Research commands

nguyenvanduocit/research-kit

Command

Create publication-ready research outputs.

jumppad-labs/spektacular

Command

Search, contribute to, or update the project's knowledge base.

leeguooooo/misonote-markdown

Command Claude Code

Generate a complete PRP for general feature implementation with thorough research. Ensure context is passed to the AI agent to enable self-validation and iterative refinement. Read the feature file first to understand what needs to be created, how the examples provided help, and any other considerations.

cmertdalli/polisci-review

Command

Run a stage-aware political science pre-submission audit with journal personas and evidence-grounded issue reporting.

carlos-rodrigo/claude-code.nvim

Command

name: research description: Comprehensive research agent that combines codebase analysis with web research, creating organized topic-specific folders with structured findings version: 1.0.0.

restarter/lets-workflow

Command

Ask a question about the outside world, get back a concise answer where every non-trivial claim carries a citation — searched and fetched from the live web, cross-checked by a skeptic agent, and honestly labeled where the evidence is thin.

miyamamoto/jvlink-mcp-server

Command Claude Code

A command for asking jvlink-mcp-server about Japanese horse racing.

HomenShum/NodeBenchAI

Command Claude Code

Run a comprehensive audit of agent-facing infrastructure against the 8-point reliability checklist.

hec-ovi/research-skill

Command

Use the bundled Codex research skill to recall, refresh, or store project-scoped research.

Mahanaicoach/competitor-x-ray

Command

Run Competitor X-Ray on a list of competitors (handles, company names, or URLs).

knitli/codeweaver

Command Claude Code

Expert in synthesizing and curating external API knowledge for precise feature integration.

MaesHughes/wuxing-search-mcp

Command Claude Code

A research command that breaks a question into parts and performs repeated searches before producing a detailed report. Research depth ranges from simple fact-finding to broad comparisons and technical investigations.

EvoClaw/amplify

Command

Design method/analysis framework with evaluation protocol and story line.

cycleuser/Skills

Command

Load the academic-guide skill and execute the full 4-phase field navigation workflow.

michielhdoteth/squish-memory

Command

Search and load past AI coding sessions from Squish memory.

arielshad/balagan-agent

Command Claude Code

Fact-check claims or verify information.

jiin-choi/vc-copilot

Command

A command for finding companies whose growth may not yet be widely noticed by venture capital investors. It uses three stages: early signals, early growth, and broader market agreement.

allxsmith/bestax

Command Claude Code

Find likely duplicates of an issue with 5 parallel search agents and report them for publication.

guzus/ai-research-arm

Command Claude Code

Research a topic with primary sources and write an HTML article. Asks first whether to run locally (in-chat, 5-15 min) or route to the GitHub workflow (self-hosted runner, 20-45 min, deeper output).

Horosheff/cursor-jr

Command

A command for updating CursorJr's collection of official Cursor documentation. It runs synchronization, coverage checks, review, installation, and verification steps.

Rito-w/claude-code-best-practice-zh

Command Claude Code

A workflow for updating a README table of collections of ready-made coding agents. It researches repositories whose main contents are agent definition files or curated links.

regenrek/oplink-mcp

Command Cursor

Use this template to evaluate alternatives to any baseline library. Replace placeholders like , , before posting or running the search.

the-thinker0/math-skill

Command

Math Research OS entry: auto-diagnose user intent, route to thinking lenses, math knowledge base, or design translation layer.

jamditis/mooc-starter-kit

Command Claude Code

Walk a claim through the SIFT method (Stop, Investigate, Find better coverage, Trace).