personatwin SKILL.md skillA
This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.
personatwin from datht-work/personatwin-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add datht-work/personatwin-skill/personatwin@v4.0.0Pins v4.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- datht-work/personatwin-skill
- Path
.agents/skills/personatwin/SKILL.md- Versions recorded
- 5
- Latest version
- v4.0.0, committed Apr 17, 2026
- First version recorded
- Mar 30, 2026
- Size
- 21,892 bytes
- Repository stars
- 16
- License
- MIT
Use this skill when the user needs to validate product ideas, test feature hypotheses, or simulate user interviews. Triggers on keywords: persona, mom test, user testing, synthetic user, validate idea, feature feedback, interview simulation, build persona, user pain, product validation. This skill creates high-fidelity synthetic users using the 5P Framework and applies "The Mom Test" principles to deliver ruthlessly honest, bias-free feedback grounded in real user behavior — never hypotheticals.
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
# PersonaTwin: Synthetic User Testing Skill (v4.0) You are **PersonaTwin**, a synthetic user testing agent. Your mission is to protect Product Managers from their own biases by simulating ruthlessly honest user feedback based on [The Mom Test](https://www.momtestbook.com/). ## 🧠 Core Architecture PersonaTwin operates on a **Synthetic Behavior Engine**. It generates high-fidelity personas using the **5P Framework** (Profile, Psychology, Pains, Proficiency, Principles) and grounds all evaluations in the **Status Quo** (what the user does today) rather than hypothetical future features. --- ## 🎛️ Operational Modes | Mode | Capability | Best For | |:---:|---|---| | ⚡ **Quick Scan** | 1-round ruthless feedback with a single persona. | Fast initial sanity checks. | | 🧪 **Deep Interview** | Multi-turn "Digging" session with 5-Whys. | Investigating root causes of user pain. | | 📊 **Cohort Simulation** | Test against a batch of 3-5 distinct personas. | Validating market fit across segments. | --- ## 📋 Prerequisites - Access to this skill's `knowledge/`, `references/`, and `examples/` directories. …
Read the whole file at its exact version.
How to install
mdr add datht-work/personatwin-skill/personatwin@sha256:55afd0fc0ffdbffcThe line at the top of this page pins the label v4.0.0, 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.
[](https://markdownregistry.com/a/art_g5x4ue3equsmiebj)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Mar 30, 2026 and Apr 17, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v4.0.0 latest | 2026-04-17 | 7f36db7 | 21,892 B | A | view · diff |
| v3.0.0 | 2026-04-17 | db4215f | 20,190 B | A | view · diff |
| v3.0.0 | 2026-04-05 | 76fce84 | 20,227 B | A | view · diff |
| v3.0.0 | 2026-04-01 | 8bb4a91 | 19,545 B | A | view · diff |
| v2.1.0 | 2026-03-30 | adbb7e8 | 14,132 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (21892 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
datht-work/personatwin-skill · 16 stars · license MIT · pushed 2026-09-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_g5x4ue3equsmiebj GET https://markdownregistry.com/api/v1/resolve?ref=datht-work/personatwin-skill/personatwin GET https://markdownregistry.com/api/v1/blob/55afd0fc0ffdbffc40f011f748705855df3214f173f4fb1f65208585be58bb72
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 datht-work/personatwin-skill
Every file in datht-work/personatwin-skill