26,182 tagged ai, measured the same way as everything else here.
Browse within: LLM 535agent 471cli 370chatgpt 286agents 197ml 140agentic 121LangChain 118chatbot 117bun 116generative-ai 104cybersecurity 102hacking 98mcp-server 83
vlad-ryzhkov/ai-context-engineering-for-qa
Skill Claude Code
Verifies structural integrity and compliance of .claude/agents/ and .claude/qaagent.md against init-agent standards. Use after modifying agent files. Do not use for SKILL.md audit — use /skill-audit.
Skill Claude Code
MUST use for ANY user request. This is a rigid requirement that applies to all tasks and conversations.
Skill Claude CodeCodex
Hatch and raise a terminal companion pet. A small ASCII creature lives beside your coding sessions — it reacts to your work, has a personality, and persists across conversations.
Skill Claude CodeCodex
This skill should be used whenever implementation or review depends on external, version-sensitive facts: libraries, SDKs, APIs, CLIs, cloud services, security advisories, changelogs, release notes, or documentation that may have changed. The skill anchors local versions, ranks source quality, runs an executable probe…
Alexander-Kz/video-layer-skill
Skill Claude CodeCodex
Produces whiteboard-explainer video layers from a voiceover MP3 for Your Channel YouTube channel (and similar faceless curiosity-essay channels). Orchestrates a multi-agent pipeline that transcribes the audio, plans rapid-cut scenes synchronized to narration, writes per-scene image prompts in fixed whiteboard style…
Skill Claude CodeCodex
Deep multi-angle web research with AI synthesis, images, videos, and persistent history.
Skill Claude Code
A Chinese-language content-writing skill for creating posts designed for platforms such as Xiaohongshu, Douyin, WeChat official accounts, Bilibili, and Weibo.
Skill Claude CodeCodex needs its repo
Dispatch coding tasks to other AI agents via oneagent (oa). Use when you want to delegate file edits, code generation, reviews, or other scoped tasks to a different model or backend — for example, sending a targeted edit to Codex while continuing your own work.
Skill Claude CodeCodex
Universal prose audit. Scores writing on TWO axes — AI-Slop (does this read like AI wrote it?) and Comprehension (can a fresh reader follow this?). Use PROACTIVELY as a mandatory final QA pass on ANY prose generated for humans to read — every email (internal or external), proposal, report, status update, blog post…
Skill Claude CodeCodex
Persistent memory system for the agent. Two-tier storage: user (/.agents/memory/MEMORY.md) and project ( /MEMORY.md). Five memory networks: experiences, world knowledge, beliefs, reflections, entity summaries. Task closure ("we're done", etc.) triggers a mandatory task-done memory sweep (remember subagents per…
flyingsquirrel0419/squirrel-skill
Skill Claude CodeCodex
Full-cycle software development agent: plans, builds, tests, lints, fixes bugs, and writes production-grade README docs. ALWAYS use this skill when the user wants to: build or scaffold a new project, add features to existing code, fix bugs, improve code quality (lint, format, refactor), write or improve a README, add…
Skill Claude Code
Framework for what to consolidate to memory before a context reset. Triggered when the runner injects a "final tick warning." YOU decide what's worth carrying forward — this skill gives you the framework, not a checklist.
luca-mastrostefano/agent-native-setup
Skill Claude Code
Extract a complete agent-native-setup profile from an existing repo's agent setup (contracts, .claude/.cursor/.gemini tooling, MCP, docs conventions, git gates) — inventory, classify, parameterize, verify by byte-diff, and ship. Use when someone wants to turn a well-structured repo into a shareable profile.
Gildaciolopes/claude-caveman-ultra
Skill Claude CodeCodex
Ultra-compressed communication mode. Cuts token usage 75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or…
Skill Claude CodeCodex
Use when a user asks how you (the agent) work, how slaude works, how to use/interact with you, what commands or capabilities exist, or how engagement, approvals, the knowledge base, skills, memory, MCP, or cron behave. Self-documentation of the slaude runtime — read it, then explain in your own voice.
Skill Claude Code
Passive screen activity tracker. Use this skill when the user asks what they did today, wants to track their screen activity, or needs to analyze their productivity patterns.
Skill Claude CodeCodex
A Chinese-language skill that guides interactions in a fictional palace-court role-play style based on the television drama Empresses in the Palace. Its description covers setup, behaviour rules, interaction methods, and reports.
Skill Claude CodeCodex
A bias-check technique: spawn 2+ independent subagents, each attacking the idea from a different angle, to catch the flaw BEFORE it's set in concrete.
Skill Claude CodeCodex
Fetch weather data for any city using the OpenWeather API.
smeseik-ai/arabic-content-studio
Skill Claude CodeCodex
A library and writing aid for opening lines in Arabic content. A hook is the first line or idea intended to make someone continue reading or watching.
Skill Codex
Turn a contested question, research brief, technical choice, or high-impact decision into a source-grounded interactive evidence map. Use when an agent must preserve support, contradiction, qualification, and missing evidence; make every evidence edge traceable to a dated source region; pressure-test a conclusion; or…
erwinblom/de-clicheverwijderaar
Skill Claude CodeCodex
Verwijdert versleten formuleringen, voorspelbare taalpatronen en lege beeldspraak uit Nederlandse teksten, zonder feiten, betekenis of de eigen stem van de schrijver te veranderen.
figueroaignacio/ignaciofigueroa.dev
Skill Claude CodeCodex
Use when the user wants to translate a repository README, make a repo multilingual, localize docs, add a language switcher, internationalize the README, or update localized README variants in a GitHub-style repository.
Skill Claude CodeCodex
AnyGen: Download artifacts from a completed task.
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: