core67 skills discovered by cue. Last updated 2026-09-05.
★ 658 · exceptional (score 19.3) · JavaScript
A Claude Code skill by Hao (駱君昊) that learns your Facebook voice and auto-posts to FB / IG / Threads / X with a 14-day content calendar. Mega-viral validated: 80K reach / 448 likes / 500 comments on first post. Includes Day 2 flop postmortem.
cue skills add Hao0321/claude-skill-social-post --profile core★ 117 · exceptional (score 19) · TypeScript
MCP server for Claude Code and Codex. One tool call replaces ~42 minutes of agent exploration
cue skills add nikolai-vysotskyi/trace-mcp --profile core★ 679 · exceptional (score 19) · JavaScript
Development workflows for Claude Code that keep broad exploration focused on the outcome you approved.
cue skills add shinpr/claude-code-workflows --profile core★ 37 · exceptional (score 16.3) · Python
Agent skill for AI trip planning (Claude Code · Codex · Gemini CLI · Cursor · Copilot · any SKILL.md agent) — verified, bookable itineraries: hour-by-hour days, real flight prices, offline KML maps, eight themed page designs · 旅行规划 / 行程 / 机票比价
cue skills add skywain/trip-planner-skill --profile core★ 53 · exceptional (score 16) · Python
Turn your Grok Bot into a 7-agent Hyperliquid trading desk. Roles, system prompts and skills your Bots use to research, size, execute and review.
cue skills add galleonlabs/hypergrok-trading-desk --profile core★ 123 · exceptional (score 15.6) · Python
Находит следы машинного текста в русском и объясняет их вам
cue skills add Vladimir-Human/humanizer-ru --profile core★ 104 · exceptional (score 15.5) · Python
Independent Claude Skills for the whole smart home: Home Assistant, ESPHome, Node-RED, custom integrations, dashboards, and fab-ready hardware design.
cue skills add tonylofgren/aurora-smart-home --profile core★ 7 · exceptional (score 14.7) · Python
Comprehensive Chinese metaphysics & fortune-telling toolkit · Claude Skill · 20+ methods · MIT
cue skills add ShousenZHANG/chinese-fortune --profile core★ 34 · exceptional (score 14.7)
A massive, self-updating local archive of AI tools — 11,000+ agent skills, 240+ MCP servers, 2,200+ IDE rules (Cursor/Cline), and 30+ system prompt collections. One repo to rule them all.
cue skills add HIDORAKAI002/ai-workspace-archive --profile core★ 35 · exceptional (score 14.7) · JavaScript
Public adapters and discovery catalog for Triptych OS (Agent OS): agent frameworks, MCP/A2A/x402 protocols, workflows, wallets, SDKs, and examples for execute-first routing, governed handoffs, and receipt-aware agent commerce.
cue skills add rhein1/agoragentic-integrations --profile core★ 0 · exceptional (score 14.5) · Shell
Claude Code skill: continuous PRD implementation loop. Pairs with j0yen/dream-skill.
cue skills add j0yen/build-skill --profile core★ 53 · exceptional (score 14) · TypeScript
Open, primary-source-backed U.S. legal content — practice guides, 50-state surveys, reviewer checklists, and standard agreement templates. Built for legal teams and the agents helping them.
cue skills add open-agreements/open-agreements --profile core★ 203 · exceptional (score 13.1) · Rust
Local-first MCP gateway. One port for every tool and every AI client: lazy discovery (~90% token savings), tool integrity + quarantine, secrets in the OS keychain.
cue skills add btsouth/toolport --profile core★ 5 · exceptional (score 13) · TypeScript
Agent profile manager for Claude Code & Codex. Per-directory profiles select which skills, MCP servers, and plugins load — automatically, before launch. Install: npm install -g cue-ai
cue skills add opencue/cuecards --profile core★ 0 · exceptional (score 13) · Python
Скилл для Claude Code: работа трекера в акселераторе — методика, шаблоны документов и инструменты. Любое число потоков и команд.
cue skills add rvignatenko/treker-akseleratora --profile core★ 0 · exceptional (score 13) · Python
A Claude Code skill: verbatim state handoff to disk before /clear or /compact, auto-resumed by a SessionStart hook.
cue skills add xoonjaeho/claude-skill-handoff --profile core★ 117 · exceptional (score 12.4) · JavaScript
Agent skills for fallow, codebase intelligence for TypeScript and JavaScript. Teaches AI agents how to find unused code, duplication, circular deps, complexity hotspots, architecture drift, design-system drift, and (with Fallow Runtime) hot-path and cold-path evidence. Works with Claude Code, Cursor, Codex, Gemini CLI, and 30+ agents.
cue skills add fallow-rs/fallow-skills --profile core★ 1 · exceptional (score 12.3) · HTML
把品牌影响力拆成可打分、可比较、可复盘的事。Claude Code skill,5 位人物评委(傅盛·Steve Jobs·李可佳·吴俊东·张一鸣)按 7 维度 × 5 镜头独立打分,Lead 合成版本化报告:雷达图 + 异议热力图 + 影响力构造图 + 90 天行动建议。`/mba <brand>` 一行触发,EVOLUTION 模式追踪同一品牌随时间演化。
cue skills add zhanglunet/mba --profile core★ 2 · exceptional (score 12) · HTML
🚀 WebGPU Agent Skill 2026: Build GPU Apps with Easel.js & AI Coding Agents
cue skills add AllyJuma1/easel-js-cpu-render-kit --profile core★ 9 · exceptional (score 11.9) · TypeScript
The agent eval standard for MCP — score output quality, catch safety failures, enforce cost budgets
cue skills add iris-eval/mcp-server --profile core★ 0 · exceptional (score 11) · Jupyter Notebook
AI-agent skill, verified Python toolkit and executed six-chapter book on compact memristor models (linear ion drift, Yakopcic, VTEAM, Stanford-PKU), cross-checked against the MemrisTec Model Library
cue skills add fabiocampolim-design/memristec-skill --profile core★ 34 · exceptional (score 10.8) · JavaScript
📋 Your project plan, kept next to the code. A Claude Code plugin: ask what's next and get the task, the reason, and a ready-to-run prompt checked against your real files.
cue skills add V-Songbird/foreman --profile core★ 5 · exceptional (score 10.6) · Python
Short-term memory proxy gateway with proactive memory surfacing for AI agents
cue skills add memtomem/memtomem-stm --profile core★ 947 · exceptional (score 10.3)
A self-improving skill for AI coding agents (Claude Code, Cursor, AGENTS.md): recognize a hard-won golden path in a session and harvest it into a reusable skill/rule for next time.
cue skills add Kulaxyz/self-learning-skills --profile core★ 4 · exceptional (score 10.3) · JavaScript
⚒️ Three Claude Code plugins: foreman keeps the plan, hush cuts the chatter, razor stops the over-building. One marketplace, install any of them.
cue skills add V-Songbird/foundry --profile core★ 9 · exceptional (score 10.1)
A Claude skill for running structured personal-data erasure campaigns — 329 data brokers, OSINT tools and breach-search engines with verified privacy contacts, request templates for 13 privacy regimes, and escalation paths to 21 regulators.
cue skills add 0nicell/data-deletion-skill --profile core★ 8 · exceptional (score 10.1) · JavaScript
🪒 Stops Claude from adding code nobody needed. A Claude Code plugin: one check before every new package, file or abstraction. Same job, half the lines.
cue skills add V-Songbird/razor --profile core★ 0 · exceptional (score 10) · Python
MCP server that governs an AI coding agent through a delivery lifecycle: each named role must produce a machine-checkable artifact before it may sign off, and the whole build record survives on disk across sessions.
cue skills add 224Sand/charter --profile core★ 49 · exceptional (score 10) · JavaScript
🤫 Claude shuts up until it's done. A Claude Code plugin: one short answer at the end, the file to open, and no log dumps in your chat.
cue skills add V-Songbird/hush --profile core★ 1 · exceptional (score 9.8) · JavaScript
A Claude Code skill that trims a project's CLAUDE.md to what is strictly necessary, replacing derivable or duplicated content with on-demand references to save context tokens.
cue skills add qiaeru/skill-claudemd --profile core★ 1 · exceptional (score 9.8) · Python
All-in-one Formula 1 MCP server — live telemetry, historical results, race analysis, and news from OpenF1, Jolpica, FastF1, and Wikidata
cue skills add praneethravuri/pitstop --profile core★ 0 · exceptional (score 9) · HTML
cue skills add sfdfddfs13QWE/advisor-strategy-skill --profile core★ 0 · exceptional (score 9) · HTML
Spotify Timestamped Notes Plugin 2026: AI-Powered Music Journal for Developer Workflow
cue skills add Albert634png/note-taker-for-spotify --profile core★ 0 · exceptional (score 9) · HTML
Token Optimizer 2026: Eliminate Ghost Tokens, Fix Context Decay & Survive Compaction
cue skills add gerrict/ghost-token-hunter --profile core★ 6 · exceptional (score 9) · Rust
Security-guarded MCP server for Bugzilla, written in Rust
cue skills add plusky/bugwarden --profile core★ 82 · exceptional (score 8.6) · TypeScript
The @skills protocol: use any SKILL.md by path, save it into .atskills/, auto-trigger it with one line. Reference implementation + integration guide for any agent.
cue skills add SylphAI-Inc/atskills --profile core★ 4 · exceptional (score 8.3) · TypeScript
Sync your full Claude Code setup across machines: skills, settings, and session history, with path remapping and per-host overrides
cue skills add funkadelic/claude-nomad --profile core★ 113 · exceptional (score 8.3) · TypeScript
Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.
cue skills add PerryLink/dsh-permission-rules --profile core★ 1 · exceptional (score 8.3) · Python
Bulgarian payroll (ТРЗ) audit skill for Claude Code and GitHub Copilot — checks ведомости against КТ, КСО, ЗДДФЛ and НСОРЗ
cue skills add svedbg/trz --profile core★ 3 · exceptional (score 8.2) · PowerShell
Claude Code가 "계획 없이 추측하고 a 파일 수정하면서 b·c 파일을 빠뜨리고 검증 없이 완료 선언"하는 것을 막기 위한 도구입니다. 모든 코드 변경은 계획 → 구현 → 다층 검증 → 완료의 자율 루프를 거칩니다.
cue skills add jongcheol-pak/claude-harness-pjc --profile core★ 0 · exceptional (score 8) · Shell
Turn recorded lectures into revisable study material. Local whisper.cpp pipeline with VAD, coverage checking, and note verification — rebuilds a per-course exam synthesis after every class.
cue skills add biswajeetdev/classnotes-agent --profile core★ 0 · strong (score 7.5) · JavaScript
Free, AI-powered PDLC automation for Cursor. Routes feature requests, bug reports, and architecture work through structured workflows.
cue skills add ShipToday/forge-plugin-cursor --profile core★ 8 · strong (score 7.1) · JavaScript
Memory and accountability for AI coding agents. Layered memory that arrives at the moment of action, multi-terminal coordination without a server, and a trust spine where every "done" is settled by a re-runnable check. Local-first: plain files + git, zero LLM in the hot path. Works with Claude Code.
cue skills add sma-framework/sma --profile core★ 22 · strong (score 6.8) · Scala
MCP server for deep semantic analysis of Scala via SemanticDB — exact find-usages, class hierarchies, implicit resolution & call paths for AI coding agents like Claude Code. Beyond grep and standard LSP.
cue skills add MercurieVV/ScalaSemantic --profile core★ 1 · strong (score 6.8) · Rust
Lossless, on-device token-cost reduction for Claude Code and LLM coding agents. Free plugin: compresses tool-result output, dedups context, compacts the system prompt — stacks on Anthropic prompt caching. Rust hot path, Python fallback, fail-open. PolyForm Noncommercial.
cue skills add MikkoParkkola/glyphdown --profile core★ 1 · strong (score 6.6) · Shell
Full-spectrum consolidation for Claude Code config files. Audits CLAUDE.md, rules, skills, and memory — not just memory. Detects dead paths, stack mismatches, duplications, vague directives.
cue skills add JulienMicrofacto/deep-clean-skill --profile core★ 2 · strong (score 6.5) · Python
Integrate Higgs v3 TTS into ComfyUI for multilingual speech synthesis, zero-shot voice cloning, emotional control, and dialogue generation.
cue skills add caiyo-slim/Higgs_v3-TTS-ComfyUI --profile core★ 1 · strong (score 6.3) · Python
Isolated Docker environments for Cursor and Claude Code with path-parity workspaces.
cue skills add aKyther/orcan --profile core★ 3 · strong (score 6.2) · Swift
A lightweight macOS menu bar utility that shows the frontmost Finder path — copy paths, run cd commands, open Terminal or Ghostty, and launch Codex, Claude, or Hermes.
cue skills add bhino50/finder-path --profile core★ 6 · strong (score 6.1) · JavaScript
own your agent security — a deterministic, offline firewall for AI agent tool calls. Blocks secret exfil, prompt injection and destructive commands before they run; same call, same verdict, no model in the decision path. 100% recall / 100% precision on a 298-sample corpus, scored in CI against live rivals. Claude Code hook or MCP proxy.
cue skills add askalf/redstamp --profile core★ 0 · strong (score 6) · JavaScript
Practical MCP servers: time tracker, price tracker, spreadsheet, invoice. Local, offline-licensed, one-time Pro.
cue skills add theluckystrike/mcp-servers --profile core★ 0 · strong (score 6) · Go
Control JetKVM devices from the CLI or coding agents through MCP
cue skills add kaaanata/jetkvm-cli --profile core★ 6 · strong (score 5.9) · Go
A Unix-friendly CLI for LLM chat and text generation. One interface for Anthropic Claude, OpenAI, Groq, and Cerebras — pipe stdin, reference files with `@path`, and stream responses right in your terminal.
cue skills add micheam/ai-assistant-console --profile core★ 1 · strong (score 5.8) · TypeScript
一個 path-scoped 的 web 介面,讓你透過瀏覽器跟住在各 repo 裡的 agent(claude -p)高效溝通。 A path-scoped web GUI to talk to the coding agents living in your repos — through the browser.
cue skills add kirinchen/porthole --profile core★ 0 · strong (score 5) · TypeScript
AI Dependency Security MCP Server
cue skills add foudhilriahi/DepGuard --profile core★ 1 · potential (score 4.8) · HTML
Blazor Server app that converts books and documents (PDF, EPUB, DOCX, HTML, MOBI, AZW, RTF, ODT) into structured courses. A multi-LLM pipeline (OpenAI, Claude, DeepSeek, Gemini) extracts concepts, correlates them via LSH/SimHash into a knowledge graph, and generates a learning path with RAG retrieval, quizzes, and progress tracking.
cue skills add mindattic/Tutor --profile core★ 1 · potential (score 4.4) · Python
A single-source catalog of “AI skills” (Markdown SKILL.md files) plus a PowerShell sync tool that pushes those skills into local/global AI tool skill paths and can generate tool-specific rule/instruction files.
cue skills add coff33ninja/ai-skills --profile core★ 1 · potential (score 4.3) · JavaScript
Installable deterministic gates (hooks) for Claude Code: block destructive commands, protected paths, and enforce delegation/spec/quality rules. Configurable per project.
cue skills add DevRik99/claude-gates --profile core★ 1 · potential (score 4.3) · TypeScript
Claude second brain — a private markdown knowledge base served to every Claude surface over MCP, with a read path that proves its own citations.
cue skills add Obelyth/cortex --profile core★ 1 · potential (score 4.3) · Shell
Claude Code skills for auditing, tuning, and safely changing UniFi networks via the controller API — baseline capture, RF tuning, the write path, and security review.
cue skills add devondragon/unifi-network-ops --profile core★ 9 · potential (score 4.2) · Ruby
Opinionated, agent-native Rails template — the production Rails starter ZAR uses internally, packaged with a CLAUDE.md operating manual, 32 Claude skills, and 17 path-scoped coding rules.
cue skills add zarpay/rails-template --profile core★ 10 · potential (score 4.1) · HTML
sprezzature is a set of Claude / OpenCode skills with a curated design system for a front-end stack. It covers colors, accessibility, the user interface (UI), user experience (UX), audio, vision, and the path from the command-line interface (CLI) to the graphical user interface (GUI).
cue skills add warith-harchaoui/sprezzature --profile core★ 4 · potential (score 3.8) · TypeScript
Read-only performance diagnostics for DeepSeek Harness: session load/restore timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via /fast, persisted as reconstructable session events with async sampling off the model path.
cue skills add PerryLink/dsh-fast --profile core★ 2 · potential (score 3.7) · Rust
SkillSpec is a DSL that adds types, contracts, composition, and tests around agent skills, then compiles back down to the same SKILL.md that existing runtimes already understand. Once a skill works and you want to make it production-ready, you codify it into a .agent file and get versioning, structural diffs, type checking, and a path to CI/CD.
cue skills add e01n0/skillspec --profile core★ 1 · potential (score 3.6) · Shell
Always-on skill pack that stops AI coding agents from claiming work is done when only the code path (not the real behavior) was verified. Portable SKILL.md for Claude Code, Codex, Cursor, and any agent.
cue skills add jpoindexter/verified-done --profile core★ 1 · potential (score 3.3) · Shell
Turn ZCode into a full AI game dev studio - 49 specialized agents, 73 workflow skills, path-scoped coding standards, and an optional hooks plugin for commit validation and session recovery. ZCode-native adaptation of Claude-Code-Game-Studios.
cue skills add HunLuanZhiZhu/ZCode-Game-Studios --profile core★ 1 · potential (score 3.3) · Crystal
Deterministic binary that delivers the right documentation to the right moment — compiles convention-doc frontmatter into triggers, generates skill wrappers, and injects path- and construct-scoped rules at edit time via Claude Code hooks.
cue skills add NEXL-LTS/agent-apropos --profile core