165 boosters for "research" — open source, verified from GitHub, ready to install
Litmus spawns multiple OpenClaw subagents that experiment on your GPU overnight. Each runs on its own git branch in a shared lab repository — every experiment is a commit, agents can read each other's code, cherry-pick breakthroughs, and build on the global best at any time.
This file is the control plane. It decides the mode, loads only the references that mode needs, and runs the shared start and finish steps. Methodology lives in The experience this skill must deliver:
Use this skill when the user gives a topic or keyword set and wants a local literature-harvesting workflow, not a one-off manual search. This skill is self-contained. The target project does not need to already contain: The bundled copies live under:
A skill-format reference for any agent (Claude Code, Codex, Cursor, Hermes, plain-MCP) calling this server. For human-readable installation instructions, see README.md. For harness-agnostic routing logic and the pasteable instruction block (drop into your harness's global / or a standalone agent's
Use AskUserQuestion to ask the buyer: Tell the user the version was updated, then re-read the EVALUATION.md file from the updated directory and proceed with the skill. After the preamble, read the full evaluation methodology:
"description": "Parallel Web Search MCP and Task API integration for Claude Code. Provides web search, content extraction, deep research, data enrichment, entity discovery (FindAll), and web monitoring.", "name": "Parallel Web Systems", "email": "support@parallel.ai"
This is a TypeScript project — AI content pipeline using Claude Agent SDK + MCP. Use strict TypeScript, follow ESLint rules, prefer async/await.
A planning-focused skill booster that helps developers research, analyze, and create implementation plans for Laravel + React admin dashboards, with intelligent state management for active vs. suggested plans.
"email": "help@calif.io", "url": "https://github.com/califio/skills" "description": "Claude Code plugins from Calif.io for AI-assisted security research and code auditing"
Heuristic scoring (no AI key configured).
A Cursor rules-based research agent specialized in exploring repositories, documentation, and remote codebases using Nia MCP tools without modifying files. Ideal for developers conducting deep technical research, knowledge discovery, and cross-team information handoffs.
"name": "ai-marketing-skills", "name": "SuperAmped", "url": "https://superamped.com"
"name": "phd-deepread", "description": "Transform academic PDFs into structured literature notes and critical-thinking canvases for Obsidian", "name": "Helen Insights",
You are a biomedical data visualization expert powered by the Bizard atlas — a comprehensive collection of 256 reproducible visualization tutorials covering R, Python, and Julia, with 793 curated figure examples from real biomedical research. When a user asks for help with data visualization — espec
Systematic, multi-engine academic paper search. Choose engines based on the search goal: Before searching, clarify:
Systematic management of an academic literature library via Zotero. Standard collection hierarchy: Use tags to cross-cut the collection hierarchy:
Pipeline for downloading academic paper full-text at scale. Handles the three classes of sources that exist in 2026: 1. Publisher TDM APIs (Elsevier / Wiley / Springer) — for paywalled content where the institution has a subscription 2. OA aggregators (Unpaywall / OpenAlex / Crossref) — for Open Acc
Turn social media paper recommendations into actionable research items. Use platform-specific tools to fetch the full content: From the extracted content, identify all referenced papers:
Systematic literature survey for positioning a research contribution. Work with the user to pin down: Every research topic sits at an intersection of multiple dimensions. Identify 2-4 axes:
<!-- Bilingual skill: this SKILL.md is the English primary; the Chinese mirror is SKILL.zh.md. Each references/.md has a Chinese mirror references/.zh.md (same content, two languages). The .md files are authoritative for the agent; the .zh.md files are for human readers. -->
Turn a folder of raw files into a Markdown vault that an LLM can grep, and then answer questions over that vault responsibly. source file, carrying retrieval frontmatter (abstract / tags / synonyms) + a
Skill metadata (version, author, license, optional_mcps, fallback) lives in manifest.json and plugin.json. Claude Code only reads and from this frontmatter; extra keys are silently ignored, so they belong with
This skill packages everything needed to build a panel that reads prediction-market probabilities from Polymarket + Kalshi (both public, read-only, no account) and presents them as a macro sentiment thermometer grouped by module.
"name": "bulk-summarize", "description": "Media research assistant for bulk video and podcast summarization across YouTube, Apple Podcasts, Spotify, and other platforms", "repository": "https://github.com/scottlepp/bulk-summarize"