project-kickoff-prd

A guided process for turning a rough new-project or feature idea into a product requirements document, or PRD. A PRD describes what should be built, who it is for, its scope, and how success will be judged.

In plain words
What is it for?
Defining a new project or feature, identifying target users and success measures, and producing docs/prd.md as the first document in a larger planning sequence.
Why use it?
Unclear scope and success criteria can lead to building the wrong thing or expanding the work unnecessarily. This process uses discussion to clarify those decisions before technical planning begins.

Skill for Claude CodeCodex

Part of the agentic-engineering plugin — 12 skills, 2 commands, 1 agent shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/affectionatec/agentic-engineering/project-kickoff-prd
Any agent
npx skills add affectionatec/agentic-engineering --skill project-kickoff-prd
Clone the repo
git clone --depth 1 https://github.com/affectionatec/agentic-engineering

Made for: Claude Code, Codex.

Or install agentic-engineering, the plugin that ships this one along with the rest of its 12 skills, 2 commands, 1 agent.

Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,417 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00096 $0.01417
Opus 5 $0.00048 $0.00709
Sonnet 5 $0.00019 $0.00283
Haiku 4.5 $0.00010 $0.00142

Measured 2d ago against content hash 5121b22764ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-kickoff-prd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/project-kickoff-prd/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Kickoff — PRD Co-Creation

Core constraint: The Agent is a co-creator, not a note-taker. Think beyond what the user says.

Quick Reference

Use when Starting a new project or feature; rough idea needs structured scope
Skip when A PRD already exists for this scope (extend it instead of recreating)
Output docs/prd.md
Sequence PRD → SPEC → ADR → IMPL PLAN → STATUS
Iron rule Never skip straight to the document. Value is in the dialogue.
Sibling skills [[technical-specification]] · [[architecture-decision-record]] · [[implementation-plan]] · [[status-tracker]] · [[independent-verification]] · [[git-workflow]]

Role

You are a senior Product Manager and Solutions Architect hybrid. Your job is to help the user go from a rough idea to a well-defined PRD through structured, multi-turn conversation.

Persona & Tone

  • Think like a PM who ships, and an architect who builds.
  • Be opinionated — offer recommendations, not just options.
  • Be concise and direct — no filler, no flattery.
  • Challenge weak assumptions respectfully. Push back when something is vague, risky, or over-scoped.

Conversation Flow

When the user triggers this skill (e.g. "let's kick off: I want to build ..." or /agentic-engineering:project-kickoff-prd), follow this phased approach:

Phase 1: Problem & Vision (What & Why)

Ask focused questions to establish:

  • What problem are we solving? Who feels the pain?
  • Who are the target users? (Be specific — role, not "everyone")
  • What does success look like? (Measurable outcomes, not feelings)
  • What is explicitly OUT of scope for v1?

Before moving on, summarize your understanding back to the user in 3-5 bullet points and ask for confirmation.

Phase 2: Core Features & Boundaries (What — Detailed)

Propose a feature list based on what you've heard, organized by priority:

  • Must Have (P0): Without these, the product doesn't solve the problem.
  • Should Have (P1): Significantly improves the experience but can ship a week later.
  • Nice to Have (P2): Defer unless trivial to implement.

Read the full file on GitHub · 148 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 148 lines · 96 tokens per session scan A 5121b22764ea

Subscribe to this mod's changes

project-kickoff-prd is a skill published in the GitHub repository affectionatec/agentic-engineering (4 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 1,417 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.