zai-orchestrator
15913Skill Claude Code
A senior architect-level skill that coordinates Vision, Search, and Zread to solve complex engineering problems.
Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 374,997 indexed, measured the same four ways as everything else here.
Skill Claude Code
A senior architect-level skill that coordinates Vision, Search, and Zread to solve complex engineering problems.
kaustubhhiware/agent-skills-fullstack-development
Skill Claude Code
Behavioral guidelines to reduce common LLM coding mistakes. Emphasizes thinking before coding, simplicity, surgical changes, and goal-driven execution. Load this when writing or modifying code to avoid overengineering and unnecessary changes.
Skill Claude Code
An example skill demonstrating the framework capabilities. Use when testing skill execution with JavaScript, Python, or Shell scripts.
Skill Claude CodeCodex
Research AEO (Answer Engine Optimization) opportunities by discovering what questions AI engines are actually answering in your niche, which domains and pages they're citing, and what content formats are winning citations.
Skill Claude CodeCodex
Format local Markdown headings and lists consistently.
Skill Claude CodeCodex
Determine which Singapore Government System Security Plan(s) apply to a system under the ICT&SS Policy Reform (IM8's successor) and emit the resulting control baseline — including stacking the Generative AI overlay and Digital Service Standards profiles on top of a cybersecurity SSP. Use whenever a project touches SG…
aidityasadhakim/ads-creative-skill
Plugin Claude Code
Bundles 3 skills · 116 tokens together
Automated ads creative generation — research brand DNA, fill 40 prompt templates, and generate images via viostudio.id API (nano-banana-2).
Skill Claude CodeCodex
Angular enterprise architecture guidelines for structuring scalable, production-grade applications. Use when scaffolding a new Angular project, reviewing project structure, setting up feature slices, choosing state management, configuring data fetching, or making architectural decisions in an Angular/TypeScript…
Skill Claude CodeCodex needs its repo
A prompt-writing guide that turns a simple image idea, visual style, and optional aspect ratio into a structured prompt for AI image generators.
Skill Claude CodeCodex
Sync local Markdown files to Notion with full formatting support. Use when user wants to backup, sync, or migrate files to Notion, mentions uploading to Notion, or says sync to Notion. Features include: (1) Recursive directory structure preservation, (2) Complete Markdown formatting (bold, italic, code, links, lists…
Skill Claude CodeCodex
Build an LLM-as-Judge evaluator for one specific failure mode. Binary pass/fail only. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness) and cannot be checked with code. Do NOT use when the failure can be checked with regex, schema validation, or execution tests. Do NOT use…
Plugin Claude Code
Bundles 2 skills · 128 tokens together
Archived FairyGUI editor and runtime reference skills (final edition).
claw-opus/proactive-self-improving-agent
Skill Claude CodeCodex
A skill that records failed actions, user corrections, missing capabilities, tool errors, outdated knowledge, and better approaches in separate files.
Plugin Claude Code
Bundles 1 skill, 2 commands, 2 hooks · 446 tokens together
Multi-language iterative PR review + autofix loop (built-in iteration engine + pr-review-toolkit + optional Codex).
torakagemusha-sudo/torafirma-skill-router
Skill Claude CodeCodex
Use first when a task may benefit from specialized capability in a large local skill library. Search indexed metadata, select an explainable ranked candidate, then fetch only the exact SHA-256 revision returned by search.
Skill Claude CodeCodex
Search BOSS直聘 for non-big-tech internship positions via chrome-osascript, extract full JD (DOM raw), summarize and tag via subagent, and persist to YAML. Optionally sync to Notion. Use when the user wants to find, collect, analyze, or track internship listings.
Skill Claude CodeCodex
Turn a CFP submission into a structured talk outline with section timings, theory/practical balance, demo risk assessments, fallback plans, and Patrick Winston opening/close principles applied throughout.
Plugin Claude Code
Bundles 13 skills · 1,038 tokens together
Integrity forensics for research papers, and the reviewer discipline for writing up what it finds. /anti-autoresearch builds a span-anchored evidence ledger, fans out 11 auditors (consistency, citation, baseline, experiment, eval design, proof / derivation, presentation, AI-style impressions, adversarial.
zeke/preview-deployments-skill
Skill Claude CodeCodex
Add Cloudflare Workers preview deployments to existing GitHub apps using GitHub Actions, Wrangler, gh secrets, and the GitHub Deployments API. Use when asked to add per-PR preview deployments, ephemeral Workers previews, preview URLs, GitHub deployment statuses, Cloudflare preview environments, or teardown on PR close.
yusufkaraaslan/skill-seekers-plugin
Plugin Claude Code
Bundles 1 skill, 3 commands · 79 tokens together
Transform 17 source types (docs, GitHub, PDFs, videos, Jupyter, Confluence, Notion, Slack, and more) into AI-ready skills and RAG knowledge for 16+ LLM platforms.
vshrinath/virtual-product-factory
Skill Claude CodeCodex
Translates vague ideas into scoped, testable specs. Asks clarifying questions and marks in/out of scope explicitly. WHEN to use it - translating vague requirements into buildable briefs, breaking large features into shippable increments, defining acceptance criteria, scoping releases, or writing feature briefs for…
Skill Claude CodeCodex
Expert Chrome developer skill covering advanced browser APIs and capabilities. Use this skill whenever working on Chrome extensions (Manifest V3), WebAssembly (Wasm 3.0), WebGPU (graphics and compute), WebNN (neural network inference), Chrome Built-in AI (Gemini Nano Prompt API, Summarizer, Translator), local ML model…
Skill Claude CodeCodex
A protocol framework for long-horizon autonomous tasks. Targets three empirically-observed failure modes — cognitive loops, stalling, runtime fragility — by prescribing state management, stall detection, and watchdog mechanisms. Validated on multiple task types including paper writing (4 ICLR-format surveys…
Plugin Claude Code
Bundles 1 skill, 5 commands · 132 tokens together
Qwen3-TTS based high-quality Korean/multilingual text-to-speech synthesis.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: