Research Stack — Security skill for Claude Code
Deep multi-source research with optional focus lenses (--focus seo,security or #tag), hunter/gatherer evidence cards, source tags and a validation gate.
How to install Research Stack
Installs to ~/.claude/skills/7alexhale5-rgb-research-stack-research-stack/SKILL.md
mkdir -p ~/.claude/skills/7alexhale5-rgb-research-stack-research-stack && curl -fsSL https://raw.githubusercontent.com/7alexhale5-rgb/research-stack/HEAD/commands/research-stack.md -o ~/.claude/skills/7alexhale5-rgb-research-stack-research-stack/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Research Stack does
description: Deep multi-source research with optional focus lenses (--focus seo,security or #tag), hunter/gatherer evidence cards, source tags and a validation gate. Usage /research-stack [--deep] [--focus tags].
Deep multi-source research with optional focus lenses. Free tools by default (web search, page fetch, Hacker News, arXiv, OSV, PageSpeed and more); paid APIs and MCPs only when configured. Every claim carries a source tag and a specific. Portable across Claude Code and
Alternatives in Security
- MCP Security Checklist (SlowMist) — Comprehensive checklist: input validation, rate limiting, RBAC, credential management, container hardening 819 ★
- CI Audit — Stack-aware CI gap detection — audits a project's GitHub Actions workflows against its declared tech stack and 117 ★
- Site Metadata — Audit and refresh the docs site's SEO/social metadata (descriptions, keywords, OG cards, JSON-LD) and verify t 76 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Agentic SEO
Claude Code skill for SEO auditing and implementation. 33-point audit, 7 JSON-LD templates, meta tags, OG, Twi
Intent Engineering
Enforce intent engineering: a Claude Code plugin with 5 review lenses (predictability, convention, simplicity,
Expectation Fit
Expectation Fit: a Claude Code plugin with 5 review lenses (predictability, convention, simplicity, experience
Global Audit
Whole-service audit via a parallel fan-out of 11 independent domain LENSES (layers, security/IDOR, state-sync,
Paper Trail Audit Sota
Audit a SOTA's bibliography. Classify each cited ref by validation state. Optional --purge removes citations t
Think Audit Reasoning
Check whether a conclusion is sound before trusting it, by sorting evidence from inference, reconstructing the
Related Agents
Laravel Nova
Use this agent when working on Laravel Nova admin panels — building or modifying Nova Resources, Fields, Actio
TAGS
Tag Vocabulary
Git Release Tagger
Use this agent when you need to create a git tag for a version of the app. Supports both post-release tags (Ap