219,033 that install into Codex. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.
Skill Codex
Use CatHub Nyaanes for session check-in and explicit end-of-work handoff. Use when beginning or resuming work, when the user asks for unread updates or current status, or when the user explicitly declares that the current work session is ending. Never infer work completion from silence, a finished job, a final answer…
Skill Claude CodeCodex
Search and manage durable personal or project knowledge through the Foundation MCP atom tools. Use when prior preferences, decisions, constraints, facts, people, procedures, or project context could materially improve the answer. Do not use for transient chatter or secrets.
Skill Claude CodeCodex
Use when you need to execute shell commands locally, in a sandbox, or on a remote SSH host.
Skill Claude CodeCodex
Use when the user wants to access, look up, create, edit, or manage credentials, passwords, secrets, login entries, secure notes, TOTP/2FA codes, or vault items in their Vaultwarden / Bitwarden vault via the vaultwarden-mcp MCP server. Trigger whenever the user mentions passwords, credentials, logins, secrets, vault…
Skill Claude CodeCodex
Use RoASr from Hermes — audit Meta (Facebook/Instagram), Google Ads and Yandex Direct ad accounts for wasted budget, list AI audit findings ranked by money at stake, read Direct search queries and ad moderation status, spy on competitor ads from the Meta Ad Library, and get Vision analysis of ad creatives (hooks…
Skill Claude CodeCodex
Audit an AI agent deployment against the CUSTODY containment framework and LASM threat model. Checks identity, input handling, supervision, traceability, operational controls, dependency management, and yield/teardown. Maps findings to NIST AI RMF, OWASP, CUSTODY pillars, and LASM layers.
Skill Claude CodeCodex
Automate SciREPL workbooks in a dedicated Chromium session with the scirepl MCP tools.
Skill Claude CodeCodex
Autonomously delegate bounded implementation, bug-fix, audit, refactor, test, research, web, or comparison work from Hermes to persistent worktree-isolated OMP sessions. Use when parallel coding or a separately steerable specialist session would materially help.
aspose-pdf-cloud/aspose-pdf-cloud-mcp
Skill Codex
Use Aspose.PDF Cloud CLI and its Aspose PDF Cloud MCP server for PDF/storage automation. Trigger when the user wants to configure or use the Aspose.PDF MCP server, connect Codex or Claude Code to Aspose PDF Cloud, list/upload/download Aspose storage files, merge or split PDFs, convert PDFs to PDF/A, extract PDF text…
Skill Claude CodeCodex
A skill that uses OCR, or optical character recognition, to read text from images and screenshots. It accepts local files, web addresses, data URIs, and base64 image data.
Skill Claude CodeCodex
Constraints and recipes for figma-meta-mcp figmaexec against the Figma Plugin API. Use when writing or reviewing figmaexec code.
Skill Claude CodeCodex
Search arXiv papers, download full text, follow citations, and run local semantic search.
Skill Claude CodeCodex
Generate images and videos through UGCmind App Tool Runtime, plus optional OpenAI-compatible and local ComfyUI image providers. Search prompt inspiration, enhance rough ideas, submit image/video jobs, and poll async project artifacts. Works in Claude Code, Cursor, Codex, Windsurf, OpenClaw, Hermes Agent, and any…
Skill Codex
Guide an incremental, evidence-aware discussion that turns an AI, product, model-strategy, competition, or implementation topic into durable personal cognition. Use when the user wants to discuss, learn, explore, compare, challenge, or deeply understand such a topic, including a recommended daily topic. Ask one…
Skill Claude CodeCodex
DataBench benchmark automation — config templates, result formats, platform details, and common workflows for TPC-DS benchmarking on EMR.
Skill Claude CodeCodex
Load this skill before creating, configuring, updating, deleting, or chatting with a Lyzr agent via the lyzr MCP server, or before starting/polling a long-running agent task. Covers: choosing a provider/model, generating and reusing sessionid across a conversation, when to use lyzrchat vs lyzrstreamchat vs…
Skill Claude CodeCodex
Ask your human for input that prose cannot capture — tuning values, colours, a choice between options, approval of a diff — by opening a real interactive UI in their browser. Use when you would otherwise guess at a subjective value, describe a visual result in words, or ask a yes/no question that would be clearer with…
Skill Claude CodeCodex
Send notes, summaries, drafts and documents to the user's reMarkable tablet using the rmprint MCP tools. Use whenever the user asks to put something on their reMarkable, print something, send something to read or annotate, or says things like "put this on my tablet", "send that to my reMarkable", "I want to read this…
Skill Claude CodeCodex
The grammar of cuts — which cut to use, when to cut, and how to pace an ad. Read before authoring any multi-shot film.
fredericbarthelet/demo-skills-over-mcp
Skill Claude CodeCodex
A description of what this skill does and when to use it.
Skill Claude CodeCodex
Use when the user wants to connect an Agent, manage its persistent Character, discover other Characters, create or participate in Worlds, manage relationships, or exchange messages.
manteclaw/base-l2-agent-kit-mcp
Skill Claude CodeCodex
MCP server providing Base L2 DeFi tools for AI agents.
Skill Claude CodeCodex
Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; webfetch fails; the site has anti-bot protections; write Python code to…
Skill Claude CodeCodex
Safe Git branch workflow — feature branches, rebase vs merge vs squash, interactive rebase, force-with-lease, reflog recovery, destructive-command guardrails.
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: