Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 268,544 indexed, measured the same four ways as everything else here.
A managed workflow for saving a new link to a local library and processing it into captured content, analysis, and reusable assets. It supports sources including Xiaohongshu, WeChat, Douyin, Bilibili, podcasts, music, articles, and general web pages.
Authors and extracts dbt MetricFlow meta context — structured YAML meta: blocks that encode business knowledge (thresholds, investigation paths, SLAs, relationships) alongside metric definitions so AI agents answer analytical questions accurately. Use when user asks about context cards, meta context blocks, dbt metric…
Search the user's local files with dowse, a Windows full-text search index (Chinese + English, PDF/txt/md/code). Use this when the user asks you to find something on their disk — a note, a doc, a config, "that file about X" — instead of grepping the whole filesystem.
MCP server for MikroTik RouterOS — 780+ tools over SSH for firewall, NAT, routing, DHCP, DNS, WireGuard, wireless, QoS and more. Runs locally from the @usex/mikrotik-mcp npm package.
★not rated 19▲
+3 yesterdayA
tokens not measured
originalMIT
Convert user-provided raster images into clean editable transparent-background SVG for icons, logos, UI glyphs, wordmarks, text marks, and other flat graphic assets. Use for PNG, JPG, WebP, or screenshot inputs, including non-transparent images whose background must be separated before vector reconstruction, combined…
Orchestrate a complete MiniMax H3 music-video production from song, lyrics, and visual references through MV direction, integer-second audio segmentation, storyboard generation, official H3 prompt writing, direct local minimax-H3-GEN submission, shared RunningHub queue autofill, resumable monitoring, automated result…
Defensive malware analysis and reverse-engineering workflow. Use for authorized lab analysis of suspicious Windows executables, DLLs, shellcode, packed samples, malicious documents, indicators of compromise, static and dynamic triage, IDA/Ghidra/debugger reasoning, anti-analysis handling, unpacking, host/network…
Generate seamless, tileable isometric terrain tiles (Hay Day / farm-game style) with ComfyUI on consumer GPUs (RTX 3060 12GB). Use this skill whenever the user wants to create ground tiles (grass, dirt, water, road, plowed field, sand, stone, snow), build a tilemap that connects without seams or gaps, fix tiles that…
Use when creating, updating, reorganizing, or reviewing aipermission documentation. Maintains project-root summary docs and the central docs tree under docs/, using GitHub Markdown relative links, small linked notes, local Docker/MCP/API-token/approval/vault/security consistency, and AI-friendly context boundaries.
Diagnose, configure, generate, simulate, and report on NI Multisim circuits through the Multisim MCP server. Use when the user asks to install or configure Multisim MCP, generate a Multisim schematic, run circuit simulation, analyze waveforms, or produce an electronic design report.
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines…
Use when installing Anthropic's Claude Science on a geo-blocked machine (e.g. China) or running it without a Claude account. Downloads the binary from the unblocked downloads.claude.ai CDN, sets up the claude-science-api-bridge local proxy to route requests to ANY OpenAI- or Anthropic-compatible API (Volcengine…
★not rated 19▲
+1 2mo agoA✓ AI review115 tokens
originalMIT
Reference and call the Salesforce Revenue Cloud (Agentforce Revenue Management) Pricing Business APIs - the Connect REST resources under /connect/core-pricing and /connect/procedure-plan-definitions. Use when the user wants to price a cart or line items, run a pricing procedure/expression set via API, hydrate or reuse…
/neat extend is a set of six MCP surgical tools for long-tail instrumentation — three diagnostic (read-only), three operative (file-scope-restricted, idempotent, reversible, observable). The user's MCP agent reasons; NEAT operates. NEAT holds no LLM key and never auto-applies. No standalone CLI variant. Discovery is…
A research skill for analysing Xiaohongshu, also called RedNote, a Chinese social platform, and turning a creator’s posts or account data into an evidence-based content profile.
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative…
Keep local AI agent environments clean, explainable, and recoverable. Use for repo artifact governance, workspace cache audits, WSL2/Docker hygiene, package and model cache mapping, C-drive growth diagnosis, and safe cleanup boundaries. Prevent throwaway Markdown files, audit local development environment sprawl, and…
Use when modifying Sourcelin UI Platform modules, shared components, routing, style boundaries, architecture documents, rules, or skills.
★not rated 18▲
+1 2mo agoA34 tokens
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: