research-toolkit skillA

research-toolkit is agent-read markdown (skill) from rrrrrredy/research-toolkit: Source-backed longform research framework for AI agents. Use for substantial industry/market/company/product/tech/policy/ecosystem reports, 中文产业/行业研究、市场分析、竞品分析、投资memo. Guides scope, sources, claims, depth, review, hard stops, and publishable prose; not quick facts/summaries..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Research Toolkit

[English](SKILL.md) | [简体中文](SKILL.zh-CN.md)

Produce the research deliverable the user requested. Use this entry point throughout the task; load the relevant methods at the stages below. The [research standard](references/research-standard.md) retains the complete rules, state contract, examples, and failure guidance. Paths in commands and code spans are relative to the installed toolkit or the research task, as indicated.

## Establish the research brief

Before collecting sources, read [research workflow](references/research-workflow.md) and check the existing conversation and materials for:

- The research question, scope, target reader, and intended decision or use.
- Output format and language, depth or length, required questions, and exclusions.
- Time and geography, required materials, evidence standard, and any deadline.

Ask one compact batch about missing information that would change the research. There is no question quota. Offer concrete choices when useful; do not require the user to write a specification or repeat supplied information. Ask about missing depth or length when it cannot be inferred from the requested output.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add rrrrrredy/research-toolkit/research-toolkit@git:20260923.e03c575
Exact content
mdr add rrrrrredy/research-toolkit/research-toolkit@sha256:a63f3035f261b781

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_4v3urlrrezxgr6z6.svg)](https://markdownregistry.com/a/art_4v3urlrrezxgr6z6)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260923.e03c575 latest2026-09-23 e03c575 9,430 BA view · diff
git:20260921.146ccf92026-09-21 146ccf9 29,802 BA view · diff
git:20260921.7cff6372026-09-21 7cff637 29,748 BA view · diff
git:20260914.6b54d622026-09-14 6b54d62 26,280 BA view · diff
git:20260910.12a53242026-09-10 12a5324 25,703 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (9430 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

rrrrrredy/research-toolkit · 12 stars · license MIT · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4v3urlrrezxgr6z6
GET https://markdownregistry.com/api/v1/resolve?ref=rrrrrredy/research-toolkit/research-toolkit
GET https://markdownregistry.com/api/v1/blob/a63f3035f261b78105136a2fd61ff6dd02e9cf158fdb76ddace991be2640c1b0

Your agent 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.

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