deep-research SKILL.md skillA

deep-research from ahgraber/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add ahgraber/skills/deep-research@git:20260819.209d97b

Pins git:20260819.209d97b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
ahgraber/skills
Path
skills/deep-research/SKILL.md
Versions recorded
4
Latest version
git:20260819.209d97b, committed Aug 19, 2026
First version recorded
Jun 28, 2026
Size
12,922 bytes
Repository stars
6
License
CC0-1.0

Use when the user wants a deep, multi-source, fact-checked web research report on a topic too broad for a single search. Triggers: "deep research on X", "research report", "investigate thoroughly", "comprehensive findings on", "what's the current state of X", "survey the landscape of". Not for: single-fact lookups, library/API/version questions (use mcp-research), or open-ended ideation (use brainstorming).

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

## Overview

`deep-research` runs a recursive, multi-round web investigation.
It fans out parallel subagents breadth-first then depth-first, runs an adversarial verification valve once per round, and synthesizes by re-deriving contested claims from retained raw sources rather than from a summary chain.
The loop is a double-diamond: each round alternates **diverge** (explore/expand) with **converge** (synthesize/review), repeating until findings saturate or the user's budget runs out.

Four invariants make this safe and cheap — they are load-bearing, not optional:

1. **Raw-to-disk.**
   Every fetch is dumped verbatim to a tmpfile.
   Subagents return only `{claim, source-url, raw-pointer, self-tag}` — never raw content upward.
2. **Review re-derives from raw.**
   The verification valve checks contested/load-bearing claims against the raw tmpfiles, never against the distilled findings ledger.
3. **Review fans out by claim.**
   "Once per round" is a _cadence_, not a single monolithic pass: extract atomic claims, dispatch one skeptic per claim (or small batch).
4. **Synthesis reads artifacts; the user reads progress.**
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ahgraber/skills/deep-research@sha256:45566d14fe18a929

The line at the top of this page pins the label git:20260819.209d97b, 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_oqjvenj3urmuquko.svg)](https://markdownregistry.com/a/art_oqjvenj3urmuquko)

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

Versions

The registry has recorded 4 versions of this file, between Jun 28, 2026 and Aug 19, 2026, about one every 17 days.

versioncommittedcommitsizeaudit
git:20260819.209d97b latest2026-08-19 209d97b 12,922 BA view · diff
git:20260715.883fbe12026-07-15 883fbe1 12,718 BA view · diff
git:20260712.b9806702026-07-12 b980670 12,712 BA view · diff
git:20260628.80004ab2026-06-28 80004ab 12,507 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 (12922 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

ahgraber/skills · 6 stars · license CC0-1.0 · pushed 2026-10-29 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_oqjvenj3urmuquko
GET https://markdownregistry.com/api/v1/resolve?ref=ahgraber/skills/deep-research
GET https://markdownregistry.com/api/v1/blob/45566d14fe18a92965ec09fe5a54a6289eb6bbb9cf605f78d2edc5141d9854a3

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 ahgraber/skills

AGENTS.md AGENTS.md file
ahgraber/skills · AGENTS.md
git:20260904.70c249b · audit A · 6 stars
agent-bridge SKILL.md skill
ahgraber/skills · skills/agent-bridge/SKILL.md · Use when an agent in one harness must create, observe, or steer one or more agents in another harness through a tmux…
git:20261020.6d30bf1 · audit A · 6 stars
alt-text SKILL.md skill
ahgraber/skills · skills/alt-text/SKILL.md · Use when the user shares an image, chart, diagram, screenshot, or figure and needs it described — for alt-text…
git:20260819.209d97b · audit A · 6 stars
antislop-writing SKILL.md skill
ahgraber/skills · skills/antislop-writing/SKILL.md · Write, rewrite, or line-edit prose so it reads as a professional wrote it, not a model: clear, specific…
git:20261026.81b2043 · audit A · 6 stars
api-design SKILL.md skill
ahgraber/skills · skills/api-design/SKILL.md · Use when designing, reviewing, or planning REST or GraphQL APIs — endpoint structure, schema design, versioning, error…
git:20260819.209d97b · audit A · 6 stars
brainstorming SKILL.md skill
ahgraber/skills · skills/brainstorming/SKILL.md · Use when turning a fuzzy idea into a refined design through dialogue — across software, writing, talks, events, naming…
git:20260819.209d97b · audit A · 6 stars
changelog SKILL.md skill
ahgraber/skills · skills/changelog/SKILL.md · Use when writing, updating, or generating a CHANGELOG.md — for a new release, an unreleased section update, or drafting…
git:20260819.209d97b · audit A · 6 stars
code-review SKILL.md skill
ahgraber/skills · skills/code-review/SKILL.md · Use when reviewing code changes before committing or merging — staged diffs, branch diffs, or PR readiness checks…
git:20261027.f541fc0 · audit A · 6 stars
commit-message SKILL.md skill
ahgraber/skills · skills/commit-message/SKILL.md · Use whenever a Conventional Commit message is being drafted — whether the user asks ("write commit message", "draft…
git:20260819.209d97b · audit A · 6 stars
debugging SKILL.md skill
ahgraber/skills · skills/debugging/SKILL.md · Use when a bug, test failure, build break, regression, flaky test, or unexpected behavior appears — before proposing or…
git:20260819.209d97b · audit A · 6 stars
editorial-review SKILL.md skill
ahgraber/skills · skills/editorial-review/SKILL.md · Use when the user wants rigorous, non-sycophantic editorial feedback on a draft, essay, blog post, or argument through…
git:20260819.8c8e388 · audit A · 6 stars
formal-verification SKILL.md skill
ahgraber/skills · skills/formal-verification/SKILL.md · Use when the user asks for formal verification or formal methods: writing or checking a design model (TLA+, Alloy, P…
git:20261018.93baf35 · audit A · 6 stars

Every file in ahgraber/skills

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 · 293,827 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 · 293,827 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 · 293,827 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 · 84,762 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 · 54,716 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 · 42,430 stars
deep-research SKILL.md skill
alirezarezvani/claude-skills · .gemini/skills/deep-research/SKILL.md
git:20260717.3691fcf · audit C · 29,054 stars
deep-research SKILL.md skill
genspark-ai/genoffice · skills/recommended/deep-research/SKILL.md · Run multi-round searches with cross-checking and produce a research report with cited sources, delivered as a Word…
v1.0.0 · audit A · 11,564 stars

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