deep-research

SkillAI & models

Deep research harness, fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the deep-research skill

What this skill tells your AI

The instructions your AI receives, as published by justinlietz93/perfect_prompts in Prompts/System_Prompts_Leaks/Anthropic/claude-code/skills/deep-research/SKILL.md and read by ahel’s review.

Run the "deep-research" workflow.

Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.

When the user wants a deep, multi-source, fact-checked research report on any topic. BEFORE invoking, check if the question is specific enough to research directly — if underspecified (e.g., "what car to buy" without budget/use-case/region), ask 2-3 clarifying questions to narrow scope. Then pass the refined question as args, weaving the answers in.

Phases:

  • Scope: Decompose question (from args) into 5 search angles
  • Search: 5 parallel WebSearch agents, one per angle
  • Fetch: URL-dedup, fetch top 15 sources, extract falsifiable claims
  • Verify: 3-vote adversarial verification per claim (need 2/3 refutes to kill)
  • Synthesize: Merge semantic dupes, rank by confidence, cite sources

Invoke: Workflow({ name: "deep-research" })

Workflow Script

scripts/workflow-script.js

Signals

GitHub stars
23
Forks
1
Last commit
Aug 2026
Hacker News mentions
1
Advanced
Item type
skill
Key
deep-research-justinlietz93
Source
github.com/justinlietz93/perfect_prompts