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.
Start, orchestrate, or resume an autonomous research project through hierarchical EXPERIMENT, WRITE, and REVIEW gates. Use when running a project from a rough idea to a complete paper, recovering after context loss, deciding which gate or inner loop must run next, auditing whether a specialist loop actually completed…
Keyless multi-engine web search, clean-Markdown fetch, and paginated read for AI agents, plus arxiv and github lookup. Bundles two portable SKILLs (clearnet and Tor), a websearch CLI with a one-call init, a self-hosted SearXNG that needs no Docker, an optional egress proxy (NordVPN SOCKS5), an optional Tor layer for…
★not rated 8 2mo agoA
tokens not measured
originalMIT
MCP server for hh.ru jobs API — vacancy search, salary stats, employers, regions. Public endpoints. Runs locally from the @theyahia/hh-mcp npm package. Needs 1 environment variable to run.
★not rated 8▲
+3 2mo agoA
tokens not measured
originalMIT
Give Claude eyes and ears on any online video, then analyze it. Downloads a video from a URL (YouTube, Instagram, X, Vimeo, and 1000+ yt-dlp sites), extracts key frames, and gets a transcript (native captions, else local Whisper), then hands the frames + timestamped transcript to Claude so it can produce a full…
Analyze a single research paper deeply and create or update evidence-grounded professional notes in Markdown, Notion, or Feishu/Lark. Use when the user asks to read, analyze, explain, summarize, interpret, or take notes on a paper, or supplies an arXiv link, PDF, DOI, title, project page, code repository, existing…
Retrieval platform for AI agents — 14 search providers, 12-step content extraction, dead URL recovery, site capture, and local corpus storage. One API. Runs locally from the argus-search Python package. Needs 8 environment variables to run.
★not rated 8▲
+1 2d agoA
tokens not measured
originalMIT
Run market research with simulated persona panels — review marketing assets, run interviews / surveys / focus groups / A-B tests / Van Westendorp / conjoint / MaxDiff / TURF / brand tracking / ethnographic / grounded theory and more. Personas live as .md files in a local .personas/ folder; build them via interview…
★not rated 8▲
+3
changed 13d agoA
tokens not measured
Unofficial MCP server for 104.com.tw (Taiwan job board): search jobs, job details, company openings, applicant analysis. Runs locally from the mcp-server-104 npm package.
★not rated 8 1mo agoA
tokens not measured
originalMIT
Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Use when turning observations or preliminary findings into transparent, testable research plans without treating…
MCP server "agntspce-search" as configured in AgntSpce/AgntSpce. Launched with /Users/prashik/Library/Application Support/AgntSpce/search/python/bin/agntspce-s.
Şirketin gözcüsü (rakip radarı). Listedeki herkese açık kaynakları tarayıcıyla okur, son günlerde kim ne paylaşmış ve hangisi tutmuş bakar, üç parçalı radar raporu yazar; taze ve ivmeli bir içerik görürse yanıt ya da gönderi taslağı ekler. CEO radar ve rakiplerimi izle işlerinde işe alır.
A field guide to Claude and AI tools inside Claude Code: answers looked up in pages that carry a verified date, a CLAUDE.md audit, and seven role-based skill packs.
★not rated 8 4d agoA
tokens not measured
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: