250,762 that install into Claude Code. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.
Skill Claude CodeCodex
Use when analyzing, auditing, reviewing or diagnosing a sales call transcript — find where the deal was lost, closer mistakes, objections missed, and a recovery line. Returns an evidence-backed QC 4.1 Light report with exact quotes, breakpoint minute, corrections, and a speakable recovery script. Works for high-ticket…
Skill Claude Code
Use this skill when the user runs open source DataHub (self-hosted, not Acryl Cloud) and wants to write quality signals, not just read them: raise or resolve incidents on a dataset, or register external assertions with pass/fail results so they appear in the Validations tab. Triggers on: "raise incident on OSS"…
Skill Claude CodeCodex
A sandbox step that applies an approved patch in an isolated environment and runs build and test checks.
Skill Claude CodeCodex
BIM Agent — Query and validate Building Information Models (IFC) through natural language.
Skill Claude Code
Get the most interesting recent posts from the user's Telegram channels.
Skill Claude CodeCodex
Read the screen and drive the desktop: accessibility tree, window targeting, screenshots, clicking, and typing. Use when a task needs a graphical application that has no command-line equivalent, or when the user asks to click, type into, or read something on screen.
Skill Claude CodeCodex
Review a cash-basis financial statement through the docverify MCP server. Use when asked to extract, check, tie out, foot, crossfoot or reconcile an Ohio black-box test of State combined statement, or when a docverify tool returns verified=false and the refusal has to be explained.
Skill Claude CodeCodex
Gráficas avanzadas OSS (gratis, sin API keys) — TimeSeries uPlot + BoxPlot/Parallel ECharts como widgets JsonLive. No reemplaza Chart nativo.
Skill Claude CodeCodex
Use RelayBridge to delegate work to other AI CLIs (Claude, Codex, Cursor, Copilot, Gemini, Grok, Perplexity, local Ollama) on subscription seats the user already pays for. Use when a task should be handed to a different model, when work should be matched to a cheap/local vs frontier model, when running many…
Skill Claude CodeCodex
Use Repo Brain to locate current repository code, consult evidence-backed memory, log reads, detect stale analyses, and refresh memory after changes.
Skill Claude CodeCodex
A tool for finding and comparing possible places to live in Japan using land prices, walking distance to stations, and public-transport travel times. It displays the results on an interactive map built with PMTiles and MapLibre.
Skill Claude CodeCodex
A skill for starting and controlling a mind map through a browser, a local Node service, and MCP. It is designed for users who may not know how to install software and does not require a desktop shell such as Tauri or Rust.
Skill Claude CodeCodex
Extract mountain bus tour, alpine trekking, and general tour data from Maitabi (bus.maitabi.jp & www.maitabi.jp) using only raw HTTP requests (curl or any HTTP client). No MCP server, no CLI, no Python package required. Supports filter modeling, REST endpoint querying, and standardized JSON output.
Atlas-X-AI/shade-browser-security
Skill Claude CodeCodex
Use when the account owner needs to move their own authenticated browser session into a Shade Browser MCP slot.
Skill Claude CodeCodex
A skill for researching short videos on Douyin and TikTok, including speech-to-text transcription and analysis of viral opening hooks. It ranks content by saves compared with likes, where saves indicate that viewers want to return to it.
Skill Claude CodeCodex
Enables the agent to perform safe, authenticated web checkouts using AgentGate virtual cards, MCP tool discovery, and OAuth 2.1 non-human identity tokens. Use this skill whenever the agent needs to: (1) navigate a web application programmatically, (2) authenticate without raw credentials, or (3) make a purchase using…
Skill Claude CodeCodex
Produce a prioritised data-quality briefing for a dbt project — what is failing, why, what it affects, and what to fix first. Use when the user asks for a data quality brief, asks "what's broken in dbt", or wants a morning check on warehouse health.
mbarbarydesign/Wellx-design-mcp
Skill Claude CodeCodex
Wellx Unified Design System — MANDATORY before building or restyling any UI in a Wellx tool. Thin pointer: core rules inline, full spec via the wellx-design-system MCP server.
Skill Claude CodeCodex
Turn a list of merged PRs into user-facing release notes grouped by theme.
Skill Claude CodeCodex
Answer questions about this project, its history, past conversations, and prior team decisions from source-backed evidence with verified citations. Use whenever the user asks what something is, why it was decided, what happened before, or what the team already knows.
mdkulkarni2005/osmos-marketing-mcp
Skill Claude CodeCodex
Generic, service-agnostic API test scenario design skill. Consumes an API contract from a Documentation MCP (or any authoritative contract source) and produces traceable, prioritized, coverage-reported test scenarios. Works for any REST/HTTP endpoint of any service/version — no hardcoded API knowledge.
Skill Claude CodeCodex
Triage a broken or degraded data asset in DataHub. Traces the downstream blast radius across all lineage hops, resolves owners, ranks by criticality, writes a structured incident report, and records the incident back into the catalog (tag + runbook document + native incident). Use when a table, view, dashboard, or…
HOTAgithub/hailab-japan-company-data
Skill Claude CodeCodex
Search Japanese company credit, basic info, financials, subsidies, and procurement. Use when an AI agent needs to research a Japanese company.
Skill Claude CodeCodex
Use before answering a complex architecture, security, research, release, incident, or multi-constraint question. Selects a finite set of review perspectives, measures contradictions between the resulting claims with local offline encoders, and returns rules for the final answer. Use when a wrong answer would be…
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: