Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,428 indexed, measured the same four ways as everything else here.
Reconstruct an authorized reference website from a supplied URL with high visual, responsive, interaction, asset, and observable behavior fidelity. Use only when the user explicitly invokes $fetch or $codex-chef-workflows:fetch for site reconstruction; do not use for JavaScript Fetch API help, generic scraping or…
Run, inspect, and manage entries in the user's skit library — their personal hub, manager, and launcher for scripts in many languages (Python, shell, JS/TS, and more), executables, command templates, and AI-agent prompts, with typed parameter forms, saved presets, and per-entry launch policy. Use when the user asks to…
Evaluate whether AdCP (Ad Context Protocol, agenticadvertising.org) — or a concrete AdCP implementation such as a seller agent, buyer agent, or orchestrator — is safe, interoperable, operationally viable, and ready for pilot or production use. Combines a weighted decision scorecard, hard safety gates that override any…
Operate Mint Club V2 with the mc CLI: inspect tokens and balances, mint or burn ERC-20/1155 bonding-curve tokens, route exact-input ZapV2 trades, transfer assets, and create ERC-20 curves across supported chains. Use for Mint Club terminal workflows that need protocol-native transactions or local Uniswap route…
Review, diagnose, and refine existing agent skills as living systems. Use when Codex needs to explain why an existing skill misfires, assess its architecture or evolution, apply an explicitly requested minimal improvement, recheck prior findings, or audit drift across source, published, and installed copies.
Generate Go CLIs from OpenAPI 3.x specs with climate, inspect generated CLIs, and emit Markdown skill prompts so those CLIs can be attached to agent workflows.
Operate websites through the local Camoufox browser runtime with persistent sessions, inspect/query/act flows, event inspection, authenticated fetches, and download handling.
Current attested Codex, Claude Code, and Agent Skills extension contracts for skilltap. Use when designing, implementing, reviewing, or documenting harness adapters; plugin or marketplace manifests; native plugin lifecycle; skill directories or SKILL.md frontmatter; AGENTS.md/CLAUDE.md bridges; configuration scopes…
Mindful-coding OS for any LLM coding agent — faster, quality, scalable output. One invoke configures seven layers (0–6): (0) BRIEF — optional one-page PRD.md (skipped if design.MD/README already covers it, or on request), plus git init, gitignore, and a day-one security baseline; (1) HARNESSING — Handoff.MD…
Match tech products and consulting services to live government tenders, grants, and RFPs. Runs locally from the @govrider/mcp-server npm package. Needs 1 environment variable to run.
★not rated 6 6mo agoA
tokens not measured
originalMITarchived
Search, read and update Aha.io ideas, features, epics, releases, goals and comments. Runs locally from the @cedricziel/aha-mcp npm package. Needs 2 environment variables to run.
★not rated 6 yesterdayA
tokens not measured
originalMIT
MCP server for Florentine.ai - Natural language to MongoDB aggregations. Runs locally from the @florentine-ai/mcp npm package. Needs 6 environment variables to run.
★not rated 6 6mo agoA
tokens not measured
originalMIT
MCP server "dorar-hadith-mcp" as configured in ibnsaleem29/dorar-hadith-mcp. Launched with https://github.com/ibnsaleem29/dorar-hadith-mcp/releases/download/v3.0/dorar-had.
★not rated 6 1mo agoA
tokens not measured
originalMIT
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields,...
Persistent memory for AI agents. Store decisions, preferences, and context that survive across sessions. Build knowledge graphs that compound over time. Hybrid search (BM25 + vector + graph) recalls what matters when you need it.
Pattern taxonomy, agent role combinations, model routing, unit-of-work sizing, review-findings settling, and resilience discipline for Claude Code dynamic workflows. ALWAYS load this skill before authoring or running any Workflow tool script, and ALWAYS load it when the user mentions "workflow" or "ultracode" in any…
An MCP server that helps users publish their MCP servers to the registry. Runs locally from the publish-mcp-server Python package.
★not rated 6 1y agoA
tokens not measured
originalMIT
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: