core77 skills discovered by cue. Last updated 2026-07-21.
★ 1774 · exceptional (score 24.5) · TypeScript
AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart search by use case, content remix, sample images.
cue skills add YouMind-OpenLab/nano-banana-pro-prompts-recommend-skill --profile core★ 110 · exceptional (score 17.9) · Python
World-class creative director in a skill. Methodology-driven ideation (SIT, TRIZ, Lateral Thinking, bisociation) + a Cannes Lions evaluation engine, powered by a library of 571 legendary award-winning cases.
cue skills add smixs/creative-director-skill --profile core★ 475 · exceptional (score 17.3) · TypeScript
Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments.
cue skills add BlockRunAI/blockrun-mcp --profile core★ 153 · exceptional (score 16.1) · JavaScript
Native Safari browser automation for AI agents. 80 tools via AppleScript — zero overhead, keeps logins, runs silently in background. Drop-in alternative to Chrome DevTools MCP with 40-60% less CPU/heat on Apple Silicon.
cue skills add achiya-automation/safari-mcp --profile core★ 62 · exceptional (score 15.6) · Shell
Agent Skill for generating AGENTS.md files following the agents.md convention | Claude Code compatible
cue skills add netresearch/agent-rules-skill --profile core★ 2 · exceptional (score 15.5) · Python
kimiflow — Claude Code + Codex plugin for codebase mapping, gated feature/fix flows, token-cheap learning memory, and Obsidian Vault MCP setup.
cue skills add kimikonapps/kimiflow --profile core★ 0 · exceptional (score 15.5)
Run your AI CMO from your agent — the AutoWhisper skill for Claude, Cursor, n8n & any MCP agent. Generate & publish marketing content across 30+ platforms.
cue skills add xnjiang/autowhisper-skill --profile core★ 151 · exceptional (score 15) · HTML
Advanced AI Code Strategy Advisor for Developer Agents (2026)
cue skills add 1iry/multi-agent-architecture-advisor --profile core★ 126 · exceptional (score 14.5) · TypeScript
MCP server for controlling Adobe Premiere Pro via CEP/ExtendScript — 269 tools for AI-driven video editing
cue skills add leancoderkavy/premiere-pro-mcp --profile core★ 52 · exceptional (score 14.1) · Go
Official MCP Server for Buildkite.
cue skills add buildkite/buildkite-mcp-server --profile core★ 152 · exceptional (score 14) · HTML
AI Coding Agent Orchestrator 2026: Pro-Level Strategy & Review Framework
cue skills add nam271212/strategic-advisor-orchestrator --profile core★ 6 · exceptional (score 14) · Shell
A Claude Code skill that writes, fixes, and validates OpenTelemetry Collector configs — processor order, core-vs-contrib, pull-vs-push exporters, the works.
cue skills add s3onghyun/otelcol-doctor --profile core★ 49 · exceptional (score 13.5) · Python
arifOS — Constitutional MCP kernel for governed AI execution. AAA trinity: AGI (Mind) · ASI (Heart) · APEX (Judge). Built for the sovereign agentic era.
cue skills add ariffazil/arifos --profile core★ 9 · exceptional (score 13.4) · TypeScript
Official MCP server for Frihet ERP — 157 tools for AI-powered invoicing, tax & e-invoicing compliance (VeriFactu, TicketBAI, Facturae), banking, CRM, HR/payroll & POS. Works with Claude, ChatGPT, Cursor, Windsurf, Cline, Antigravity, Codex, Copilot, Gemini CLI — and any MCP-compatible client.
cue skills add Frihet-io/frihet-mcp --profile core★ 135 · exceptional (score 13.3)
The CCAR-F, CCAR-P prep guide built for non-technical learners and engineers alike. Curated resources, Claude skills, and a learning path that goes beyond the exam.
cue skills add sarveshtalele/claude-architect-exam-guide --profile core★ 0 · exceptional (score 13) · Python
Claude Code skill for data-driven SEO content auditing (keep/boost/merge/noindex/remove) from GSC BigQuery data, with a data-sufficiency guard
cue skills add berfuece/seo-prune-audit --profile core★ 0 · exceptional (score 13)
Review a PRD / spec and catch structural defects before code — formal-verification thinking as a Claude Code skill, every finding traced to the source.
cue skills add happysasha18/product-prover --profile core★ 6 · exceptional (score 12.6) · Shell
The best blockchain harness for agentic AI - on-chain execution with runtime, skills, and component library.
cue skills add aomi-labs/skills --profile core★ 32 · exceptional (score 12.5) · Python
Agent-native course marketplace and skill registry for executable AI-agent curricula
cue skills add nicolasmelo1/logion --profile core★ 51 · exceptional (score 12.5) · HTML
🧿 MythOS 2026: Claude-Powered AI Narrative Engine & Sub-Agent Framework for Epic Storytelling
cue skills add KarmaDevplacer/Mythos-Claude-Orchestrator --profile core★ 103 · exceptional (score 12.3) · Shell
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★ 151 · exceptional (score 12) · HTML
Claude Mythos Engine 2026: AI Sub-Agent Framework for Epic Interactive Storytelling
cue skills add Vitorlindo201/Themata-Claude-Scribe --profile core★ 1363 · exceptional (score 12) · Python
Local first codebase intelligence
cue skills add chunkhound/chunkhound --profile core★ 32 · exceptional (score 11.7) · Python
Outline-Driven Development for Claude Code - 46 agents, 25+ skills, diagram-first methodology, AST-based editing, atomic commits.
cue skills add OutlineDriven/odin-claude-plugin --profile core★ 2 · exceptional (score 11.4)
Organize Codex, Claude Code, MCP, skills, plugins, and AI-agent tools into one clean local home with safe migration rules and legacy path support. 整理 Codex、Claude、MCP、skills 和插件到统一 AI home。
cue skills add lxhcn/ai-home-migration --profile core★ 3 · exceptional (score 11.2) · 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 11) · Python
Downloadable Chinese writing naturalization skill package for preserving facts, terminology, disclosure, genre, and author voice.
cue skills add Oxforce/haning-humanize-writing-skill --profile core★ 1 · exceptional (score 10.8) · 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★ 900 · exceptional (score 10.6)
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★ 1 · exceptional (score 10.3) · TypeScript
Per-project todo tracking + project brain + autonomous plan-then-build, with a local broadsheet dashboard for Claude Code
cue skills add gonoff/claude-todos-skill --profile core★ 3 · exceptional (score 10.2) · TypeScript
AI prompts, agents, and skills as loadable plugins.
cue skills add ncaq/konoka --profile core★ 0 · exceptional (score 10) · 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★ 0 · exceptional (score 10) · HTML
Lint Your Prompts, Ship Better Agents – Prompt Refiner 2026 Rule Engine
cue skills add Kenny27lokku/prompt-integrity-validator --profile core★ 1 · exceptional (score 9.8) · HTML
Claude Newton: AI Reasoning Partner 2026 - Calibrated Pushback & Current Sources
cue skills add Darkmalan-1987/sparring-reason --profile core★ 0 · exceptional (score 9.5) · HTML
Claude Quiz Engine 2026 - Moodle MCQ Generator for GIFT XML Aiken
cue skills add Rick-254/moodle-quizsmith --profile core★ 12 · exceptional (score 9.3) · JavaScript
Operational metadata, health, schemas, and public interface discovery for Bittensor subnets.
cue skills add JSONbored/metagraphed --profile core★ 0 · exceptional (score 9) · HTML
cue skills add sfdfddfs13QWE/advisor-strategy-skill --profile core★ 1 · exceptional (score 8.3) · Python
⏱️🎮 Speedrun Route Optimization & Sequence-Break Analysis Engine | Production-grade Claude Code harness (v2.1.0). Features Microkernel Event Bus, DAG critical-path solver, frame-math heuristics, and live speedrun.com / TASVideos API integrations.
cue skills add dungnotnull/speedrun-route-optimization-agent-skill --profile core★ 4 · exceptional (score 8.3) · Go
CLI to move, transfer, and sync Claude Code project state across paths, archives, and remote storage.
cue skills add it-bens/cc-port --profile core★ 1 · exceptional (score 8.1) · PowerShell
Agent skill for Codex on Windows (installable for Claude Code too): triage sandbox startup failures by layer - CreateProcessAsUserW error 5 on the agent execution path, Git Bash/MSYS2 Win32 error 5 incompatibility, elevated setup-helper ACL failures, and config.toml permission tokens that can brick every session.
cue skills add h8nc4y/codex-windows-sandbox-troubleshooting --profile core★ 0 · exceptional (score 8) · HTML
把 Typeless 本地语音记录变成图示化个人复盘的 Claude Code Skill
cue skills add JamesRRR/typeless-personal-review --profile core★ 0 · exceptional (score 8)
Senior Python backend code-review tool. An editor, not a rewriter: it points at the lines that will page you at 3am, explains why, and hands the fix back. Built as an ICM workspace.
cue skills add sergeymanevitch/Redline --profile core★ 19 · strong (score 7.5) · Go
Move your Claude Code history, memory, and sessions between machines (Linux/macOS/Windows), with paths fixed automatically.
cue skills add gowtham-sai-yadav/claude-teleport --profile core★ 0 · strong (score 7.5) · HTML
Claude Code Plugin 2026 — Evidence-Based Vitamin & OTC Analyzer 📊 Install 2 Lines
cue skills add Syarwanfjr/supplement-evidence-stack --profile core★ 0 · strong (score 7.5) · HTML
Spotify Timestamped Notes Plugin 2026: AI-Powered Music Journal for Developer Workflow
cue skills add Albert634png/note-taker-for-spotify --profile core★ 0 · strong (score 7.5) · HTML
Best Claude Code Memory Toolkit Alternative 2026 – Smart Markdown Session Manager
cue skills add Abdo2011-Mahmoud/claude-session-memory-core --profile core★ 0 · strong (score 7.5) · HTML
Token Optimizer 2026: Eliminate Ghost Tokens, Fix Context Decay & Survive Compaction
cue skills add gerrict/ghost-token-hunter --profile core★ 0 · strong (score 7.5) · HTML
Top AI-Powered UI/UX Design Generator & Code Assistant 2026
cue skills add MichelSR25/Claude-Code-Agent-Design-Kit --profile core★ 0 · strong (score 7.5) · HTML
Best AI Code Architect 2026: Diagram-First Agent Orchestrator with AST Editing & Atomic Commits
cue skills add Fiskopoi/outline-driven-toolkit --profile core★ 0 · strong (score 7.5) · HTML
AI Content Guard 2026: Adversarial Fact-Check Gate for Error-Free Code & Copy
cue skills add Anant-pentester/adversarial-gatekeeper --profile core★ 0 · strong (score 7.5) · HTML
Best AI Agent Skill Finder 2026 – Multi-Registry Install & Security Labels
cue skills add Edward0l1/skill-flare-discover --profile core★ 1 · strong (score 6.8) · 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★ 1 · strong (score 6.7) · Python
fidelis is zero-LLM agent memory for Claude Code and AI agents: a local-first memory layer whose default retrieval path uses BM25, dense vectors, and reciprocal rank fusion with no LLM call. It returns your original passages verbatim instead of paraphrasing and runs fully local. Benchmarked on LongMemEval-S. MIT, by Hermes Labs.
cue skills add hermes-labs-ai/fidelis --profile core★ 3 · strong (score 6.6) · Python
Path-aware bash permissions for Claude Code.
cue skills add karlkfi/claude-workspace-guard --profile core★ 2 · strong (score 6.5) · 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★ 16 · strong (score 6.4) · 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 6.3) · CSS
Turn any podcast transcript into reusable AI judgment assets — framework cards, decision checklists, interview talking points, and an interactive HTML course.
cue skills add Cobb04/podcast-to-course --profile core★ 0 · strong (score 6)
Hosted guarded screenshots and PDFs for MCP clients
cue skills add BaiqingL/latchshot-mcp --profile core★ 6 · strong (score 5.7) · 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★ 0 · strong (score 5.5) · HTML
sPEG Framework 2026: AI-Powered Scarcity-Adjusted Equity Valuation Tool – GitHub
cue skills add Aungkyawdna/sPEG-compound-solvency-model --profile core★ 0 · strong (score 5.5) · HTML
🧠 LoreConvo 2026: Claude Session Memory Mesh – Persistent Cross-Surface AI Conversations
cue skills add iproject96/loreweave-memoria --profile core★ 3 · strong (score 5.2) · 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 · strong (score 5) · 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★ 0 · strong (score 5) · TypeScript
cue skills add kieksme/mcp-swetrix --profile core★ 4 · potential (score 4.6) · Swift
macOS menu bar app for grabbing code/text blocks out of your active Claude Code session — fenced code, tool output, file paths, URLs, whole messages — click to copy, drag to paste, star to pin.
cue skills add krisbradley/clawpypaste --profile core★ 4 · potential (score 4.5) · 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★ 2 · potential (score 4.4) · 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★ 1 · potential (score 4.3) · Python
Multi-way sync of agentic chat history (Cursor IDE/CLI, Claude Code, Codex) between Macs, with per-machine username/path rewriting.
cue skills add mhadifilms/chatmesh --profile core★ 1 · potential (score 4.2) · JavaScript
Interactive, local-first study path for Anthropic's four Claude Certification exams — lessons, quizzes, practice exams, and flashcards. Unofficial.
cue skills add davidalex89/claude-cert-study-path --profile core★ 10 · potential (score 4.2) · TypeScript
Learn Claude Code -- Harness Engineering for Real Agents (forked with learning path guides)
cue skills add Zenobia000/learn-claude-code --profile core★ 3 · potential (score 3.7) · JavaScript
Stop burning tokens on trial-and-error: make your AI agent find the path that actually works, name what is impossible, and stress-test it before you build. Cross-LLM skill suite (Claude Code, Codex, Cursor, Windsurf, Cline, Gemini, OpenCode).
cue skills add divisingh19988-gif/d-strange --profile core★ 2 · potential (score 3.5) · Shell
Harness-first agent research: a bounded act→verify loop runner with one-line adapters for 10 lean harnesses (Pi, Hermes, aider, Codex, Goose, Claude, Ollama…) + Crucible, a portable benchmark that scores the harness, not the model — gated Safety×Completion/Path/State Goodput, factorial harness×model×seed, cost & local-vs-cloud routing.
cue skills add Siddhant-Goswami/Crucible --profile core★ 1 · potential (score 3.3) · Python
Autonomous product-readiness audits for apps & AI agents — a Claude Code and Codex skill suite that safely walks your user paths, finds where they break for real users, grades findings by evidence, and never calls anything "ready" without proof. Not code review — does it actually work?
cue skills add NeuraCerebra-AI/Shipworthy --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/apropos --profile core★ 1 · potential (score 3.3) · JavaScript
A framework-agnostic Roblox/Luau coding standards & best practices skill for AI agents. Features an interactive CLI installer supporting version selection, automatic path detection, and autocomplete search for 72+ agents (Claude Code, Cursor, Windsurf, Cline, Antigravity, etc.).
cue skills add andrian-syh/roblox-best-practices-skill --profile core★ 1 · potential (score 3.1) · TypeScript
An ESLint for the Skills era: a paranoid, offline CLI that lints, audits, and scores your SKILL.md / agent-skill files for secrets, prompt-injection bait, token bloat, broken paths, and over-broad tool grants.
cue skills add rwrife/skill-sniffer --profile core★ 16 · potential (score 3) · Rust
🪛 Rust powered precision file tools for AI agents thats minimize context use: patch-based edits, kernel-enforced path confinement. Dramatically fewer tokens than naive read/write. MCP Server or embeddable, bring your own MCP (Rust, Python, Nodejs). Come with Skills.md (npx skills add ckanthony/Chisel)
cue skills add ckanthony/Chisel --profile core