agent-prd SKILL.md skillB

agent-prd from the-utopia-studio/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add the-utopia-studio/skills/agent-prd@git:20260806.73fec06

Pins git:20260806.73fec06 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
the-utopia-studio/skills
Path
plugins/utopia-founder-productivity/skills/agent-prd/SKILL.md
Versions recorded
1
Latest version
git:20260806.73fec06, committed Aug 6, 2026
Size
53,683 bytes
Repository stars
7
License
Apache-2.0

Interview the user and produce an Agent PRD — the planning document that must exist before any agent code is written. Use when the user wants to build, scope, spec, or plan a new agent, generator, critic, pipeline stage, harness, or autonomous system; when they say "new agent", "agent PRD", "spec this agent", "plan this agent", "I want to build an agent that...", or ask what questions they should answer before starting. Also use when an existing agent is being rebuilt or a stage is being added…

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

# Agent PRD

## What this skill does

Products get a PRD before anyone writes code. Agents almost never do, which is why
they get rebuilt three times. This skill fixes that: it runs a structured interview
and produces a single markdown document — the **Agent PRD** — that defines what the
agent is, how it will be judged, how it loops, what it remembers, and what will
break it.

**The output is a document. Not code, not a scaffold, not a repo.** If the user asks
you to start implementing during the interview, finish the PRD first and say why.

The PRD exists to make three things true before the first commit:

1. Success is defined in terms something can check, not in terms of vibes.
2. The loop has a stop condition that is not just a step ceiling.
3. Nothing important lives only in a context window or only in a process that can die.

---

## Output contract

This skill produces **two** documents, in order:

1. `<agent-slug>-PRD.md` — what the agent is and how it will be judged. Always.
2. `<agent-slug>-WORKORDERS.md` — how it gets built, as sequenced tasks with
   acceptance tests. Only after the PRD clears its hard gates.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add the-utopia-studio/skills/agent-prd@sha256:4bcc26fcb2015489

The line at the top of this page pins the label git:20260806.73fec06, 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_62vufjnu7iiuzeme.svg)](https://markdownregistry.com/a/art_62vufjnu7iiuzeme)

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

Versions

The registry has recorded 1 version of this file, committed on Aug 6, 2026.

versioncommittedcommitsizeaudit
git:20260806.73fec06 latest2026-08-06 73fec06 53,683 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No script tag (matched: <script)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (53683 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

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

the-utopia-studio/skills · 7 stars · license Apache-2.0 · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_62vufjnu7iiuzeme
GET https://markdownregistry.com/api/v1/resolve?ref=the-utopia-studio/skills/agent-prd
GET https://markdownregistry.com/api/v1/blob/4bcc26fcb2015489fc4c44cdd524668fb057b96e87869c903aae1c78a3b9581e

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 the-utopia-studio/skills

ceramic-design-system Cursor rule
the-utopia-studio/skills · .cursor/rules/ceramic-design-system.mdc · Ceramic Design System rules
git:20260806.119ea10 · audit A · 7 stars
AGENTS.md AGENTS.md file
the-utopia-studio/skills · AGENTS.md
git:20260826.edc6b9f · audit A · 7 stars
CLAUDE.md CLAUDE.md file
the-utopia-studio/skills · CLAUDE.md
git:20260806.119ea10 · audit A · 7 stars
AGENTS.md@agents/ada AGENTS.md file
the-utopia-studio/skills · agents/ada/AGENTS.md
git:20260806.73fec06 · audit A · 7 stars
AGENTS.md@agents/khalil AGENTS.md file
the-utopia-studio/skills · agents/khalil/AGENTS.md
git:20260806.73fec06 · audit A · 7 stars
AGENTS.md@agents/salim AGENTS.md file
the-utopia-studio/skills · agents/salim/AGENTS.md
git:20260806.73fec06 · audit A · 7 stars
agent-persona-builder SKILL.md skill
the-utopia-studio/skills · plugins/utopia-founder-productivity/skills/agent-persona-builder/SKILL.md · Design persistent AI agent personas with distinct voices, durable memory, and clear operating rules. Use when the user…
git:20260806.73fec06 · audit A · 7 stars
alignment-values-north-star SKILL.md skill
the-utopia-studio/skills · plugins/utopia-founder-productivity/skills/alignment-values-north-star/SKILL.md · Creates actionable alignment frameworks that give teams a shared North Star (direction), values (guardrails), and…
git:20260806.73fec06 · audit A · 7 stars
defuddle SKILL.md skill
the-utopia-studio/skills · plugins/utopia-founder-productivity/skills/defuddle/SKILL.md · Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use…
git:20260806.73fec06 · audit A · 7 stars
draft-nda SKILL.md skill
the-utopia-studio/skills · plugins/utopia-founder-productivity/skills/draft-nda/SKILL.md · Draft a detailed Non-Disclosure Agreement between two parties covering information types, jurisdiction, and clauses…
git:20260806.73fec06 · audit A · 7 stars
executive-onboarding-playbook SKILL.md skill
the-utopia-studio/skills · plugins/utopia-founder-productivity/skills/executive-onboarding-playbook/SKILL.md · Plan a VP or CPO 30-60-90 day diagnostic onboarding path. Use when entering a new executive product role and avoiding…
git:20260806.73fec06 · audit A · 7 stars
find-skills SKILL.md skill
the-utopia-studio/skills · plugins/utopia-founder-productivity/skills/find-skills/SKILL.md · Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is…
git:20260806.73fec06 · audit A · 7 stars

Every file in the-utopia-studio/skills

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