218,997 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 Claude CodeCodex
Answers "why does this code exist" for colinhacks/zod by tracing file:line -> git blame -> commit -> PR -> linked issue via the provenance-mcp MCP tools (traceline, askwhy, searchhistory), then renders a cited WHY/EVIDENCE/STILL LIVE?/VERDICT/CONFIDENCE verdict. Never authors a reason without a citation -- marks NOT…
alizaimovic/sql-database-bridge
Skill Claude CodeCodex
Use the SQL Database Bridge MCP tools to inspect schemas and run safe SQL queries against configured databases.
Skill Claude CodeCodex
Buy and audit World Cup betting edges from LineLock over Injective x402. Use when the user wants the next knockout pick (model probability vs market odds + a conviction staking ladder), wants to pay per-call in USDC without an API key, or wants to audit a tipster's settled record by closing-line value (CLV). Handles…
Skill Codex
Plan, time-box, schedule, inspect, and control user-owned tasks in Timex, the local project-based timer app exposed over MCP. Use when a user wants a daily plan, focused work blocks, calendar starts, task durations, or Timex project/timer operations. Prefer semantic Timex tools; use Native UI automation only for…
testman2025/weekly-review-skill
Skill Claude CodeCodex
A skill for helping an AI agent review its weekly work. It covers usage and time summaries, prompt improvement, causes of efficient or inefficient work, trends, open-session cleanup, and scheduled weekly reports.
Skill Claude CodeCodex
A skill that converts structured knowledge lists and proposed capabilities into importable TFOnto files. TFOnto is a file format for describing a robot's concepts, data fields, relationships, and capabilities.
cornerblue/aibtc-mcp-server-orphan
Skill Claude CodeCodex
Bitcoin L1 wallet for agents - check balances, send BTC, manage UTXOs. Extends to Stacks L2 (STX, DeFi) and Pillar smart wallets (sBTC yield).
Skill Claude CodeCodex
Manage TiDB Cloud Serverless clusters, branches, and execute SQL queries via MCP.
Skill Claude CodeCodex
Drive an antidetect browser from your AI agent. Oculr gives the agent real, isolated Chromium browser profiles with engine-level fingerprinting and per-profile proxies, controlled over MCP and raw Chrome DevTools Protocol. Use when an agent needs to browse or act inside real logged-in sessions, manage many separate…
Skill Claude CodeCodex
Generate professional AI images and videos using Dreamshot's API.
Skill Claude CodeCodex
Survey an existing repository into an empty Kiln project over the kiln MCP server. Use when asked to "survey this repo into Kiln", "bootstrap Kiln from this codebase", or extract requirements/blueprints from existing code — whenever the mcpkilnproposefeature tool is available and the target is a fresh Kiln project.…
Skill Claude CodeCodex
A tool that turns video, audio, or meeting recordings into written summaries with sections for the overview, chapters, key points, and action items.
Skill Claude CodeCodex
Collaborate in Huddora using plugin seat identity, WebSocket delivery, message search, files, task handoff context, and room-scoped personas.
Skill Claude CodeCodex
Exhaustive adversarial documentation verification. Use when checking README accuracy, API documentation completeness, or any docs where missing features could mislead users. Enumerates ALL features from source, compares to docs, proves coverage gaps with formal logic.
Skill Claude CodeCodex
Esta skill transforma al agente en un Ingeniero de QA especializado en Yari Medic. Su misión es auditar código contra los documentos de grounding en data/projectcontext/.
Skill Codex
Add or extend laboratory instrument support in the lab-equipment-mcp repository. Use when an agent or developer needs to onboard a new oscilloscope, power supply, multimeter, signal generator, electronic load, or another test instrument; add another connection method to an existing model; work from a downloaded…
Skill Claude CodeCodex
Provides AI agents with autonomous API key acquisition and management via MCP.
Skill Claude CodeCodex
Use when researching Norwegian companies via Brønnøysundregistrene — company lookup, industry/municipality search, roles, or annual accounts. Read before the first query; the register answers wrong questions with plausible numbers instead of errors.
Skill Codex
Access and manage a personal @163.com mailbox through the local 163 Mail MCP server or its bundled CLI. Use when the user asks Codex to check connection status, list folders, search or read 163 mail, summarize messages, draft or send mail, move messages, move them to Trash, download selected attachments, or mark them…
Skill Claude CodeCodex
Use when working with SentientUI — an adaptive UI personalization platform — from an AI agent. Covers connecting to the SentientUI MCP server, reading experiment data (variant performance, personas, goal funnels, AI insights, guardrail events), creating and pausing variants, and integrating the @sentientui/react SDK…
Skill Claude CodeCodex
Query the codebase connection graph (HTTP calls, DB/queue access, imports) across app-web + app-services. Use when asked who calls a route, what touches a table/stream, how two parts of the code connect, or to (re)build the graph.
Skill Claude CodeCodex
Discover and extract sitemaps from any website using SitemapKit. Use this skill whenever the user wants to find pages on a website, get a list of URLs from a domain, audit a site's structure, crawl a sitemap, check what pages exist on a site, or do anything involving sitemaps or site URL discovery — even if they don't…
Skill Codex
Create and maintain effective durable memories with the agent-memory MCP tools. Use when the remember, review, revise, and forget tools are available, when starting a task that may benefit from prior workspace context, or when confirmed preferences, corrections, decisions, constraints, pitfalls, and reusable…
songofhawk/playwright-mcp-tabbed
Skill Claude CodeCodex
Parent Agent uses playwright-tabbed to allocate browser tabs and partition tasks, then spawns child agents in parallel — each operating on its assigned tabid — for browser acceptance testing or automation, with a final aggregated summary. Suitable for multi-page validation, parallel module checks, and…