research-agent SKILL.md skillA

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

Install it, pinned
mdr add ellmos-ai/skills/research-agent@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
ellmos-ai/skills
Path
skills/research/research-agent/SKILL.md
Versions recorded
5
Latest version
v0.2.0, committed Aug 23, 2026
First version recorded
Jul 23, 2026
Size
6,997 bytes
Repository stars
9
License
MIT

Project-first Research pipeline with live gates, source/PDF evidence, claim boundaries, compute and publication controls; includes an optional PubMed/arXiv standard-library helper.

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

<img src="banner.png" width="100%" alt="research-agent banner">

> **Deutsch** — Offizielle Deutsch-Version / Documento Oficial en Deutsch.

# Research Agent (Deutsch)

Diese Fassung ist der zentrale Paketursprung. Innerhalb von
`<OneDrive>/.TOPICS/.RESEARCH` gilt die aktuelle Projekt- und
Research-Pipeline als Autorität; der mitgelieferte PubMed/arXiv-Code ist nur
ein optionales Recherchewerkzeug.

## Verbindliche Autoritätskette

1. Aktueller Nutzerauftrag und globale `AGENTS.md`-/`GPT.md`-/`CLAUDE.md`-
   Regeln.
2. Projektlokale aktuelle Dateien, Livezustand, Locks, Entscheidungen und
   Register. Nummerierte Fortsetzungen und explizite Current-Pointer gehen
   ihren Vorläufern vor; Archive und Konfliktkopien werden nicht stillschweigend
   zur Ersatzautorität.
3. Live-Pipeline im Research-Root: insbesondere `CLAUDE.md`, `START*`,
   `MASTER*`, `POLICY*`, `PUBLIKATIONSVERFAHREN.md`, `QUALITY_RULES*`, aktuelle
   Status-/TODO-Pointer sowie `CHECKS-LOG.txt` und `CHECKS-REG.md`.
4. Dieser Skill und seine generischen Suchskripte.

Zu Beginn sind `~/.codex/GPT.md`, die beiden globalen
`CLAUDE.md`-Dateien, die Research-Regeln und die aktuellen projektlokalen
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ellmos-ai/skills/research-agent@sha256:e74f1bcd5fddbcf7

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_bmvs2nq6owoqikjs.svg)](https://markdownregistry.com/a/art_bmvs2nq6owoqikjs)

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

Versions

The registry has recorded 5 versions of this file, between Jul 23, 2026 and Aug 23, 2026, about one every 8 days.

versioncommittedcommitsizeaudit
v0.2.0 latest2026-08-23 9e49feb 6,997 BA view · diff
v0.1.02026-08-23 f025c2c 3,148 BA view · diff
v0.1.02026-07-30 08fbb89 3,129 BA view · diff
v0.1.02026-07-29 6a2d333 3,064 BA view · diff
v0.1.02026-07-23 17481b4 3,139 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 (6997 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

ellmos-ai/skills · 9 stars · license MIT · pushed 2026-11-07 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_bmvs2nq6owoqikjs
GET https://markdownregistry.com/api/v1/resolve?ref=ellmos-ai/skills/research-agent
GET https://markdownregistry.com/api/v1/blob/e74f1bcd5fddbcf7f172c542aa7b2f9923b36a747d62029ad34864fa04df30c6

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 ellmos-ai/skills

llms.txt llms.txt file
ellmos-ai/skills · llms.txt
git:20261012.88059cd · audit A · 9 stars
buero SKILL.md skill
ellmos-ai/skills · skills/assist/buero/SKILL.md · Ordnet Büroaufgaben, Korrespondenz und Fristen ohne Bindung an eine bestimmte Office-App.
v2.0.0 · audit A · 9 stars
dev SKILL.md skill
ellmos-ai/skills · skills/assist/dev/SKILL.md · Developer assistant (ATI successor). Provides a quick project overview via headless scan and routes to the available…
v0.1.0 · audit A · 9 stars
dossier-briefing SKILL.md skill
ellmos-ai/skills · skills/assist/dossier-briefing/SKILL.md · Generates a structured research briefing for a topic or person as a Markdown scaffold (stdout or file). No persistent…
v1.0.0 · audit A · 9 stars
finanz-versicherung SKILL.md skill
ellmos-ai/skills · skills/assist/finanz-versicherung/SKILL.md · Strukturiert bereitgestellte Finanz- und Versicherungsunterlagen als neutrale Übersicht und Checkliste.
v2.0.0 · audit A · 9 stars
formbuilder-reader SKILL.md skill
ellmos-ai/skills · skills/assist/formbuilder-reader/SKILL.md · Prüft bereitgestellte Formularbeschreibungen auf Struktur, Validierung, Verständlichkeit und Barrierefreiheit.
v2.0.0 · audit A · 9 stars
gesundheit SKILL.md skill
ellmos-ai/skills · skills/assist/gesundheit/SKILL.md · Ordnet freiwillig bereitgestellte Gesundheitsinformationen und bereitet Fragen für Fachpersonen vor.
v2.0.0 · audit A · 9 stars
haushalt-manager SKILL.md skill
ellmos-ai/skills · skills/assist/haushalt-manager/SKILL.md · Plant Haushaltsaufgaben, Routinen und Zuständigkeiten ohne Bindung an eine bestimmte App.
v2.0.0 · audit A · 9 stars
hauslagerist-reader SKILL.md skill
ellmos-ai/skills · skills/assist/hauslagerist-reader/SKILL.md · Analysiert bereitgestellte Bestandslisten oder Exporte ohne Bindung an ein bestimmtes Lagerprogramm.
v2.0.0 · audit A · 9 stars
kalender SKILL.md skill
ellmos-ai/skills · skills/assist/kalender/SKILL.md · Calendar skill with user-adaptive backend selection (Flag 3). Default: local SQLite store. Optional: Google Calendar…
v0.1.0 · audit A · 9 stars
kontaktbuch SKILL.md skill
ellmos-ai/skills · skills/assist/kontaktbuch/SKILL.md · Ordnet freiwillig bereitgestellte Kontaktdaten datensparsam und erkennt mögliche Dubletten.
v2.0.0 · audit A · 9 stars
location-suche SKILL.md skill
ellmos-ai/skills · skills/assist/location-suche/SKILL.md · Location, restaurant and hotel search via OpenStreetMap (Nominatim + Overpass API). Returns POIs (Points of Interest)…
v1.0.0 · audit A · 9 stars

Every file in ellmos-ai/skills

Other files named research-agent

research-agent SKILL.md skill
atmosphere/atmosphere · modules/skills/src/main/resources/META-INF/skills/research-agent/SKILL.md · Market research specialist that searches the web for market data, competitor intelligence, and industry reports, with…
git:20260505.c9625e8 · audit A · 3,830 stars
research-agent SKILL.md skill
mckruz/microsoft-agentic-harness · skills/research-agent/SKILL.md · Finds, reads, and analyzes information from project files and source code.
v1.2.0 · audit A · 18 stars
research-agent SKILL.md skill
chainlesschain/chainlesschain · desktop-app-vue/src/main/ai-engine/cowork/skills/builtin/research-agent/SKILL.md · 技术研究代理 - 搜索文档、Stack Overflow、GitHub获取技术方案,综合输出可执行建议
v1.0.0 · audit A · 11 stars

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