Research

26,283 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.

search

865

paperfoot/search-cli

Skill Claude CodeCodex

Multi-provider search CLI with 13 explicit modes (you pick the mode/providers; no intent guessing). Results are rank-fused across providers. Run search agent-info for full capabilities and exit codes.

not rated 52 +1 1mo ago A 43 tokens original MIT

litllm

868

LitLLM/LitLLM

Skill Claude Code

Generate a related-work section, find prior literature, or rank candidate citations for an academic paper. Uses LLM-driven debate ranking over Semantic Scholar / arXiv / OpenAlex search, with optional citation-graph BFS expansion (deep research). Use when the user provides a paper (PDF or markdown) and asks for…

not rated 52 +1 4mo ago C 80 tokens original Apache-2.0

openalex

869

oksure/openalex-research-mcp

Skill Claude Code needs its repo

A skill for searching OpenAlex, a free catalog of research papers, authors, institutions, journals, and research topics.

not rated 52 +5 2mo ago A 100 tokens original MIT

notebooklm-mcp

870

alfredang/notebooklm-mcp

Skill Claude CodeCodex

This skill enables automated content processing and generation through NotebookLM, converting various content sources into multiple output formats.

not rated 52 +1 7mo ago B 0 tokens

deepsrt-mcp

871

DeepSRT/deepsrt-mcp

MCP server Claude CodeCodexCursor +2

DeepSRT MCP Server - YouTube video summarization and transcript extraction. Runs locally from the @deepsrt/deepsrt-mcp npm package.

not rated 52 1y ago A tokens not measured

doc-audit

872

Mexregkan/claude-for-researchers

Skill Claude Code

Evaluate one project document in detail — a workbook section, big picture, strategy map, handoff message, paper, brief, or primer — without editing it. Runs the mechanical lint, builds a claim ledger, types every headline against the eight claim statuses in CLAUDE.md, traces cited evidence to the scripts and logs that…

not rated 52 9d ago A SkillSpector: warn 140 tokens original MIT

hn

873

heartleo/hn-cli

Plugin Claude Code

Bundles 1 skill · 149 tokens together

Hacker News for Claude. Scan the front page for today's themes, hot discussions, and industry mix.

not rated 51 +1 16d ago A tokens not measured original MIT

huntkit

874

assafkip/huntkit

Plugin Claude Code

Bundles 3 skills, 22 commands, 2 hooks · 400 tokens together

Investigation toolkit for Claude Code. Case management, OSINT, structured analytic techniques (Heuer / CIA tradecraft primer), chain-of-custody evidence capture, and bundled MCP servers for infrastructure recon and threat intel.

not rated 51 yesterday A tokens not measured original MIT

ajhcs/healthcare-agents

Agent Claude Code

Use for Community Health Coordinator work in Population Health & Community Health including CHNA, community benefit, Schedule H, grants, CBO partnerships.

not rated 51 1mo ago A 35 tokens original Apache-2.0

khanote.start-my-day

876

almost-khan/khanote

Skill Claude CodeCodex

You are running the daily research briefing or ad-hoc research workflow for the user.

not rated 51 5mo ago A 0 tokens

deep-research

877

lvndry/jazz

Skill Claude CodeCodex

Conduct comprehensive multi-source research for complex questions using a team of specialist investigators. Use when the user asks a complicated question requiring multiple sources, in-depth analysis, cross-referencing, or expert-level research reports. Triggers on "research", "investigate", "deep dive", "analyze…

not rated 51 today A SkillSpector: pass 75 tokens original MIT

interview-the-system

878

luanmorenommaciel/uc-transact-co

Skill Codex

Turn an ambiguous question about an unfamiliar or brownfield system into a bounded, read-only, evidence-backed investigation with a confirmed investigation contract, deliberate context manifest, claim ledger, ontology, owned open questions, and reviewable technical brief. Use when asked to investigate a repository…

not rated 51 +2 28d ago A 95 tokens

research-craft

879

nik1t7n/research-craft-skill

Skill Claude CodeCodex

Use when planning, reviewing, or improving research work: choosing research problems, designing ML/AI experiments, reading papers, building experiment loops, analyzing outputs, writing research notes, or turning vague curiosity into a disciplined research plan. Emphasizes avoiding absorbed problems, upgrading…

not rated 50 2mo ago A 76 tokens original MIT

ethglobal

881

ethglobal-skills/repo

Plugin Claude Code

Bundles 1 skill · 56 tokens together

Search 17,000+ ETHGlobal hackathon projects, sponsor bounties, and prize winners across all events from ETHWaterloo to present.

not rated 50 3mo ago A tokens not measured

xueqiu-summary

883

chenmuwen0930-rgb/openclaw-skill-snowtrace

Skill Claude Code

A Chinese-language skill that gathers recent posts from followed Snowball influencers and market data for a user's watchlist. Snowball is a Chinese investment social network, and the skill combines the results into an investment reference report.

not rated 50 6mo ago A 40 tokens original MIT

llm-wiki

884

Oshayr/LLM-Wiki

Plugin Claude Code

Bundles 5 skills, 10 agents · 634 tokens together

LLM-powered personal wiki — autonomous knowledge base with research-on-miss, ingestion, search, a browsable web UI, and universal data gravity. Saves and retrieves knowledge automatically whenever relevant.

not rated 50 +1 4mo ago A tokens not measured original MIT

agentbay-ai/agentbay-skills

Skill Claude CodeCodex

A public-opinion monitoring workflow that collects posts or other information by keyword and platform, analyzes sentiment, and produces a report.

not rated 50 7mo ago A 125 tokens

research-proof-plugin

887

tonyblu331/research-proof

Plugin Claude Code

Bundles 1 skill · 101 tokens together

Falsifiable research planning for AI agents: pressure-test claims, freeze evaluators, use AI-lab and medical evidence patterns, build proof ladders, and maintain proof ledgers.

not rated 50 +2 3mo ago A tokens not measured original MIT

dsh-deepread

888

xiehuan123/dsh-deepread

Plugin Claude Code

Bundles 1 skill · 123 tokens together

Deep-reading assistant: five modes (quick, deep, knowledge-map, Feynman, full book) to extract core claims, argument structure, and key evidence from books and articles; exports Markdown, FreeMind/XMind mindmaps, and HTML reports.

not rated 50 +2 changed 2d ago A tokens not measured original MIT

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: