Skills, plugins and agents for Information research

Search your complete conversation history stored in session JSONL files. Use this when a user references older/parent conversations or asks what was said before.

Spike

Use when the user wants to test an idea before committing to a real build: "spike this", "quick prototype", "is this possible", "compare A/B", "before we build".

Discrawl

Use local Discord archive data first for Discord questions. Hit Discord APIs

Graincrawl

Use local Granola archive data first. Check freshness for recent/current questions:

Slacrawl

Use local Slack archive data first. Check freshness for recent/current questions:

Tavily Tools

| Need | Tool | When |

search first Research Before You Code

Systematizes the "search for existing solutions before implementing" workflow.

Market Research

Produce research that supports decisions, not research theater.

Cursor

Exa Search

Neural search for web content, code, companies, and people via the Exa MCP server.

Deep Research

Produce thorough, cited research reports from multiple web sources using firecrawl and exa MCP tools.

Post hoc Analyzer Agent

★182.1k

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

anthropics

Interviewe moi

★108.4k

This helps determine what the user actually wants, rather than what they think they should want. To do this, we conduct a structured interview

addyosmani

PDF Analysis and Editing

★78.8k

Reads, analyzes, and converts PDF documents using Claude.

shareAI-lab

Market Research

★55.5k

You have raw research material (transcripts, surveys, reviews, tickets). Your job is to extract signal.

coreyhaines31

Cli tout ce qui concerne intelwatch

★54.9k

Zero friction. Full context. Competitive intelligence, M&A due diligence, and OSINT directly from your terminal. Uses Node.js/npx.

HKUDS

Exa web search (CLI)

★54.9k

Agent-native CLI for Exa web search and content retrieval workflows.

HKUDS

Academic research skills

★52.9k

Ajoute Production-grade academic research pipeline for Claude Code: research → write → review → revise → finalize. 4 skills, 35+ modes, 38-agent ensem

Autoskill

★52.8k

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones

K-Dense-AI

Scientific research in the journal Nature

★49.3k

Multi-source literature search, citation verification, MeSH search strategy, and literature synthesis.

Yuan1z0825

Apify Market Research

★47.9k

Analyze market conditions, geographic opportunities, pricing, consumer behavior, and product validation

sickn33

context7

★43.0k

Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.

Claude CodeOpenClaw