deep-research SKILL.md skillA

deep-research from jgwill/miadi-orchestration-kit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jgwill/miadi-orchestration-kit/deep-research@v0.2.0

Pins v0.2.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jgwill/miadi-orchestration-kit
Path
skills/deep-search/SKILL.md
Versions recorded
1
Latest version
v0.2.0, committed Apr 26, 2026
Size
12,508 bytes
Repository stars
5
License
none declared

This skill should be used when the user asks for "deep research", "thorough research", "research everything about", "cover every angle", "comprehensive research on", "spawn research agents", "/deep-research", or wants multi-agent parallel research on any topic. Also triggers when user says "research this for me", "find everything about", "I need a research doc on", or describes needing exhaustive coverage of a subject. NOT for quick lookups or single questions — this is for producing…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Deep Research

Multi-agent parallel research orchestrator. Decomposes any research topic into 3-6 specialized angles using MECE principles, spawns Opus sub-agents to cover each angle simultaneously, runs gap analysis, then synthesizes findings into one comprehensive vault document.

Anthropic's own multi-agent research system outperforms single-agent by **90.2%**. This skill applies those same proven patterns.

For detailed sub-agent prompt templates by research type: read `references/agent-templates.md`.
For the full research on multi-agent orchestration patterns: read `references/orchestration-patterns.md`.

## Who This Is For

Olle Dyberg — AI content creator and consultant (@olleai on TikTok, ~9K followers, 1.1M+ views) building around Claude Code, AI agents, and context engineering. Research serves: content creation, meta-prompts, consulting prep, and product development.

## The Research Diamond

Every research session follows this shape:

```
         [Broad: Decompose question]
              /        \
    [Narrow: 3-5 parallel agents]     ← Wave 1
              \        /
         [Evaluate: Gap analysis]
              /        \
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jgwill/miadi-orchestration-kit/deep-research@sha256:024668236db50bf4

The line at the top of this page pins the label v0.2.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7ttkhr67pomvstgg.svg)](https://markdownregistry.com/a/art_7ttkhr67pomvstgg)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Apr 26, 2026.

versioncommittedcommitsizeaudit
v0.2.0 latest2026-04-26 ac1bfa0 12,508 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (12508 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

jgwill/miadi-orchestration-kit · 5 stars · license none declared · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7ttkhr67pomvstgg
GET https://markdownregistry.com/api/v1/resolve?ref=jgwill/miadi-orchestration-kit/deep-research
GET https://markdownregistry.com/api/v1/blob/024668236db50bf49ce305780e2363d0eb0682e7f0230bcedc9aeb5a978c2c8a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from jgwill/miadi-orchestration-kit

AGENTS.md AGENTS.md file
jgwill/miadi-orchestration-kit · AGENTS.md
git:20260905.7457baf · audit A · 5 stars
AGENTS.md@antigravity AGENTS.md file
jgwill/miadi-orchestration-kit · antigravity/AGENTS.md
git:20260607.e22b11e · audit A · 5 stars
AGENTS.md@claude AGENTS.md file
jgwill/miadi-orchestration-kit · claude/AGENTS.md
git:20261018.428e9dc · audit A · 5 stars
ava-companion SKILL.md skill
jgwill/miadi-orchestration-kit · claude/ava-companion/skills/ava-companion/SKILL.md · Be Ava, Guillaume's companion, in a Claude Code session, in an episode or not. Use when /ava is run, when Guillaume…
git:20261006.d525fcb · audit B · 5 stars
mia-episode-companion SKILL.md skill
jgwill/miadi-orchestration-kit · claude/mia-episode-companion/skills/mia-episode-companion/SKILL.md · Be Mia, William's development companion, in a Claude Code seat bound to one Chronicle episode. Use when a mia-listen…
git:20261020.10db0ba · audit B · 5 stars
screenwalk-notebook SKILL.md skill
jgwill/miadi-orchestration-kit · claude/miadi-deepdiver/skills/screenwalk-notebook/SKILL.md · Turn Miadi reviews and their screenwalk videos into a Gemini Notebook, ask it the episode's questions, generate and…
git:20261020.caa57ce · audit A · 5 stars
operator-desk SKILL.md skill
jgwill/miadi-orchestration-kit · claude/miadi-operator-desk/skills/operator-desk/SKILL.md · Answer William's questions about how the Miadi Factory works (a tool's commands, tmux and other multiplexers, which…
git:20261007.d6f124d · audit A · 5 stars
miadi-pi-network SKILL.md skill
jgwill/miadi-orchestration-kit · claude/miadi-pi-network/skills/miadi-pi-network/SKILL.md · Work with the Miadi Pi Network hub from a Claude Code session — join as a peer, list peers, send a prompt to another…
git:20260906.a175fb2 · audit B · 5 stars
AGENTS.md@claude/miadi-session-issue AGENTS.md file
jgwill/miadi-orchestration-kit · claude/miadi-session-issue/AGENTS.md
git:20261019.b144a52 · audit A · 5 stars
AGENTS.md@claude/miadi-session-observability AGENTS.md file
jgwill/miadi-orchestration-kit · claude/miadi-session-observability/AGENTS.md
git:20261021.ca1ff8d · audit A · 5 stars
session-continuity SKILL.md skill
jgwill/miadi-orchestration-kit · claude/miadi-session-observability/skills/session-continuity/SKILL.md · T1's practice: after a reboot or an exit, every terminal still knows which agent session it held, and the agents come…
v1.1.0 · audit A · 5 stars
session-fork SKILL.md skill
jgwill/miadi-orchestration-kit · claude/miadi-session-observability/skills/session-fork/SKILL.md · Branch a Claude Code session without touching it. Ask a branch of another session a question with every tool disabled…
git:20261008.7c09d63 · audit A · 5 stars

Every file in jgwill/miadi-orchestration-kit

Other files named deep-research

deep-research SKILL.md skill
affaan-m/ecc · docs/ja-JP/skills/deep-research/SKILL.md · コンテキスト深い研究を実施し、複雑なテーマについての権威ある答えを生成します。複数のソースをキュレート、相互参照、合成してコンテキスト内の完全な画像を構築します。
git:20260517.ec9ace9 · audit A · 284,510 stars
deep-research SKILL.md skill
affaan-m/ecc · .agents/skills/deep-research/SKILL.md · Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited…
git:20260918.c752aac · audit A · 284,510 stars
deep-research SKILL.md skill
affaan-m/ecc · .kiro/skills/deep-research/SKILL.md · Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited…
git:20260607.4ad5756 · audit A · 284,510 stars
deep-research SKILL.md skill
bytedance/deer-flow · skills/public/deep-research/SKILL.md · Use this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like "what is X"…
git:20260303.7de9439 · audit A · 84,193 stars
deep-research SKILL.md skill
imbad0202/academic-research-skills · deep-research/SKILL.md · Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full…
v2.12.1 · audit A · 53,066 stars
deep-research SKILL.md skill
thu-maic/openmaic · skills/agent-runtime/deep-research/SKILL.md · Courses whose content rests on current, external or real-world facts that must be verified against live sources before…
git:20260827.0462157 · audit A · 41,208 stars
deep-research SKILL.md skill
alirezarezvani/claude-skills · .gemini/skills/deep-research/SKILL.md
git:20260717.3691fcf · audit C · 28,445 stars
deep-research SKILL.md skill
davidondrej/skills · skills/research-and-web/deep-research/SKILL.md · Run deep research through DeepAPI and save a report with sources. Use when asked for deep research, DeepAPI research…
git:20261018.eaed515 · audit A · 4,161 stars

Browse by kind, by grade A, or by owner.