ai-prd skillA
ai-prd is agent-read markdown (skill) from rizwanzafaris/product-manager-os: Write and pressure-test a PRD for an AI or agentic system. Use when a product manager is specifying a feature where the implementer is a model, not an engineer - LLM features, agents, copilots, ML-backed decisions - or when reviewing an existing PRD that says "the AI should" anywhere. Turns acceptance criteria into eval sets, makes non-determinism an explicit requirement, and treats guardrails as features with owners. For products under a financial or data regulator, routes to the regulated modu.
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
# AI PRD: write requirements a model system can actually be held to A PRD for an AI system is a different document. Your requirements are not instructions to an engineer; they are constraints on a system that will improvise. This skill restructures the document around that fact. ## Files this skill drives - [../../templates/definition/prd.md](../../templates/definition/prd.md), the base PRD template - The AI overlay in `templates/ai/`: [eval-spec.md](../../templates/ai/eval-spec.md), [guardrails.md](../../templates/ai/guardrails.md), [hallucination-controls.md](../../templates/ai/hallucination-controls.md), [human-approval-gates.md](../../templates/ai/human-approval-gates.md), [prompt-structure.md](../../templates/ai/prompt-structure.md), [context-management.md](../../templates/ai/context-management.md), [red-team-review.md](../../templates/ai/red-team-review.md), and for agentic systems [agent-architecture.md](../../templates/ai/agent-architecture.md) and [multi-agent-workflow.md](../../templates/ai/multi-agent-workflow.md) …
Read the whole file at its exact version.
How to install
mdr add rizwanzafaris/product-manager-os/ai-prd@git:20260919.72235e0mdr add rizwanzafaris/product-manager-os/ai-prd@sha256:997be44e1c8d418cPin 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.
[](https://markdownregistry.com/a/art_oym5f4dlpzdflpy3)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260919.72235e0 latest | 2026-09-19 | 72235e0 | 10,802 B | A | view · diff |
| git:20260904.53136c1 | 2026-09-04 | 53136c1 | 9,029 B | A | view · diff |
| git:20260903.fb8c390 | 2026-09-03 | fb8c390 | 7,013 B | A | view · diff |
| git:20260901.cbea862 | 2026-09-01 | cbea862 | 6,893 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 (10802 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
rizwanzafaris/product-manager-os · 4 stars · license MIT · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_oym5f4dlpzdflpy3 GET https://markdownregistry.com/api/v1/resolve?ref=rizwanzafaris/product-manager-os/ai-prd GET https://markdownregistry.com/api/v1/blob/997be44e1c8d418cec87e019aaffcaf2e5bcd451714ae3713a96afede6f64e07
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.