Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 269,407 indexed, measured the same four ways as everything else here.
QVeris provides professional data and tool access for AI. Use standardized capabilities/query for qverisfinance. CAP workflows, or discover/call for specialized services such as real-time data, historical sequences, structured reports, web extraction, PDF workflows, media generation, OCR, TTS, translation, and more.…
Build production-quality architecture diagrams in the "centvra/deepstream" house style using the prettygraph helper — title + subtitle, semantically-COLORED rounded node boxes (icon on the left + bold label), tinted nested clusters, and gray concern-labeled edges. Consult before writing a pretty-style diagram.
Build and deploy a small Slack Events API adapter for an Amazon Bedrock AgentCore Harness, with incremental responses delivered through Slack chat.startStream, chat.appendStream, and chat.stopStream. Use when a customer wants to create or reuse an AgentCore Harness, expose it as a Slack bot, stream InvokeHarness…
Build and maintain a project-serving knowledge base inside the current project's .project-knowledge/ directory. Use when Codex should initialize a project knowledge base, inspect current project knowledge status, rebuild the project knowledge graph, or crystallize stable knowledge from the current task into…
Maintain a personal LLM-generated wiki/knowledge base in Obsidian. Use this skill whenever the user wants to: ingest a new source (AI tool, GitHub repo, article, social post, project doc) into their wiki, query or search their wiki, lint/health-check the wiki, create or update wiki pages, manage the wiki index or log…
Compose UI screens from existing components. Proposes ASCII wireframe layouts with real component mapping and coverage %, then specs the chosen layout. 6 actions: init, spec, spec-review, craft, ship, review. Core guarantee: zero component reinvented. Auto-activates on: "design-screen", "design-screen spec"…
Convene a symmetric committee meeting between the profiles declared in /.veche/config.json on a single question, then report each participant's stance and the consensus. Use when the user wants a second opinion, wants to stress-test a decision against another model, or asks to "hold a meeting" / "convene a committee"…
A lightweight, multi-guild Discord MCP server with 95+ tools. Runs locally from the @pasympa/discord-mcp npm package. Needs 1 environment variable to run.
★not rated 21 todayA
tokens not measured
originalMIT
Use this skill when the user needs to connect to Odoo via XML-RPC, sync Odoo data to external systems (Google Sheets, databases, APIs), read or write Odoo models (stock.picking, sale.order, purchase.order, product.product, etc.), set up cron-based sync jobs, or deploy Odoo integrations on Railway/Render/Fly.io. Also…
Organize starred GitHub repos into stable, clear lists: detect new stars, download READMEs into a local corpus, classify each repo against the taxonomy, and sync the approved mapping back to GitHub via gh. Use this when a user wants their starred repos sorted into lists, a recent batch of new stars filed…
Conduct the Knack 6-phase interview with a user to author a new skill. Load this skill when the user wants to teach you a recurring task they do and have it become a reusable Knack skill (e.g. "use knack to capture how I triage support tickets").
Use this when the user wants to generate, normalize, verify, deduplicate, or export training datasets for Codex, Antigravity, or Claude Code from topics, URLs, reference material, web research, or existing JSONL/CSV files. Supports SFT and DPO workflows, custom export schemas, and deterministic local pipeline scripts.
Profile a research lab (a professor, or a school/department) over the last N years by collecting every paper from OpenAlex, structuring it into a temporal knowledge graph (ontology) — Papers, Researchers, Topics, Themes, Methods, Venues, Citations — and synthesizing a grounded report of the lab's year-by-year output…
Use for persistent, one-question-at-a-time consultation on an ambiguous repository change: inspect supplied territory, save decisions, produce an approved plan, run a scored bounded adversarial review with explicit targets and automatic-review limits, resolve or accept human-owned risks, and hand off to a fresh…
MCP server that validates AI-generated Android code against official SDK documentation. Runs locally from the androjack-mcp npm package.
★not rated 21 10d agoA
tokens not measured
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: