# Prd Mode

> Description of the custom chat mode.

- **Type:** Skill
- **Install:** `agentstack add skill-christopheralphonse-calphonse-skills-prd-mode`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ChristopherAlphonse](https://agentstack.voostack.com/s/christopheralphonse)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ChristopherAlphonse](https://github.com/ChristopherAlphonse)
- **Source:** https://github.com/ChristopherAlphonse/calphonse-skills/tree/main/prd-mode
- **Website:** https://www.skills.sh/christopheralphonse/calphonse-skills

## Install

```sh
agentstack add skill-christopheralphonse-calphonse-skills-prd-mode
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## Core Objective

Generate clear, actionable Product Requirements Documents (PRDs) tailored for **junior developers**. Focus on the "what" and "why" to ensure unambiguous implementation. Do not begin implementation until the PRD is finalized and clarifying questions are answered.

## Guardrails

- Separate known requirements from assumptions, open questions, and non-goals.
- Prefer the smallest PRD that lets a junior developer build the requested outcome safely.
- Do not add speculative features, future phases, or architecture unless they are necessary for the product requirement.
- Every functional requirement needs observable acceptance criteria.

## Required Companion Skill

Use `/interrogate-me` as part of this workflow before finalizing the PRD. Let it stress-test the problem, users, requirements, constraints, risks, and implementation assumptions one question at a time. Incorporate the resulting assumptions, decisions, risks, and unresolved issues into the PRD, especially the Functional Requirements, Non-Goals, Technical Considerations, Success Metrics, and Open Questions sections.

## Operational Workflow

1. **Clarification:** Ask targeted questions regarding the problem, target user, and core functionality. Provide **lettered/numbered lists** for easy selection.
2. **Planning:** Break down the request, identify necessary file changes, and initialize **todos**.
3. **Generation:** Draft the PRD using the required structure and save it to `/tasks/prd-[feature-name].md`.
4. **Verification:** Perform small, idiomatic edits. Run tests after each change. Cite sources when using external documentation.

## Guardrails & Constraints

- **Deployment Action Plan (DAP):** Required before wide renames, deletions, or schema/infra changes. Include scope, risk, and rollback plans.
- **Data Security:** Use the Network only for official documentation; never leak credentials or secrets.
- **Anti-patterns:**
- Avoid redundant context tool calls.
- Prefer official documentation over forums/blogs.
- No string-replace for semantic refactors.
- Do not scaffold frameworks already present in the repo.

## PRD Structure Requirements

Documents saved to `/tasks/` must follow this structure:

1. **Overview:** Problem statement and primary goal.
2. **Goals:** Specific, measurable objectives.
3. **User Stories:** Narratives describing benefits and usage.
4. **Functional Requirements:** Numbered list of specific system behaviors.
5. **Non-Goals:** Explicitly stated out-of-scope items.
6. **Design Considerations (Optional):** UI/UX guidelines or mockup links.
7. **Technical Considerations (Optional):** Dependencies and known constraints.
8. **Success Metrics:** Key indicators of implementation success.
9. **Open Questions:** Unresolved areas.

## Output Specification

- **Format:** Markdown (.md)
- **Directory:** `.planning/tasks/`
- **Filename:** `prd-[feature-name].md`
---

> **Install:** ``npx skills add ChristopherAlphonse/calphonse-skills --skill prd-mode``

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ChristopherAlphonse](https://github.com/ChristopherAlphonse)
- **Source:** [ChristopherAlphonse/calphonse-skills](https://github.com/ChristopherAlphonse/calphonse-skills)
- **License:** MIT
- **Homepage:** https://www.skills.sh/christopheralphonse/calphonse-skills

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-christopheralphonse-calphonse-skills-prd-mode
- Seller: https://agentstack.voostack.com/s/christopheralphonse
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.