50,342 tagged Claude Code, measured the same way as everything else here.
Browse within: agentic-ai 319antigravity 269agentic-skills 191ai-workflows 185coding-agents 164agentic-framework 109agentic-workflow 109swarm 109Autonomous Agents 106claude-code-skills 99ci 97LLM 96actions 96cai 96
unhealthy-outlander317/context-doctor
Skill Claude CodeCodex
Visualize and diagnose OpenClaw context window usage. Generates a terminal-rendered breakdown showing workspace files (status, chars, tokens), installed skills inventory, and token budget allocation across bootstrap components. Use when: (1) user asks about context window health or token usage, (2) debugging agent…
Skill Claude CodeCodex
Search and read past agent sessions on this machine — your own and other agents' — with agentcarto. Use when the user refers to earlier work ("what did we decide", "carry on from last time", "when did we touch this file"), or when the context you need is in a session rather than in the code.
Skill Claude CodeCodex
Claude-native multi-model routing — dispatch each task to the right Claude model tier (Fable judgment · Opus orchestrate/review + hard build · Sonnet build · Haiku volume) via model-pinned subagents. Use when routing a Claude task by model or reasoning effort, consulting the advisor at a commitment boundary, or…
Skill Claude CodeCodex
Adversarially grill CLAUDE'S OWN answer/plan/reasoning before it ships — make the reasoning explicit (explain harder), then spawn a fresh effort-escalating refute jury that KILLS by default and injects FALSE-PREMISE trap questions, looping until no new defects survive. Forces source citations on every claim…
perfect7613/dsa-system-design-optimizer
Skill Claude CodeCodex
Audits real codebases for data structure, algorithm, database, caching, scalability, reliability, and AI-system design improvements. Use when users ask to reduce time or space complexity, find hot paths, choose DSA patterns, optimize queries, improve architecture, scale a product, review infra, design RAG/agent…
Skill Claude CodeCodex
Cut context tokens by rendering it as images. ctx2img paint turns any text-shaped input (a repo, a directory, a file, markdown, stdin) into dense images that carry the full text at 60-75% fewer tokens, with stable handles and a verbatim factsheet; ctx2img read recovers guaranteed-exact text. Use before ingesting any…
Skill Claude Code
A Chinese-language helper that scans installed AI tools and translates or fills in their skill descriptions so developers can understand what each capability does. It can also produce a list of available skills, agents, and command-line tools.
Skill Claude Code
Expert implementation guidance for the Claude Agent SDK (Python). Use when users are building with the Agent SDK — creating custom tools, managing sessions, controlling permissions, streaming responses, integrating MCP servers, adding hooks, defining subagents, or deploying SDK-based agents. Also use for SDK…
Skill Claude CodeCodex
Design production-grade agentic AI systems from a natural-language use case. Runs a clarification loop, walks grounded decision trees (workflow vs agent, RAG vs fine-tuning, single vs multi-agent, autonomy tiers), and emits a detailed enterprise system design document with embedded interactive architecture, sequence…
Skill Claude Code
A report generator for Ba Zi, a Chinese birth-chart system also called the Four Pillars of Destiny. It calculates the chart from birth information and produces a self-contained HTML report covering elements, cycles, and related interpretations.
Skill Claude CodeCodex
Use when a user needs help turning a business change, technical change, or refactor into execution-ready delivery artifacts (shaped brief, implementation plan, task breakdown) and/or running the implementation through gated, independently reviewed and QA'd multi-agent execution with anti-hallucination grounding. Not…
eva0005/product-marketing-publisher
Skill Claude CodeCodex
Builds the full product marketing foundation for a product — positioning, target audience, messaging pillars, and product soul — then generates channel-ready content (GitHub PR with markdown release note/announcement, X/Twitter tweet copy). Use this skill whenever the user wants to define or sharpen how their product…
Skill Claude CodeCodex
Orchestrate multi-phase background development using coding agents. Use when: (1) a project has multiple sequential tasks that should run autonomously without human intervention between steps, (2) the user wants continuous background work with crash recovery, stall detection, and progress reporting, (3) the user…
Skill Claude CodeCodex
Full-depth audit (a11y, UX, perf, SEO, security, DB, architecture, legal compliance, ops, observability) of a project. Audits by reading the source directly — installs nothing, writes nothing outside docs/audits/. Reports findings with file:line evidence and calibrated severity, optionally mitigates as discovered. Use…
Maximumsoft-Co-LTD/claude-flightdeck
Skill Claude Code
/review — the unified review gate. Use when the user says '/review', '/review design', '/review security', '/review gates', '/review ultra', 'review the UI', 'check design fidelity', 'verify the redesign', 'security review', 'is this safe to merge', 'check for vulnerabilities', 'review the diff', 'review the agent's…
smarks26/claude-plugin-template
Skill Claude Code
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Skill Claude CodeCodex
Situational awareness across your live Claude Code sessions. Open a fresh window and run /conductor to see what every OTHER running window is doing, what it finished, and what's left — read from each session's own transcript. Use when the user says "sort out my windows", "what are my sessions doing", "summarize my…
Skill Claude CodeCodex
Agentic coarse-to-fine blueprint for generating large-scale, explorable, editable 3D open-world scenes from a single open-ended text prompt — derived from Tencent Hunyuan's WorldClaw (arXiv 2608.05248, Guo/Li/Li/Huang, 2026). Use whenever a project needs to generate a whole 3D world / open-world scene / large terrain…
Skill Claude Code
Convene the Council of Gamgee — seven analytical frameworks debate your question in parallel, then deliver a synthesized strategic recommendation.
Skill Claude Code
Cross-project session management hub for Claude Code. Use this skill when the user wants to manage conversations across different projects and directories. Trigger on /recall command or these specific phrases: "/recall", "/recall save", "/recall list", "/recall load", "/recall resume", "/recall rename", "/recall…
xiaxiagaogao/obsidian-cc-memory
Skill Claude CodeCodex
Persist and recall per-workspace long-term memory in an Obsidian vault, organized by workspace (one folder per git repo). Use this skill at the START of working in any project to load what was previously learned there, and WHENEVER you make an architecture/design/tooling decision, settle a convention, hit and resolve…
Skill Codex
Use the authenticated Cloister Host MCP bridge to discover and run Profile-allowed commands on the macOS host from a Cloister guest. Use when a task needs an available host-native toolchain, build command, or other executable exposed through cloisterhost, and when reporting Host Exec approvals, denials, output, or…
Skill Claude CodeCodex
Produce an audit-aware, agent-executable master plan (PLAN.mdx) for a software project before application code is written. One command runs discovery, forces hard-to-reverse decisions, and plans product, architecture, roadmap, stack, repo, build, deploy, observability, launch, security, code quality, style genome…
AttendantLion8/provider-fallback-plugin
Skill Claude CodeCodex
Skill for managing model provider priorities with authentication (OAuth/Subscription/API), usage limits, and automatic fallback across all major AI providers.
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: