Discover, inventory, dedupe, score, and monitor public SOURCES of agent skills (repos, directories, awesome-lists, mirrors) across GitHub, GitLab, Bitbucket, Codeberg/Forgejo, SourceHut, generic git, and websites. Keeps a durable SQLite inventory with no duplicate rows and no duplicate notifications, and emits…
Build and expand an insight-ready raw-material layer by discovering page-level sources, deduplicating them with an internal pre-crawl link index, capturing raw Markdown, verifying metadata in place, and keeping ingest/register state aligned. Use for additive source harvesting, raw webpage capture, source registry…
Fetch and analyze X (Twitter) articles/posts using the Twitter API. Use when user provides an X post URL or post ID and wants to retrieve the article content and get an analysis/interpretation of the post. Handles both URL formats (x.com or twitter.com) and direct post IDs.
Runs multi-source web search through the AI Search Gateway. Use when the user wants fresh web results, research across sources, AI summaries, or MCP-based search integration.
A reporting workflow for analysing AI news for the TrendLife AI Taskforce. It produces daily, weekly, or monthly reports prepared for sharing with others.
Search the web using Exa's AI-powered search API. Supports semantic search, content extraction, direct answers, and deep research with structured output.
Search YouTube videos by query or within specific channels. Supports date filtering, sort ordering, and duration filters to exclude YouTube Shorts. Returns LLM-optimized JSON with video details.
Use the CBETA MCP server for Chinese Buddhist scripture search, catalog lookup, metadata retrieval, KWIC inspection, and source-text citation. Use when Codex needs live CBETA queries, Buddhist canon text lookup, work/juan/linehead citation, translator or dynasty searches, or CBETA MCP tool guidance.
ML research agent persona and operating protocols. Use when designing experiments, choosing problems, reading literature, analyzing training runs, writing research notes, debugging models, or when the user invokes research mode. Embodies outcome-first reasoning, fast iteration loops, taste-building, and honest logging…
Convert external material into reusable, linkable, executable literature-note assets. Use for articles/books/papers/videos/podcasts: multi-pass reading → extract tools/templates → atomize → link discovery → dedupe → index note → QA.
Runtime helper for autonomous-research-loop ledgers plus headless drive, host-owned multi-agent panel phases (--panel on, auto, or off), and the default cross-platform force-loop kit (bootstrap/start/drain with enforce/hard/notify defaults). Use to initialize, append, validate, inspect, smoke-test, drive, or…
Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure…
A research workflow for tracking the life cycle of an investment theme and identifying the companies or other assets best connected to it. It separates broad industry research, theme-based research, and analysis of individual stocks.
Maintain the rolling A-share strategy library that stores imported macro hypotheses, scenario cards, daily market entries, holdings-first actions, and main-board tradable picks under strategylibrary/. Use when Codex needs to convert user macro materials, live market validation, or same-day A-share review into…
Combines search results from multiple sources into coherent, deduplicated answers with source attribution. Handles confidence scoring based on freshness and authority, and summarizes large result sets effectively.
One or two sentences describing what this skill enables Claude to do and when it should trigger. Be specific about the Zotero API area or task covered.
Search OpenSearch documentation, blogs, and community forums. Use when the user asks about OpenSearch features, configuration, APIs, troubleshooting, k-NN, neural search, cluster settings, index mappings, query DSL, or any OpenSearch-related questions.
A Korean-language workflow skill for answering engineering questions using Korean laws, construction standards, agency rules, and other cited sources. It covers fields such as roads, buildings, bridges, water, railways, and construction management.
Use when an agent can run shell commands and needs secure short-lived human surveys. Secure E2EE via uvx is the default; plaintext is explicit opt-in only.
Use when a user asks for a literature review, survey, "related work", or "what's the state of the art / recent advances" on a research topic — and the arXiv tools (the arxiv-mcp server's arxiv tools, or the arxiv CLI) are available.
Use EasySourceFlow whenever the user provides a supported webpage, video, cloud-document link, or file for summarization. A bare supported link or attachment means "summarize this with EasySourceFlow" unless the user explicitly requests a different operation. Also use it for notes, transcription, previous results…
★not rated 2 1mo agoA79 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: