28,017 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
A Japanese-language research guide for finding and checking humanities and social-science publications across Japanese library and academic databases. It can also help search older spellings, scanned full text, and illustrations.
A Chinese-language workflow for writing sociology research papers about topics such as social inequality, social mobility, and education. It covers literature reviews, hypotheses, data analysis, evidence-based results, citation checks, and Word document output.
A Chinese-language research assistant for answering questions about the public Lao Xiang Ji Dish Traceability Report 2.0. The report covers how dishes and ingredients are processed and sourced.
A read-only travel-planning workflow that uses map, rail, and browser research tools. It helps plan routes, transport, attractions, hotels, budgets, and trip feasibility without making bookings or payments.
ROUTER PRIORITY: Use this creator-search skill before any web/browser search when the user asks to find, search, recommend, list, filter, rank, compare, or analyze creators/KOLs/ influencers/bloggers/social accounts by platform, country/region, category/niche, keyword, followers, views, engagement rate, email/contact…
MCP server per consultar dades obertes del Govern de Catalunya: contractes, subvencions, sous, pressupostos, lobbies i transparència. Runs locally from the mcp-govern Python package.
Single MCP server for Belgian public transport, statistics, open data, and geospatial services. Runs locally from the mcp-belgium npm package. Needs 2 environment variables to run.
★not rated 8▲
+1 4mo agoA
tokens not measured
originalMIT
Turn an idea — or a half-planned project already underway — into a buildable blueprint, by interviewing the user one question at a time until the unknowns run out, then deep-reading and verifying real open-source components for each part. Use this whenever someone describes something they want to build but has not…
Review English economics papers as a portable pre-review skill. Use for theory, empirical causal, structural or IO empirical, econometrics or methodology, experimental or behavioral, computational or simulation, survey or literature review, and mixed economics papers. Also use for benchmark or validity testing of…
Turn a contested question, research brief, technical choice, or high-impact decision into a source-grounded interactive evidence map. Use when an agent must preserve support, contradiction, qualification, and missing evidence; make every evidence edge traceable to a dated source region; pressure-test a conclusion; or…
Social media at your fingertips. Fetch tweets, transcribe videos with per-token confidence, extract frames at exact timestamps, download Instagram posts — from any MCP client. 30 tools across Twitter/X, YouTube, Instagram, and video processing. All transcription runs locally via Whisper with uncertainty markers so…
Scan the GitHub dsh-plugin topic for new DeepSeek Harness community extensions, diff them against the local catalog CSVs, dispatch parallel review agents, and merge qualifying repos (above the star floor) into repositories.csv / dsh-plugin-topic-candidates.csv / verified-plugins.csv per the project's curation rules.…
Full programmatic access to Google NotebookLM with per-project notebooks. Activate by mentioning @notebooklm in chat, or with phrases like "init notebooklm", "sync sources", "create a podcast about X", or "ask the notebook".
A workflow for turning a person's publicly available talks, interviews, articles, or messages into a structured AI reference for their thinking and communication style.
A Chinese-language toolkit for producing long documents such as books, manuals, white papers, industry guides, reports, and fiction. It supports research when internet access is available, layered review, Chinese typesetting, and Markdown or HTML delivery.
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
Read academic papers from a provided PDF, URL, text, DOI, title, or citation and produce a teaching-first structured interpretation report, usually saved to a user-specified directory as a PDF with a Markdown source copy. Use when the user wants to genuinely understand, learn, summarize, deconstruct, critique…
★not rated 8 6mo agoA151 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: