2,098 tagged agent-skills, measured the same way as everything else here.
Browse within: claude-code-plugin 256agentic-ai 110agents 106claude-code-marketplace 97skills 93claude-code-skills 92cli 85ai-tools 69agentskills 68ai-coding 65LLM 63claude-code-plugins 57antigravity 54claude-skill 51
Plugin Claude Code
Bundles 6 skills, 1 agent · 1,280 tokens together
A growing collection of portable agent skills: ai-os-init (scaffold an AI Operating System project structure), sqlalchemy-patterns (SQLAlchemy 2.0+ async/PostgreSQL reference), system-flow-mapper (document any codebase's architecture and request flow), and shop-scout (compare prices, discounts, coupons & seller safety.
bethanychamberlain/claude-skills-librechat
Plugin Claude Code
Bundles 3 skills · 144 tokens together
Essential LibreChat admin skills: YAML config, agents, troubleshooting.
Plugin Claude Code
Bundles 5 skills, 1 hook · 219 tokens together
A self-observation tool that examines your conversations with an AI language model to find recurring personal patterns, including the difference between your public and underlying preferences.
Plugin Claude Code
Bundles 1 skill · 114 tokens together
Decision research for Claude Code and Codex - cited findings where every claim states how well it is supported. Judges a source by whether it suits the claim it backs rather than by its domain, counts corroboration only across genuinely independent sources reached from different search angles, and says so plainly when.
Plugin Claude Code
Bundles 19 skills, 6 agents, 2 hooks · 3,169 tokens together
Push Claude Code beyond stock. Skills, agents, Codex collab — opinionated and personal.
Plugin Claude Code
Bundles 4 skills, 5 hooks · 334 tokens together
Persist knowledge and plans across Claude Code sessions. Provides /record-knowledge, /plan-task, /review-knowledge, and /recall-knowledge skills.
Zihao-Wu06/claude-code-orchestrate
Plugin Claude Code
Bundles 1 skill, 1 command, 3 agents · 286 tokens together
Multi-model orchestration for Claude Code: the session model leads as tech-lead orchestrator, routing work across model-pinned executors (deep-reasoner/Opus, fast-worker/Sonnet, scout/Haiku) and a cross-vendor Codex peer — with a first-match routing table, delegation contracts, budget modes, an escalation ladder, and…
Plugin Claude Code
Bundles 1 skill · 144 tokens together
A plugin that turns academic papers into explanations for people without a research background.
Plugin Claude Code
Bundles 1 skill · 68 tokens together
Create data-rich HTML slide decks with charts, technical diagrams, code, reliable viewport fitting, and browser-native delivery.
volkthienpreecha/modesofthinking
Plugin Claude Code
Bundles 1 skill, 10 commands · 175 tokens together
Context-efficient multi-perspective reasoning with bounded agent councils.
Plugin Claude Code
Bundles 3 skills, 6 commands · 145 tokens together
Universal Knowledge Graph — LLM-maintained personal wiki. Ingest sources, query and synthesize knowledge, maintain cross-referenced wiki pages.
Plugin Claude Code
Bundles 6 skills, 3 hooks · 317 tokens together
A reviewable Markdown second brain for Codex and Claude Code.
TopEase-AI/topease-customs-mcp-skill
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 90 tokens together
A customs-data connection for Claude Code that turns natural-language trade questions into calls to a customs-data service. The description is written in Chinese and does not provide more detail about the available data.
Plugin Claude Code
Bundles 1 skill · 132 tokens together
Answers a user-interface question with 3-5 numbered, operable HTML variants built from the application's real tokens and CSS, opens them in the browser and takes your reply back into the session.
Plugin Claude Code
Bundles 1 skill · 102 tokens together
Check whether a repository agrees with itself, for Claude Code and Codex - broken links, dangling heading anchors, orphaned files, duplicate and near-duplicate content, and translations that have fallen behind. Deterministic: no model calls, no network, no dependencies, and it never modifies the repository it scans.…
Plugin Claude Code
Bundles 181 skills, 3 commands · 13,385 tokens together
Apideck Unified API development plugin for Claude.
Plugin Claude Code
Bundles 1 skill · 178 tokens together
Cala pre-processes the world's public information and serves it as structured data for AI agents. Query any real-world entity — companies, people, investors, founders, executives, funding rounds, acquisitions, industries, laws, regulations, countries, products, events, awards, financial metrics — and get typed…
zhouxifox6249-byte/codex-obsidian-loop
Plugin Claude Code
Bundles 1 skill · 107 tokens together
Task-driven Codex + Obsidian loop for agent memory, source boundaries, durable result writeback, and lint.
arifulislamat/bd-income-tax-skills
Plugin Claude Code
Bundles 1 skill · 149 tokens together
Compute and explain Bangladesh individual income tax (Income Tax Act 2023 + Finance Act): slabs, thresholds, salary exemption, Section 78 investment rebate, minimum tax, net-wealth surcharge, filing/PSR rules, Tax Day, and penalties. Deterministic calculator, no network calls.
Plugin Claude Code
Bundles 3 skills · 288 tokens together
Universal E2E and manual acceptance testing for any repo: test-init generates project test plans (TESTSE2E.md, TESTSMANUAL.md), test-e2e executes them autonomously, test-manual conducts them with you at the controls. Every run writes a timestamped protocol file.
Plugin Claude Code
Bundles 1 skill · 207 tokens together
Check domain availability across many TLDs at once, with registration and renewal price, and the registry's own eligibility rules. Never reports an unreachable or rate-limited registry as available.
Plugin Claude Code
Bundles 8 skills, 8 commands, 2 agents · 1,040 tokens together
The specwright ladder for Claude Code and Codex: init, propose, plan, implement, review, archive, ship, and delivery.
Plugin Claude Code
Bundles 4 skills · 170 tokens together
Levers for AI coding agents — multiply the agent's force, divide the human's effort.
Plugin Claude Code
Bundles 4 skills, 2 commands, 2 agents, 1 MCP server · 806 tokens together
Paper-grounded ML research and open-problem attack for Claude Code. Crawls arXiv and citation graphs, reads whole papers in parallel subagents, mechanically verifies every quote, archives a model's real code locally and grounds later sessions in it, and runs falsifiable attacks on hard unsolved problems.
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: