xiaohongshu
7705Skill Claude CodeCodex
A tool for Xiaohongshu, a Chinese social platform for lifestyle and consumer posts, images, and videos.
All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 437,679 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.
Skill Claude CodeCodex
A tool for Xiaohongshu, a Chinese social platform for lifestyle and consumer posts, images, and videos.
Skill Claude CodeCodex
Technical reference for writing open-sheet workbooks — the file contract, the component surface, references and formulas, number formats, and the rules that keep a workbook a live model. Use this whenever writing or editing a file under sheets/ /index.tsx. The workflow for drafting a new workbook from scratch lives in…
Skill Claude Code needs its repo
Run after setup-infrastructure to map rooms, entities, and preferences to the dashboard and automation templates. Conversational and resumable. Trigger phrases: "customize my home", "set up rooms", "configure automations", "map my entities", "set up my dashboard", "finish setup", "resume setup".
MCP server Claude CodeCodexCursor +2
MCP server "tiger-cli" as configured in timescale/tiger-cli. Runs in Docker (ghcr.io/timescale/tiger-cli:0.27.0). Needs 2 environment variables to run.
Skill Claude CodeCodex
Methodology for auditing a real non-technical small service business, understanding its operations, and designing an AI agent system (lead generation, qualification, estimation, booking, billing, reporting) that the owners interact with entirely by text message.
Plugin Claude Code
InfraNodus skills: a knowledge graph + gap finder for your notes, vault or agent memory (the infranodus core skill), plus research-to-publish workflow skills: LLM wiki, ontology, project memory, perspective shifting, cognitive variability, writing and SEO. Experimental skills moved to infranodus/skills-lab.
Skill Claude Code needs its repo
Decide whether a preview the visual-diff bot flagged actually regressed or is simply nondeterministic, using a repeat-render oracle at a single commit. Use when a PR's preview diff reports a changed preview whose source the PR does not touch, or when a render, GIF or filmstrip is suspected of being unstable.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 69 tokens together
Trading Skills — live AI crypto trading signals with reasoning, confidence and verified outcomes. Free key for every signal; Pro adds entry, SL, TP and leverage.
emaynard/claude-family-history-research-skill
Skill Claude CodeCodex
Provides assistance with planning family history and genealogy research projects.
Skill Claude CodeCodex
Anti-detection browser automation MCP skill for OpenClaw agents with 53 tools for navigation, interaction, observation, extraction, downloads, profiles, sessions, and stealth web search.
Skill Claude Code
A tool for searching past Claude Code, Codex, and Pi work sessions. It finds earlier conversations and solutions from session history.
doordash-oss/agentic-orchestrator
Skill Claude CodeCodex
Revise an implementation roadmap based on critic feedback.
Plugin Claude Code
Plugin marketplace listing 1 plugin: llm-router.
MCP server Claude CodeCodexCursor +2
SwiftLens is a Model Context Protocol (MCP) server that provides deep, semantic-level analysis of Swift codebases to any AI models. By integrating directly with Apple's SourceKit-LSP, SwiftLens enables AI models to understand Swift code with compiler-grade accuracy. Runs locally from the swiftlens Python package.
promptadvisers/bench-studio-public
Skill Codex
Create and inspect images, videos, local websites, and designed PDF documents through Bench Studio. Use when a request involves choosing a fal model, mapping reference media to model-specific fields, generating media with transparent pricing, building a prompt-driven website or PDF through the cached Codex…
Plugin Claude Code
Plugin marketplace listing 1 plugin: metaxy.
Skill Claude CodeCodex
Run local black-box voice tests against the physical Dotty robot by playing a TTS prompt through the workstation speakers while the C920 records video and room audio. Use when testing Dotty's wake word, ASR, spoken response, expressions, or end-to-end voice behavior on this bench.
IamRamgarhia/All-In-One-Free-SEO-Tool
Plugin Claude Code
Bundles 5 skills · 184 tokens together
Drive a self-hosted SEO tool: read what it found, decide what to change, write the copy, apply it to the live site, and undo it if it was wrong.
Skill Claude CodeCodex
Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
Plugin Claude Code
Bundles 7 skills, 1 command · 807 tokens together
Personal experience knowledge graph for Claude Code. Build the graph by talking. Renders English resumes and Korean cover letters from the same vault.
madebyaris/advance-minimax-m3-cursor-rules
Skill Cursor
Category-aware design skill that builds distinctive, production-grade UIs. Brand-vs-product register, color strategy commitment, scene-based theme choice, palettes, font pairings, UX patterns, shadcn/token integration, empty-error-loading copy, secondary slop signals, multimodal design parity from mocks, and a…
Skill Claude CodeCodex
Use the standalone qiaomu-bento-ppt skill to create or edit qiaomu-style bento presentations as self-contained .bento.html files from briefs, notes, reports, URLs, data, or existing bento decks. Use this skill when the user explicitly asks for bento/slides, a .bento.html deck, an offline-editable single-file HTML…
Skill Claude CodeCodex
Use this skill when the user needs recent public internet information such as official announcements, release notes, news, vulnerability notices, or public documentation.
OdradekAI/harness-engineering-guide
Skill Claude CodeCodex
Audit, design, and implement AI agent harnesses for any codebase. A harness is the constraints, feedback loops, and verification systems surrounding AI coding agents — improving it is the highest-leverage way to improve AI code quality. Three modes: Audit (scorecard), Implement (set up components), Design (full…
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: