agentleFS
jggomezjggomez/expert-ai-developer-skills/skills/product-analyst/SKILL.md

product-analyst

Skill30 starsChanged 4 days agoApache-2.0View on GitHub

Analyzes ambiguous feature requests, clarifies business rules, and authors ultra-concise Product Requirements Documents (docs/<feature-name>/prd.md <= 70 lines) with standard User Stories (US-XX) and testable Acceptance Criteria (AC-XX).

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    SKIP: when the user prompt already defines clear scope/stories, or for bugfixes, refactors, chores, documentation updates, and purely …

    line 14
  2. Distinctive:

    If business rules or boundaries remain genuinely ambiguous, ask concise option-based questions with clear trade-offs (never vague …

    line 20
  3. Very specific:

    Create docs/<feature-name>/ and write docs/<feature-name>/prd.md (<= 70 lines hard cap) using the exact 4-section template in …

    line 23
  4. Very specific:

    Antigravity: Use view_file/grep_search, align via ask_question when needed, and write docs/<feature-name>/prd.md.

    line 39

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Product Analyst Skill

Overview

This skill converts underspecified feature requests into crisp, directly testable product specifications stored in docs/<feature-name>/prd.md (strictly capped at <= 70 lines, zero filler prose). Every PRD follows a fixed 4-section standard (Objective, Scope, User Stories, Acceptance Criteria & Edge Cases) so engineering and QA have exact US-XX -> AC-XX traceability.

When to Use

Capability-Gated Trigger Rules

  • INVOKE ONLY IF business scope, user stories, or acceptance criteria are ambiguous or missing.
  • SKIP when the user prompt already defines clear scope/stories, or for bugfixes, refactors, chores, documentation updates, and purely technical CLIs.
  • Delegate Elsewhere: System schemas & ADRs -> senior-architect-engineering; UI tokens & screens -> ui-ux-designer; TDD coding -> code-implementer.

Process

Phase 1: Context Check & Targeted Clarification

  1. Inspect existing routes, models, and docs/ (docs/specifications/ if present) to avoid asking questions already answered by the codebase.
  2. If business rules or boundaries remain genuinely ambiguous, ask concise option-based questions with clear trade-offs (never vague open-ended prompts).

Phase 2: Author Concise Standard PRD (docs/<feature-name>/prd.md, <= 70 lines)

Create docs/<feature-name>/ and write docs/<feature-name>/prd.md (<= 70 lines hard cap) using the exact 4-section template in references/prd-template.md:

  1. ## 1. Objective: 2–4 lines stating the concrete problem and measurable business outcome.
  2. ## 2. Scope: Crisp In-Scope and Out-of-Scope bullets preventing scope creep.
  3. ## 3. User Stories: Numbered US-01, US-02 in strict standard format:
    • As a <role>, I want <action>, so that <outcome> (or Como <rol>, quiero <acción>, para <beneficio>).
  4. ## 4. Acceptance Criteria & Edge Cases: Numbered AC-01, AC-02 explicitly mapped to US-XX (AC-01 (US-01)), written as directly testable Given/When/Then or crisp bullets covering validation, permissions, and boundary/failure cases.

Global Sync: If the workspace maintains docs/specifications/ or a global requirements index, update its links to keep documentation synchronized.

Usage

Example Prompts

  • "Clarify scope boundaries for workspace invitations and write a concise docs/workspace-invites/prd.md (<= 70 lines)."
  • "Extract US-XX user stories and testable AC-XX acceptance criteria for CSV report exports."

Host Execution

  • Claude Code: Inspect context via Read/Grep, clarify genuine gaps, and write docs/<feature-name>/prd.md.
  • Antigravity: Use view_file/grep_search, align via ask_question when needed, and write docs/<feature-name>/prd.md.

Red Flags

  • ❌ Writing bloated PRDs (> 70 lines), executive-summary fluff, or multi-page tables for straightforward features.
  • ❌ Invoking PRD authoring on bugfixes, refactors, chores, or prompts that already specify clear acceptance criteria.
  • ❌ Writing untestable criteria ("must be fast and intuitive") or omitting US-XX / AC-XX identifiers and Out-of-Scope bullets.
  • ❌ Asking obvious questions answerable from repository code, or writing production source code directly.

Verification

  • docs/<feature-name>/prd.md exists, is strictly <= 70 lines, and contains zero filler prose.
  • Uses the exact 4 sections from references/prd-template.md: 1. Objective, 2. Scope, 3. User Stories, 4. Acceptance Criteria & Edge Cases.
  • Every story (US-XX) uses As a / I want / so that (Como / quiero / para) format, and every AC-XX maps to a US-XX with testable validation/permission/edge rules.
  • Existing docs/specifications/ indexes synchronized if present.

References

  • Concise Standard PRD Template (<= 45 lines): references/prd-template.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.