Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 274,421 indexed, measured the same four ways as everything else here.
Read and change a database safely through Gatekeeper. You propose SQL, a human approves and runs it in Beekeeper Studio, and the rows come back to you; you never connect to the DB or run SQL yourself. Reads are the default; a write runs only if a human arms write mode. Use this whenever you need to read data, run a…
A Chinese-language workflow for producing research papers from topic selection through final checks. It covers research, outlining, writing, charts, citations, formatting, and review, with required checks between stages.
Present context-aware ChoicePilot buttons and progressively clarify ambiguous requests. Use when uncertainty about the objective, scope, constraints, authorization, risk, cost, privacy boundary, external effects, preservation requirements, or acceptance criteria could materially change the work. Ask one high-value…
MCP server "kafka" as configured in aswinayyolath/kafka-mcp-server. Runs /home/oem/Documents/kafka-mcp-server/kafka_mcp_server.py with python. Needs 2 environment variables to run.
Use when auditing a public website for AI visibility, agent accessibility, scrapability, or search-discovery readiness with the free MachineRead Essentials audit. Triggers: 'audit this URL for AI readiness', 'check if the site is agent-friendly', 'run a MachineRead audit', 'get a public-readiness score'. Calls POST…
Dispatch a task to Hermes over the async MCP bridge, optionally run the background watcher, then verify Hermes's result as an independent satellite verifier. Use when dispatching work to Hermes ("send this to Hermes"), running the Hermes work queue, or acting as the satellite verifier of a Hermes result. Reach for it…
MCP server "openlibrary-search" as configured in uysalserkan/openlibrary-mcp. Runs locally from the git+https://github.com/uysalserkan/openlibrary-mcp Python package.
Predict LinkedIn post performance before publishing. Get GO/WAIT/IMPROVE/NO verdict, estimated impressions, debate score, cringe detection, hook analysis, and timing optimization. Use when user mentions LinkedIn posts, content strategy, post drafts, or engagement optimization. Zero LLM calls — instant predictions via…
Execute and CLOSE an ExecPlan end-to-end in CueCrux — the execution half that execplan-synthesize/appraise/research (authoring half) hand off to. Runs the milestone loop: claim from the ranked board, announce focus for collision detection, worktree, implement, gate fact, PR, shepherd checks, merge, next milestone…
Database, collection, and user administration on a DocumentDB (MongoDB-compatible, PostgreSQL-backed) server via the documentdb-mcp MCP server — list/create/drop/rename databases and collections, and manage database users and their roles. Use when the agent must provision or tear down namespaces, enumerate the…
Helps an organization admin manage custom Forge workflows conversationally — both AUTHORING new workflows and DELETING existing org- or team-scoped overrides. Invoke this skill whenever the user asks to "create a workflow", "customize my SDLC", "build a new workflow", "set up a custom process", "author a workflow"…
Author pages on Magnolia author instances. Use when the user asks to create, update, publish, or read pages or components on a Magnolia CMS. Backed by the magnolia-author MCP server.
MCP server "pageindex-local-windows" as configured in jamesbubenik/pageindex-local-mcp. Runs C:\Users\user\pageindex-local-mcp\dist\index.js with node. Needs 9 environment variables to run.
MCP server "enclave" as configured in zd87pl/slm-vault. Runs advanced_vault.mcp_server with python. Needs 1 environment variable to run.
★not rated 2 14d agoA
tokens not measured
originalApache-2.0
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: