agent-ready skill for safe local Desktop, Downloads, and Documents organization with dry-run, rollback, duplicate quarantine, receipt organization, and clean

Kill bad plans before they kill you. Premortem skill with Base Rates, Bias Circuit-Breaker, L/I Scoring, and Commitment Mechanism — the first to combine all 4 c

Automate security research workflows with structured tool-driven assessments for Claude via MCP.

Extract and summarize social media content from platforms like Instagram, TikTok, X, and YouTube using Claude Code.

Evaluate project fundability and refine grant logic using AI agent skills to identify innovation, assess feasibility, and reduce rejection risks.

Autonomous AI SDR skill for Hermes Agent — finds buyers, qualifies leads, sends outreach, manages CRM across WhatsApp/Email/Telegram for B2B export businesses

AI Research Writing Skill (AI论文写作技能) is an agent skill for ML / AI / CV / NLP researchers. Point your coding agent at code, experiment logs, notes, and a venue

Full-spectrum consolidation for Claude Code config files. Audits CLAUDE.md, rules, skills, and memory — not just memory. Detects dead paths, stack mismatches, d

A translator between you and your codebase. It reads your request back in plain words so you see what the agent understood before it builds.

Your agent hits a gap in the spec and guesses. Urd makes it stop and ask instead.

Design intelligence engine for AI coding. 120 anti-pattern linter rules, 110 brand DESIGN.md specs, MCP server, 22 commands, 17 IDEs, 17 languages. MIT.

电商商品图生成 — Hermes / OpenClaw / Claude Desktop 一键装的 MCP server

Free, MIT Agent Skill (Claude/Cursor/Hermes) for cinematic scroll-driven websites — pinned chapters, parallax, 3D tilt, and full Shopify-Editions-style release

Systematic project assessment against checkpoint-enabled skills with scripted verification + LLM review - by Netresearch

TYPO3 TypoScript, TSconfig and Fluid reference lookup for AI agents

AI Agent Skill for NSAuditor AI — gives any AI coding agent built-in knowledge of NSAuditor's MCP tools, schemas, plugins, and security audit workflows. Works w

富邦新一代（Fubon Neo）Python 技能包：交易與行情工作流、測試環境整合測試、多代理（Codex/Claude/Gemini）適配。

Claude Code skill for PaperBanana - Generate publication-quality academic diagrams with AI

论文排版 skills for Codex and Claude: automatic DOCX thesis formatting with backups, structure mapping, and custom format support

AI agent skill: deep, Socratic-maieutic review notes for books / games / movies / music in Obsidian format

Claude.ai skill for AIPL marketing team — automates B2B lead enrichment for Indian companies, outputs Vtiger-ready files, smart credit allocation across Lusha/A

连接 bizyair.cn 云端生态，赋予 Agent 图像/视频生成、AI 应用执行与 ModelZoo 模型调用等 AIGC 能力，助力实现更高效的视觉创作与 AI 任务流自动化。

Manage iOS app metadata, TestFlight builds, and releases directly from your terminal using this Claude Code skill.

Turn your local Claude Code / Codex CLI history into a shareable, anonymized AI-Native developer profile + viral SVG poster. A skill, not a script — 100% local

Public Agent Skill for Silicon Circle: post tasks, find bounties, submit work, earn Proof Points, and route accepted work into marketplace closeout.

🚀 Optimize App Store visibility with AI agents in the Claude Code framework for enhanced performance and growth.

Make WeChat mini-program & mini-game docs agent-readable: complete nav maps + on-demand markdown fetcher (a Claude skill).

Use when the user says "improve this skill", "rewrite this skill", "this skill is weak", "fix this skill", or when you encounter a skill scoring <3/5 during an audit. Follow the steps in order.

When user asks about managing Claude Code or Codex profiles, skills, MCPs, or agent configuration, use cue CLI commands to help them

Guide for creating and configuring AgenticX agents with roles, goals, tools, LLM providers, and execution strategies. Use when the user wants to create agents, assign tools to agents, configure LLM backends, set up agent execution, or build multi-agent systems.

Guide for managing AgenticX skills including listing, searching, installing, uninstalling, publishing, and running a skill registry server. Use when the user wants to manage skills, find available skills, publish custom skills, set up a skill registry, or understand the skill ecosystem.

Use when the user asks to "set SEO alerts"; configures ranking, traffic, technical, competitor, and notification thresholds. SEO预警/排名监控

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Use when analyzing backlink profiles, link authority, toxic links, link-building opportunities, or competitor link gaps. 外链分析/反向链接

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Reference for the Codex API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Codex/Anthropic in any form (Codex, Anthropic, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `Codex-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from mem...

Guide for Rust development including code style, testing, building, and quality checks using cargo tools. Apply when working with Rust code, Cargo.toml, or running cargo commands.

Use when checking for security vulnerabilities in NanoClaw skills, before installing new skills, or when asked about security advisories affecting the bot

Use this skill when the user wants to understand, document, or explain a codebase — even if they don't say "document" explicitly. Trigger on: "explain this codebase", "how does this project work", "create onboarding docs", "document the architecture", "I'm new to this repo", "generate a codebase overview", or any request to understand unfamiliar code. Produces a single docs/CODEBASE.md with architecture, components, data flow, setup instructions, and a recommended reading path for new develop...

Use when the user asks to "compare competitors" or find SEO/GEO gaps; analyzes keywords, content, backlinks, AI citations, and traffic share. 竞品分析/竞争对手

Use when the user asks to "find content gaps"; maps competitor topics, missing keywords, and editorial calendar opportunities. 内容缺口/选题规划

Use when auditing content quality, E-E-A-T, publish readiness, or 内容质量/EEAT评分. Runs 80-item CORE-EEAT scoring with veto checks and fix plan.

Use when updating outdated content, fixing traffic/ranking decay, refreshing stats, adding new sections, or improving freshness signals. 内容更新/排名恢复