AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
hint-shu avatar

hint-shu

8 listings · 0 installs

Open-source publisher. Listings imported from github.com/hint-shu — credited to the original author with their license.

↗ github.com/hint-shu
8 results
Self-run
SKILL

Deep Research

Advanced deep research (L2) — runs /research (L1) first, then adds reflection loop, contradiction detection, and tree depth 2 for follow-up questions. ~12 min, 20-30 sources, ~2000 word report. Use for serious questions, technology choices, non-trivial investigations.

0
26
Free
Self-run
SKILL

Expert Research

Expert-level research (L3) — runs /deep-research (L2) then adds critic agent, fact-checking pass, multi-perspective search, and human-in-the-loop plan approval. ~20 min, 40-60 sources, 3000+ word report with executive summary. Use for strategic decisions, technology migrations, important investigations.

0
19
Free
Self-run
SKILL

Osint Research

OSINT recon skill — passive entity discovery for domain / IP / email / person / company / github user. Builds a hybrid findings/dossier/graph report from free public sources (Whois, DNS, crt.sh, Wayback, Shodan InternetDB, GitHub code search, Tavily/Firecrawl/Exa/Perplexity dorks, optional theHarvester/subfinder). No subscription dependencies. Disclaimer is non-removable; secrets are redacted; bl…

0
39
Free
Self-run
MCP

Deep Research

Claude Code research ladder: 6 composable skills (L0→L5) from 10s fact-check to 1h knowledge vault, plus /osint-research for entity recon. Stack: Firecrawl (search+scrape+summary) + Tavily (search + research with structured schema verdicts) + Exa (neural) + optional Codex CLI cross-model. MIT.

0
35
Free
Self-run
SKILL

Ultra Research

Ultra research (L5) — maximum depth. Runs /academic-research (L4) then adds peer-review simulation, recursive exploration until knowledge saturation, full agent crew (7+), and builds a complete knowledge base with executive summary, glossary, timeline, playbooks, counter-arguments, and open questions. 1+ hour, 150+ sources, 10000+ word main report + full vault structure. Auto-syncs to auto-memory…

0
25
Free
Self-run
SKILL

Research

Standard deep research (L1) with planner decomposition and per-source summarization. ~5 min, 10-15 sources, structured ~1000 word report. Default choice for "расскажи про X", "как работает Y", "что нового в Z". Use this when /quick-research is too shallow and /deep-research is overkill.

0
28
Free
Self-run
SKILL

Academic Research

Academic-grade research (L4) — runs /expert-research (L3) then adds academic sources (arXiv, Google Scholar), full multi-agent crew (Planner + 2x Researchers + Critic + Editor), timeline analysis, methodology section, and annotated bibliography with source quality ratings. ~40 min, 80-120 sources, 5000+ word report. Use for scientific overviews, research-grade investigations.

0
24
Free
Self-run
SKILL

Quick Research

Quick web research for simple questions — fast answer with 3-5 cited sources in ~1 minute. Use for fact-checks, simple lookups, "what is X", "latest version of Y", "who made Z". For anything deeper, use /research (L1) or /deep-research (L2).

0
30
Free
You've reached the end · 8 loaded