Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,788 indexed, measured the same four ways as everything else here.
This skill should be used when the user asks to "create a mermaid diagram", "fix mermaid error", "mermaid syntax error", "diagram not rendering", "flowchart not working", "sequence diagram broken", "escape special characters in mermaid", or mentions "mermaid", "flowchart", "sequence diagram", "class diagram", "state…
Use when evaluating a business idea, startup concept, marketing campaign, or go-to-market strategy. Trigger when user mentions idea validation, business feedback, campaign review, GTM strategy, pitch review, or asks "is this worth building/pursuing?" Don't use for code review, technical architecture, or implementation…
Knowledge management with QMD (Quick Markdown Search). Search, retrieve, and organize your personal knowledge base, notes, docs, and meeting transcripts. Use when asking about past notes, documentation, meetings, or when needing to recall information from your indexed markdown files.
Prepare and automate video drafts for Xiaohongshu, Douyin, Bilibili, and WeChat Channels with Ego Lite. Use for first-run onboarding, per-user available/default platform selection, video intake, platform copy and tags, parallel upload scheduling, draft recovery, original declarations, optional upload of provided cover…
Build, test, and manage mcpGraph tools using the mcpGraphToolkit MCP server. Discover MCP servers and tools, construct graph nodes with JSONata and JSON Logic, and interact with mcpGraph configurations. IMPORTANT: Always read this file before creating graph tools using mcpGraphToolkit.
A review framework for deciding whether an engineering idea or technical commitment is necessary, too broad, or premature. It examines the real problem, complexity, evidence, non-goals, and ease of reversal.
Reverse-engineer how someone thinks, talks, and makes decisions, then build a stress-tested AI System Prompt that replicates their voice and judgment, plus a rules file that code can check drafts against. Trigger on: digital twin, persona extraction, clone my voice, replicate how I think, build a system prompt from my…
You are an autonomous engineer for the cashfree/agent-skills repository. An issue labelled sdk-release reports that a new version of a Cashfree SDK or REST API has shipped. Your job: research the release from authoritative sources, update the changelog knowledge-base skill (and any integration skill the change…
A persistent Markdown knowledge base maintained by an AI agent. Markdown is a plain-text format for structured notes; the knowledge base can hold personal research or documentation about an open-source project's design.
Migra workflows de n8n/Make al ecosistema Claude Code. Analiza JSONs, mapea nodos, propone implementacion (skills, crons, web apps, dashboards) y detecta mejoras. Usa cuando el usuario pegue un JSON de n8n o mencione migrar automatizaciones.
Use with Codex, Claude Code, or another MCP client when lsp-mcp-server is connected and semantic code navigation, analysis, refactoring, or diagnostics are needed. Covers all 29 lsp tools for TypeScript, Python, Rust, Go, C/C++, Ruby, PHP, Elixir, Kotlin, Java, and user-configured languages. Prefer these tools to text…
Automated smart contract security audit pipeline. Auto-detects codebase size and scales accordingly — standard mode for small codebases, chunk mode with persistent state for large ones. Runs context building, dual-expert review, adversarial triage, and structured reporting. Use when auditing smart contracts, reviewing…
Build Instagram comment-to-DM funnels via Upload-Post API. Use when the user wants to automatically send DMs to people who comment specific keywords on their Instagram posts, set up lead capture funnels from comments, automate Instagram DM outreach to commenters, or monitor post comments and reply privately. Also…
Apply Altshuller's TRIZ (Theory of Inventive Problem Solving) to resolve engineering contradictions and produce inventive concepts instead of compromise solutions. TRIGGER when the user describes a technical trade-off ("improving X makes Y worse"), a physical contradiction (one element must have opposite properties)…
Query and analyze exported Apple Health metrics and raw samples with the nucleus-apple CLI. Use when the task involves trend summaries, daily metrics, raw sample inspection, sync change history, or diagnosing gaps between aggregates and raw exports.
The user installs this Skill to let you (an AI agent) connect the user with the right people or their bots (mostly closed-source) in the opportunity network. Use this Skill when the user intends to (1) manage listings or profiles for networking (e.g., "create a listing based on the information" or "what listings do I…
A review process for academic papers that uses six specialist AI reviewers and produces an annotated document in English and Chinese.
★not rated 23 3mo agoA103 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: