All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 417,707 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.
MCP server "media-crawler-mcp-service" as configured in mcp-service/media-crawler-mcp-service. Runs locally from the media-crawler-mcp-service Python package.
Designs high-performing ad creatives across Instagram, Facebook, TikTok, LinkedIn, Google (Display / Demand Gen), YouTube, Pinterest, and X/Twitter — locking platform dimensions, safe zones, text overlay policy, character limits, industry visual DNA, ad objective hierarchy, composition patterns, CTA strategy, and…
Create a final zeroshot talking-avatar video or prepare its script from a reference video. Use when an agent should accept an uploaded video or authorized Douyin link, transcribe and rewrite spoken copy, authenticate with LycheeAILab, clone an authorized voice, synthesize LycheeTTS speech, build an internal motion…
18 AI-native GTM skills for founders and revenue teams: positioning, AI pricing, cold outreach, AI SDRs, enrichment, video outreach, launches, SEO, social selling, content-to-pipeline, UGC ads, paid creative, retention, partnerships, GTM engineering, and metrics.
GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, KvikIO, cuCIM, cuxfilter, cuVS, cuSpatial, and RAFT. Use whenever the user mentions GPU/CUDA/NVIDIA acceleration, or wants to speed up NumPy, pandas, scikit-learn, scikit-image, NetworkX, GeoPandas, or Faiss workloads. Covers physics…
A systematic research assistant for Chinese law. It searches laws, regulations, judicial interpretations, guiding cases, and typical cases, then organizes the legal sources and how they relate.
Use when the user wants comic story architecture, page and panel planning, a four-panel narrative, a complete text storyboard, or a targeted story, shot, layout, or continuity revision.
Do not load unless the request or established context explicitly identifies Home Memory (HM) and requires a documentation decision about record boundaries, relationships or information placement. If the product is ambiguous, ask whether the user means Home Memory or Smartconstruct and load neither product skill first.…
Silently restructures the user's natural-language prompt into the format the model CURRENTLY running this skill handles best, then answers. On activation it identifies which model family is executing it (Claude, GPT, Gemini, Llama, DeepSeek, Mistral, Qwen, Grok, Perplexity, Kimi, GLM, Command, Nova, or Phi) and loads…
Design, build, and maintain autonomous OpenClaw workflows (stewards). Use when creating new workflow agents, improving existing ones, evaluating automation opportunities, or debugging workflow reliability. Triggers on "build a workflow", "create a steward", "automate this process", "workflow audit", "what should I…
Manage, search, organize, and maintain Obsidian vaults integrated with Claude Code and Cowork. Use this skill whenever the user mentions Obsidian, vault, notes, daily journal, meeting notes, knowledge base, brain dump, note-taking, or wants to capture/organize/search/review their personal or work notes. Also trigger…
A reference-formatting skill creates Chinese academic bibliography entries and BibTeX, a machine-readable format for citation tools, from literature titles.
Free SEO + AEO + GEO toolkit by Akii. All skills run on your Claude Code session model (Claude Sonnet / Opus / etc). Aligned with Google's AI Optimization Guide for Google AI Overviews + AI Mode. Audit sites, plan content, optimize pages, generate schema, cluster keywords. AI Visibility Score specifically calls the…
★not rated 76 3mo agoA
tokens not measured
originalMIT
Claude plans, delegates, and tastes every plate. Sonnet, Codex, GLM, or Grok does the knife work. A Claude Code plugin for the orchestrator/implementer split: /serve runs the whole line autonomously (implement, cross-review, fix, verify), /fire hands specced implementation to the worker, /taste runs cross-model review.
★not rated 76 1mo 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: