All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 437,253 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.
Plugin Claude Code
Bundles 20 skills, 4 commands · 1,887 tokens together
HomeKit smart home control via MCP - control lights, locks, thermostats, and scenes.
Plugin Claude Code
Bundles 1 skill · 73 tokens together
nteract notebooks (nightly channel) for Claude Code.
Skill Claude CodeCodex
Search local coding-agent session history and identify safe resume commands. Use when the user asks to find, inspect, continue, or recover previous work from Claude Code, Codex, Pi, or another agent indexed by fast-resume.
bjgreenberg/senior-engineering-partner
Plugin Claude Code
Bundles 1 skill · 244 tokens together
A strict code reviewer, pair programmer, debugger, and mentor for Python, Bash, Google Apps Script, and JavaScript — a security-first, phase-aware engineering discipline with an enforced spec → plan → TDD → verify workflow.
SyntaxSmith/nature-writing-skill
Skill Claude CodeCodex
A Chinese-language academic writing skill for AI and machine-learning researchers preparing papers for Nature journals. It focuses on story, structure, and writing quality for venues such as Nature Machine Intelligence and Nature Communications.
Skill Claude CodeCodex
Decomposition playbook + specialist-roster conventions + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically…
Plugin Claude Code
Bundles 36 skills, 16 commands, 8 agents · 2,371 tokens together
Incremental task management for coding agents: grill the problem, plan test-driven missions, bracket every implementation with critics.
Plugin Claude Code
Astro language server for .astro files.
Skill Codex
Publish local HTML, Markdown, or built static web projects with Pagecast as shareable public URLs. Use whenever Codex creates or finishes an .html, .htm, .md, .markdown, or static build output that a person could share (a report, plan, doc, dashboard, or analysis) — proactively offer to publish it without being asked…
Skill Claude CodeCodex
Review planning documents by reading the plan docs and doing a thorough codebase walkthrough, then writing detailed review docs. Use when the user asks to review, audit, critique, or validate a plan, design doc, or spec in the permit0 repository.
Skill Claude CodeCodex
Use this skill when the user wants to boot and interact with iOS or Android devices/simulators — inspect the screen, execute actions, generate or edit test cases, or run UI tests via the noqa platform.
Plugin Claude Code
Bundles 5 hooks, 2 MCP servers
Model Context Protocol (MCP) server for versioned prompt templates, multi-step workflow chains, and quality gates. Symbolic syntax: >>prompt --> >>chain @framework :: 'gate'.
agent37-platform/agent37-skills-collection
Plugin Claude Code
Bundles 1 skill · 129 tokens together
Generate a compact 'prompt request' one-pager that summarizes the current session for a pull request: one consolidated User block folding every ask and decision, plus one Assistant block summarizing what was built.
Skill Codex
Use when the user wants a Chen-model ER diagram from SQL CREATE TABLE statements or DBML, wants to rearrange or clean up an existing sql2er state, wants a skeleton-only overview with attributes hidden at generate time, or needs drawio/svg/png/json/html exports with final visual review.
FrankS-IntelLab/agentic-kaggle-skill
Skill Codex
Kaggle-first end-to-end competition workflow for scored submissions. Use when Codex must run Kaggle or competitive ML workflows through scored submission, including code competitions, validation, metrics, policy-safe public notebook/discussion intel, tabular/text/image modeling, tuning, ensembling/stacking, proactive…
Skill Claude CodeCodex
Read, search, and draft email in the connected mailbox (Gmail or Microsoft 365). Use when the user asks about their inbox, wants a message found or summarized, or wants a reply drafted. Sending is gated by a separate, explicitly granted permission — never assume you can send, and never claim a message was sent unless…
Skill Claude CodeCodex
Skill "closer" from gtm-skills/gtm, covering closer, your personality, the golden rule, your resources and methodologies.
Plugin Claude Code
Bundles 1 skill · 68 tokens together
Surgical, non-interactive git hunk control for AI agents.
Skill Claude CodeCodex needs its repo
Deploy an Agent Kernel project to AWS, Azure, or GCP using Terraform modules, or to any Kubernetes cluster (on-prem, baremetal, EKS) using the official Helm chart. Supports serverless and containerized modes for all three clouds. AWS supports execution modes (restsync, restasync, async) with a reply messagetype…
Plugin Claude Code
Bundles 1 skill · 61 tokens together
Guides users through a structured symptom interview, literature search, and evidence evaluation to prepare for medical appointments.
rottenpen/fengge-wangmingtianya-perspective
Skill Claude CodeCodex
A fictional speaking style based on a wandering, realistic, darkly humorous character called 峰哥亡命天涯. It gives direct, conversational commentary on relationship, work, and life problems.
mujingquan835/dashiai-ppt-skill
Skill Codex
A tool for creating new slide decks or editing existing PowerPoint presentations while keeping unrelated content unchanged. It produces offline HTML slides that can be edited in a browser and exported to PPTX or PDF.
Skill Codex
Build, inspect, run, and debug OmniSim robotics worlds through the first-party MCP tools. Use for requests involving OmniSim scenes, robots, cameras, contacts, physics checks, or screenshots; do not use for unrelated simulators.
Plugin Claude Code
Bundles 45 skills, 1 MCP server · 1,630 tokens together
45 UX and design-system skills for AI agents: brand foundation, design tokens, layout, components, UX polish and an accessibility gate, plus live token extraction from any site through dembrandt.
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: