All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 435,642 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.
MCP server Claude CodeCodexCursor +2
Nova3D MCP server — structured, part-aware 3D generation for AI agents. Runs locally from the nova3d-mcp Python package. Needs 2 environment variables to run.
Skill Claude CodeCodex
Use this to build and flash custom firmware onto a Solo 2 Hacker key — including checking the lock/seal state (Secure vs Hacker, which is the PFR seal field, not secure boot), matching the build to the key's storage mode, and validating the equivalent build on an EVK first. Use it WHENEVER you are about to write…
Skill Codex
Install, open, download, or deploy GEO Citation Lab from its GitHub repository. Use when a user asks to install the lightweight offline viewer, open the research reports locally, download the full GEO citation dataset, prepare the analysis environment, or publish the viewer to GitHub Pages.
MCP server Claude CodeCodexCursor +2
MCP server "just-prompt" as configured in disler/just-prompt. Launched with uv --directory . run just-prompt --default-models openai:gpt-5:high,openai:gpt-5.
Skill Claude Code
Provides guidance for valid skill usage.
Plugin Claude Code ✓ vendor
Bundles 1 skill · 112 tokens together
Deploying and managing apps on Laravel Cloud.
shannhk/hermes-agent-control-room
Skill Claude CodeCodex
Use when creating a fresh Hetzner Cloud VPS with an SSH alias, local project folder, provisioning script, destroy script, and optional handoff into setup-control-room.
Skill Claude CodeCodex
Use the ax CLI instead of curl + throwaway parsing scripts whenever you fetch a URL, explore an unknown web page, or extract structured data from HTML. Trigger whenever you are about to write an inline script (python3 heredoc, node -e, regex over HTML) or a bare curl for one-off web fetching, scraping, or page…
Skill Claude CodeCodex
Orchestrator reference for pi-messenger Crew planning, task management, configuration, and agent coordination. Crew workers already have the pimessenger actions they need in crew-worker.md.
Skill Claude CodeCodex needs its repo
Authors deterministic, LLM rubric, and human graders for skillgrade evaluations. Use when creating scoring scripts, writing evaluation rubrics, setting up human review workflows, or combining multiple graders with weighted scoring. Don't use for setting up eval pipelines, configuring eval.yaml defaults, or general…
Skill Claude CodeCodex
Literature-backed English technical-prose writing rules. Use when writing or editing prose in .md, .tex, .rst, or .txt files, especially research papers, proposals, documentation, and release notes.
Command Claude Code
You are saving what you learned this session into the megamemory knowledge graph. This is YOUR memory — record anything valuable for future sessions: what you understood about the project, what you built, decisions that were made, patterns you noticed, or intent the user shared.
UKGovernmentBEIS/inspect_evals
Skill Claude Code
Review a single evaluation's validity — whether its claims hold up, whether its name is accurate, whether samples can be both succeeded and failed at, and whether scoring measures ground truth. Use when user asks to check validity of an eval, or as part of the Master Checklist workflow. Do NOT use for code quality or…
Skill Claude CodeCodex
Open a Markdown plan or document for the human to review and annotate in a Herdr pane; their feedback arrives as your next message. Use when you have written a plan, spec, or design document that needs human review before you act on it.
Skill Claude CodeCodex
A Chinese-language assistant for writing articles for WeChat Official Accounts, China's platform for publishing articles to subscribers. It can write the article, prepare image prompts, and produce inline HTML for the layout.
Skill Claude CodeCodex
Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and…
Skill Claude CodeCodex
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
marckohlbrugge/37signals-skills
Skill Claude Code
Review Ruby/Rails code like DHH would - direct, opinionated, allergic to over-engineering. Use when the user runs /dhh or asks for a DHH-style review of a diff, file, or recent changes.
Skill Claude CodeCodex
A job-search assistant for researching roles, adapting résumés, preparing for interview rounds, and creating a DOCX résumé. It covers internships, graduate roles, career changes, and many business and technical positions.
Skill Claude CodeCodex
Use when building Vue 3 UI with @vuetify/v0, or before hand-rolling behavior it already ships, such as a button, dialog, popover, setTimeout timer, selection, form, registry, virtual list, focus handling, snackbar, theme, RTL, breakpoints, an SSR window check, or a WAI-ARIA compound, along with the rest of its…
Skill Codex
A tool for rewriting Simplified Chinese so it sounds more natural while keeping the original facts, meaning, evidence strength, tone, and authorial voice.
OpenClaudia/openclaudia-skills
Skill Claude Code
Send messages and rich content to Slack channels via webhooks or Bot API. Use Block Kit for formatted announcements, marketing reports, and community updates. Trigger phrases: "post to slack", "slack message", "slack webhook", "slack notification", "slack announcement", "send to slack", "slack marketing", "slack…
Skill Claude Code
Generate a context-aware HTML document and show it in an agterm overlay, end to end. With no arguments it works out the subject from the session - the issue, PR, branch, plan, diff or topic being discussed - and asks with the likely variants when that is unclear; with arguments it takes them as the brief, including…
Plugin Claude Code
Bundles 2 commands, 1 hook · 21 tokens together
Automated code review loop: Claude implements, Codex reviews independently, Claude addresses feedback.
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: