Research plugins

Analyzes GitHub trending repos, PyPI/NPM download spikes, and tech Twitter to identify emerging developer trends before they hit mainstream news.

1 skill

Executable scientific rubrics and criterion-level research revision.

8 skills

Traceable materials paper-production workflows: routed research, evidence-grounded writing, figures, data, citations, and reviewer responses.

17 skills · 1 MCP server

Search the web, read the clean text of a page by URL, crawl a few pages of one site and search Telegram channels through the NeuralDeep Search API with an sk- key. A standard-library Python client takes the key from --api-key, NEURALDEEP_SEARCH_API_KEY or NEURALDEEP_API_KEY, prints compact text or the raw JSON and exits with meaningful codes.

1 skill

ODIN workflows for source-backed investigation, verification, and design rationale.

13 skills

Multi-engine AI web search — Perplexity, Google AI, ChatGPT, and Gemini in parallel. No API keys needed.

1 MCP server

Research-team agents for Claude Code: supervisor, analysis-implementer, paper-writer, figure-descriptor, reviewer, literature-curator. Ships 6 agents, 13 slash commands, 18 skills, and 4 hooks for academic paper workflows.

18 skills · 13 commands · 6 agents · hooks

Agents and skills for Research-Through-Design approach to research software design

1 skill · 2 commands · 1 agent

Moteur de recherche autonome local-first — collecte multi-sources, dédup, scoring, synthèse Markdown.

Query Spicy Regs regulatory datasets with DuckDB against the public Cloudflare R2 bucket.

1 skill

Searches arXiv, summarizes or compares papers, and builds a compact literature survey as citation-ready, source-linked paper cards. Prefer the Researcher shadow agent for noisy multi-paper retrieval.

1 skill

Pre-registers a performance study, numerical comparison, parameter sweep, or benchmark: thresholds, tolerances, environment pins, and verdict conditions locked into the validation contract before any measurement. Not for diagnosing a stalled bug; use scientific-debugging.

1 skill

Diagnoses stalled or cross-system failures and wrong, NaN, nondeterministic, or unexpectedly slow scientific results through falsifiable hypotheses across distinct fault classes, with evidence-cited verdicts before any fix. Not for designing benchmarks or pre-registered experiments; use experiment-protocol.

1 skill

Ask a question, get an answer with citations you can check. It runs from a two-minute lookup to a multi-week investigation with its own folder, and argues against its own findings before handing them over.

12 skills · 2 agents · hooks

Multi-agent research pipeline with parallel researchers and synthesis

2 commands · 6 agents · 5 MCP servers · hooks

Medical research planning, literature review, data analysis, manuscript writing, peer review, revision, and submission.

2 skills

Power search via Exa MCP. 8 modes: quick, deep, code, docs, debug, news, compare, research.

1 skill

Connects Claude Code to a local RKA backend for provenance-tracked research workflows. Provides typed MCP dispatch, three research roles (Brain, Executor, and PI), five Core slash commands, and a SessionStart backend check. Manuscript drafting is provided separately by the explicit-only rka-writer plugin.

4 skills · 5 commands · 1 MCP server · hooks

Multi-agent research system for comprehensive topic investigation. The research-team:coordinator skill decomposes a topic into subtopics, spawns parallel research-specialist subagents, and delegates synthesis to a report-writer — all from the main agent thread so nested-spawn constraints don't apply. Reports are plain Markdown by default, with Obsidian and Joplin profiles and five report templates.

2 skills · 2 agents

Socratic onboarding, 4-stage reflexive coding, methodology hooks, specialized agents and the Lotus Wisdom MCP for the sandwich methodology.

29 skills · 4 agents · 1 MCP server · hooks

Autonomous AI research pipeline that identifies, analyzes, and synthesizes SOTA AI research via Hugging Face and ArXiv. Discovers and ranks papers by relevance/recency/impact, extracts benchmarks from full-text markdown, and produces thematic synthesis reports.

1 skill

Build and analyze signalling networks from interaction databases with NeKo.

Configure, simulate, and analyze stochastic Boolean models with MaBoSS.

Build, inspect, and export PhysiCell and PhysiBoSS configuration files.

Sustained mathematical research with auditable claims, dependencies and reproducible experiments

11 skills

Detect hallucinated references in academic paper PDF files: extract -> verify against offline DBLP + CrossRef/arXiv/Semantic Scholar and other open databases -> triage the residue -> report likely-hallucinated citations.

1 skill

Evidence-bounded drafting, rewriting, auditing, and venue adaptation for IEEE and ACM engineering manuscripts.

1 skill

Setup plus 17 CLI-backed Bohrium skills for compute jobs, development nodes, datasets, files, scientific databases, images, projects, knowledge bases, papers and patents, PDFs, scholars, SciencePedia, scientific tools, web search, sandboxes, LKM, and Science Mentor. Requires the bohr CLI (setup skill can install it).

18 skills

OSS Radar search pipeline: data prep, agent harness, research/impl agents, and the searchpo-full-flow command.

8 skills · 1 command · 3 agents · 1 MCP server

Digest-bound lending-data releases with a resumable Ethereum USDC interval collector proven against live providers and attributing proxy logs by transaction position, unsigned evidence statements, reviewed credit views and address queries.

1 skill