core67 skills discovered by cue. Last updated 2026-10-22.
★ 31733 · exceptional (score 20.5) · TypeScript
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
cue skills add mksglu/context-mode --profile core★ 554 · exceptional (score 20.3) · Python
Autonomous text-to-game pipeline for Godot, powered by Claude Code,Codex,Opencode
cue skills add RandallLiuXin/GodotMaker --profile core★ 4225 · exceptional (score 18) · JavaScript
Answer me with HTML — an agent skill that answers hard questions with a one-page HTML you can actually read. 让 AI Agent 用一页 HTML 回答复杂问题。
cue skills add QingYunA/answer-me-with-html --profile core★ 320 · exceptional (score 16.8) · Java
Production-grade Claude Code and Codex skills for Spring Boot developers
cue skills add rrezartprebreza/spring-boot-skills --profile core★ 7 · exceptional (score 16.2) · Python
Claude Code skill for Chinese long-form & WeChat article production · 中文长文与公众号内容生产
cue skills add sanshengai/sansheng-write --profile core★ 20 · exceptional (score 16) · Python
Thuế thu nhập cá nhân 2026: skill AI (Claude) tính thuế, quyết toán, giảm trừ gia cảnh, thuế người nước ngoài — Vietnam personal income tax 2026 skill
cue skills add tndvnn/tncn --profile core★ 117 · exceptional (score 15.9) · HTML
AI Coding Agent Orchestrator 2026: Pro-Level Strategy & Review Framework
cue skills add nam271212/strategic-advisor-orchestrator --profile core★ 37 · exceptional (score 14.8)
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★ 0 · exceptional (score 14.5) · Shell
An operational tool for monitoring knowledge persistence and state integrity in AI agent environments.
cue skills add aniboy2k-gif/memory-health --profile core★ 161 · exceptional (score 14.5) · JavaScript
JobAppAgent: open-source AI job application agent (Agent Skill + CLI). Searches wide, matches one verified résumé, applies within your rules on Greenhouse, Ashby and Lever, tracks confirmed submissions.
cue skills add vaibhavarora14/job-application-agent --profile core★ 37 · exceptional (score 14.3) · JavaScript
Claude Code plugin suite: brewcode (skill/agent/rule authoring, semble semantic search, superreview and teams setups), brewdoc (doc sync, PDF, publish), brewtools (text optimization, secrets scan, deploy, SSH, subagent guards)
cue skills add kochetkov-ma/claude-brewcode --profile core★ 6 · exceptional (score 14.2) · 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★ 8 · exceptional (score 13.8) · Python
A free, open-source suite of website skills: instructions your AI coding assistant follows to build and test a site you own, so people find it on Google and in AI answers.
cue skills add karero/croftweaver --profile core★ 3 · exceptional (score 13.6) · Python
The fast tier of the wise-men council as its own skill: three Claude subagents down three reasoning paths, one checked decision memo in a third of the full council's time. Ships its own blind eval.
cue skills add Ali-expandings/wise-men-flash --profile core★ 84 · exceptional (score 13.4) · Python
Self-hosted meeting notes with no bot in the call. Records Meet, Teams and Zoom from the browser, transcribes on your own hardware, and lets Claude or ChatGPT read and edit your library over MCP.
cue skills add Valtora/Nojoin --profile core★ 33 · exceptional (score 12.6) · JavaScript
Chart a project from a loose idea, then navigate it ticket by ticket on GitHub Issues.
cue skills add ToRvaLDz/trailhead --profile core★ 23 · exceptional (score 12.5) · Python
Claude Code skill for managing the full software development lifecycle
cue skills add DarrenBenson/sdlc-studio --profile core★ 4 · exceptional (score 12.3) · 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★ 5 · exceptional (score 12.2) · Shell
Agent Skill for creating and managing TYPO3 extension tests | Claude Code compatible
cue skills add netresearch/typo3-testing-skill --profile core★ 2 · exceptional (score 12) · Python
Multi-perspective parallel Codex review for Claude Code — N sub-agents, each framed with a role you decide per call.
cue skills add ehzawad/codex-council --profile core★ 45 · exceptional (score 11.3) · Python
Generate personalized coding lessons from your own codebase. A Claude Code skill: three surfaces (tutorial / vocab / status), six writing-to-learn entries, audience-facing path with six venue templates. v2.0.0 released 2026-05-10.
cue skills add Terryc21/tutorial-creator --profile core★ 970 · exceptional (score 11)
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★ 0 · exceptional (score 11) · Python
RONGE UI DESIGN — a screenshot-driven 90-point UI method for mobile products
cue skills add bugtakue/ronge-ui-design --profile core★ 0 · exceptional (score 11) · Python
Measure responsive layout instead of eyeballing screenshots. Real device widths, named offenders, fix patterns. Works as a Hermes/Claude Code skill or a plain Playwright script.
cue skills add lareesahu/responsive-audit --profile core★ 120 · exceptional (score 10.8) · 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★ 6 · exceptional (score 10.7) · 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★ 3 · exceptional (score 10.7) · TypeScript
portuguese (Brazil) on rails
cue skills add h0ffmann/ptbr-writer --profile core★ 0 · exceptional (score 10.5) · HTML
cue skills add sfdfddfs13QWE/advisor-strategy-skill --profile core★ 2 · exceptional (score 10) · JavaScript
Claude Code skill: describe the data you want from any website and get a CSV — no selectors, no code. 스크래핑을 몰라도 'URL + 한 문장'으로 데이터를 CSV로 받는 Claude Code 스킬. Playwright analysis, sample-row confirmation, rate-limited collection, saved recipes; honest about bot checks, logins and robots.txt.
cue skills add scrapesmith/scrape-skill --profile core★ 45 · exceptional (score 9.9) · TypeScript
Point it at a repo and it configures your AI coding assistant for that stack: agents, framework skills, MCP servers, path-scoped rules. One install, seven assistants - Claude Code, Copilot, Cursor, Gemini CLI, Codex CLI, Cline, Kimi Code. MIT.
cue skills add claude-dev-suite/claude-dev-suite --profile core★ 4 · exceptional (score 9.2) · TypeScript
Your AI forgets. Pathrule remembers. The open-source knowledge layer for coding agents: path-scoped memories, rules and skills for Claude Code, Codex, Cursor, Copilot, Windsurf and any MCP client.
cue skills add pathrule/pathrule --profile core★ 9 · exceptional (score 9.1) · TypeScript
Claude Code mods on demand — a skill that reads your conversation and builds the mod that fits: plan progress bar, files pane, context gauge, risky-command guard, test watcher. 11 tested templates, 29 building blocks, a map of 3,057 public mods. Terminal and desktop.
cue skills add timoncool/givememod --profile core★ 6 · exceptional (score 9) · Python
无为 WUWEI: a Claude Code and Codex plugin that runs a chartered agent team through your day, with guards that make the safe path the default one.
cue skills add taoq-ai/wuwei --profile core★ 0 · exceptional (score 9) · HTML
Claude Code Plugin 2026 — Evidence-Based Vitamin & OTC Analyzer 📊 Install 2 Lines
cue skills add Syarwanfjr/supplement-evidence-stack --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★ 1 · exceptional (score 8.8) · Python
Auf den Millimeter geprüft, nicht nur behauptet: DIN-5008-Briefe aus Markdown, als PDF/A gesetzt. Skill für KI-Agenten und CLI.
cue skills add blitzsicht/falzmarke --profile core★ 5 · exceptional (score 8.5) · Go
CLI that ports Claude Code and OpenAI Codex project state: it rewrites absolute paths after a project directory moves, and exports, imports and syncs project state through archives and remote storage.
cue skills add it-bens/cc-port --profile core★ 2 · exceptional (score 8.5) · Python
Claude Code Agent Skill/API: mentor for embedded/IoT hardware projects (MCU selection, cost & time estimates, MVP-first build plans, PCB transition guidance).
cue skills add mh-mansouri/embedded-iot-mentor --profile core★ 0 · exceptional (score 8.5) · Python
给 B 端产品经理用的需求分析 skill：先向客户提问澄清问题，再产出全套可追溯的需求文档。阶段闸门 + 编号体系强制执行，AI 不替你编业务事实。
cue skills add yangdavip/effective-requirements-analysis-skill --profile core★ 1 · exceptional (score 8.3) · Shell
Run OpenAI Codex and a fresh Claude subagent as parallel adversarial reviewers on a design, PR, or prod gate, then adjudicate both. Always asks: is there a simpler path?
cue skills add RHSTheSecond/cross-model-adversarial-pass --profile core★ 1 · exceptional (score 8.3) · Python
Claude Code plugin that audits careers pages, EVPs and job ads through a candidate's eyes. Scores what your employer brand proves, not what it promises. No evidence → no claim.
cue skills add denzjama/employer-brand-auditor --profile core★ 2 · exceptional (score 8) · TypeScript
Run a plan through AI coding agents (Claude Code, OpenAI Codex, Mistral Vibe) as a sequence of gated phases, and get a change you can review. The golden path, just facts.
cue skills add lbdremy/phax --profile core★ 10 · exceptional (score 8) · Python
Open source input firewall for AI agents, beta. A local scanner checks text, code, PDFs, images, QR codes, audio and video with 1,583 patterns across 117 categories and reports findings and incomplete scans. A Claude Code hook blocks secret material in tool calls and the paths and hosts your policy lists before tools run.
cue skills add sunglasses-dev/sunglasses --profile core★ 0 · exceptional (score 8) · JavaScript
Salesforce presales workflow as a Claude Code plugin — discovery to scope matrix, sprint plan, and timeline with Excel output
cue skills add namit-jpg/presales-agent-skill --profile core★ 0 · exceptional (score 8) · JavaScript
Claude Code plugin that turns text and data into explainer diagrams, tables, and charts, exported as animated HTML and WebP
cue skills add namioto/dsviz --profile core★ 0 · exceptional (score 8) · Python
List of newly created MCP Servers. Automatically updating hourly.
cue skills add GHLists/new-mcp-servers --profile core★ 87 · strong (score 7.8) · 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★ 21 · strong (score 7.8) · Python
Model-agnostic output control for LLM agents: concise, action-first answers with proof and risk preserved. Native install paths for Claude Code and Codex.
cue skills add FlorianBruniaux/flow-lean --profile core★ 1 · strong (score 7.7) · JavaScript
Send screenshots and files to Claude Code / Codex CLI running on a remote Linux server — upload in the browser, copy the path, paste to the agent. npx / uvx, HTTPS, zero deps. 在远程 Linux 上用 Claude Code、Codex CLI 时，把截图和文件从浏览器传给 AI agent，并下载结果。
cue skills add woodti/remote-fileshare --profile core★ 5 · strong (score 6.8) · TypeScript
Keep your AI coding agents true to spec: Tier1 fast-path + Tier2 guards + Tier3 micro-eval on every edit, for Claude Code, Codex, OpenCode and Pi
cue skills add irfndi/oh-my-plumb --profile core★ 1 · strong (score 6.4) · 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 6.3) · Swift
Paste macOS screenshots into the terminal with Cmd+V. A small Swift LaunchAgent puts the screenshot's file path on the clipboard, so coding agents like Claude Code and Codex can read it.
cue skills add s3rgiosan/snaptty --profile core★ 10 · strong (score 6.2) · 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★ 0 · strong (score 6) · Python
Free SEO, GEO & AEO agent skills (SKILL.md) for Claude Code, Codex & Cursor: keyword clustering, search intent, cannibalization, content decay, llms.txt check, AI visibility score.
cue skills add cygnixlabs-cmd/cygnix-seo-skills --profile core★ 0 · strong (score 6) · HTML
Free QR code generator — private by design. 100% browser-side.
cue skills add BryceBin/freeqrly --profile core★ 1 · strong (score 5.8)
10 high-leverage skills for Claude Desktop: research, decisions, meetings, communication, feedback, document comparison, learning paths, content transformation, explanations, and brainstorming
cue skills add abouchard11/claude-desktop-skills --profile core★ 1 · strong (score 5.8) · JavaScript
Claude Code plugin for vfkb — the primary distribution path for the Claude Code harness face (ADR-0045)
cue skills add vilosource/vfkb-claude-plugin --profile core★ 3 · strong (score 5.6) · JavaScript
The hackathon playbook for coding agents. 12 Agent Skills and 5 subagents that take Claude Code, Codex or Cursor from the problem statement to the podium: decode the rubric, build the demo path, prove every number, simulate the judges, ship the package.
cue skills add SaudSatopay/bullseye --profile core★ 1 · strong (score 5.3)
Datacircle lists all the GTM APIs
cue skills add waynehamadi/datacircle --profile core★ 4 · potential (score 4.7)
Unofficial RPM spec for Anthropic's Claude Desktop on Fedora — fixes Wayland/Vulkan crash and Cowork's QEMU firmware paths
cue skills add htsh/claude-desktop-fedora --profile core★ 12 · potential (score 4.4) · 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★ 2 · potential (score 4.4) · Python
GuardRun: a safety-first AI agent harness for DeepSeek and Claude, with a path sandbox, shell command policy, approvals, secret redaction and an audit log.
cue skills add hannnnnnnny/GuardRun --profile core★ 1 · potential (score 4.3) · JavaScript
LLM-agnostic agent harness for trading futures on Claude Code, Codex, or Qwen Code, with a risk-gated order path and pluggable broker MCP servers (TopstepX default).
cue skills add johnamcruz/futures-trading-harness --profile core★ 1 · potential (score 4.2) · Python
Automatic + visual QA for Blender (bpy) scenes — catches overlaps, floating parts, z-fighting and blocked paths, with a Claude Code skill, a pitfalls guide and cosy low-poly example scenes.
cue skills add nonsenseblue/blender-qa --profile core★ 12 · potential (score 3.4) · 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 3.1) · 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★ 26 · potential (score 3.1) · 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