Agent skill

requirements-discovery

Quellcode ansehen: nickcrew/claude-cortex

#124Globales Ranking · von 124 SkillsSafe

Installation

npx skills add nickcrew/claude-cortex --skill requirements-discovery

61

Installationen

EU-hosted inference API

Power your AI agent skills with open-source models.

Drop-in OpenAI-compatible API. No data leaves Europe.

MiniMax

MiniMax M3

$0.50 / $1.90

per M tokens

Z.ai

GLM 5.3 Flash

$0.20 / $0.60

per M tokens

MoonshotAI

Kimi K3

$4.00 / $18.00

per M tokens

DeepSeek

DeepSeek V4.1 Flash

$0.40 / $1.42

per M tokens

Requirements Discovery

Systematic requirements elicitation through structured questioning, stakeholder analysis, and specification development. Transforms ambiguous project ideas into concrete, measurable specifications.

When to Use This Skill

  • Gathering requirements for a new project or feature from vague descriptions
  • Conducting stakeholder interviews to uncover needs and constraints
  • Writing or structuring a Product Requirements Document (PRD)
  • Defining project scope with clear boundaries and priorities
  • Creating user stories with well-defined acceptance criteria
  • Identifying non-functional requirements (performance, security, scalability)
  • Resolving conflicting stakeholder priorities
  • Validating requirement completeness before handing off to implementation

Quick Reference

Task Load reference
Interview patterns, PRD structure, scope definition, user story mapping skills/requirements-discovery/references/elicitation-techniques.md

Core Principles

  • Ask "why" before "how": Uncover true user needs, not assumed solutions
  • Socratic questioning: Guide discovery through questions rather than assumptions
  • Progressive refinement: Move from broad goals to specific, testable criteria
  • Stakeholder balance: Integrate diverse perspectives without letting any single voice dominate

Workflow

1. Discovery

Understand the problem space before defining solutions.

  • Identify all stakeholders and their roles
  • Conduct structured interviews with open and closed questions
  • Map user personas and their pain points
  • Capture constraints (technical, budget, timeline, regulatory)

2. Specification

Transform raw input into structured requirements.

  • Draft PRD with functional and non-functional requirements
  • Write user stories with acceptance criteria
  • Prioritize using MoSCoW or similar framework
  • Define scope boundaries (what is explicitly out of scope)

3. Validation

Verify completeness and alignment before implementation.

  • Review specifications with stakeholders
  • Confirm acceptance criteria are testable and measurable
  • Baseline success metrics and KPIs
  • Log open questions and follow-up actions
  • Prepare implementation handoff document

Common Mistakes

  • Jumping to solutions before understanding the problem
  • Treating requirements as fixed rather than iteratively refined
  • Missing non-functional requirements (performance, security, accessibility)
  • Failing to define what is out of scope
  • Writing acceptance criteria that cannot be objectively tested
  • Skipping validation with actual users or stakeholders

So verwenden Sie diesen Skill

  1. 1

    Install requirements-discovery by running npx skills add nickcrew/claude-cortex --skill requirements-discovery in your project directory. Führen Sie den obigen Installationsbefehl in Ihrem Projektverzeichnis aus. Die Skill-Datei wird von GitHub heruntergeladen und in Ihrem Projekt platziert.

  2. 2

    Keine Konfiguration erforderlich. Ihr KI-Agent (Claude Code, Cursor, Windsurf usw.) erkennt installierte Skills automatisch und nutzt sie als Kontext bei der Code-Generierung.

  3. 3

    Der Skill verbessert das Verständnis Ihres Agenten für requirements-discovery, und hilft ihm, etablierte Muster zu befolgen, häufige Fehler zu vermeiden und produktionsreifen Code zu erzeugen.

Was Sie erhalten

Skills sind Klartext-Anweisungsdateien — kein ausführbarer Code. Sie kodieren Expertenwissen über Frameworks, Sprachen oder Tools, das Ihr KI-Agent liest, um seine Ausgabe zu verbessern. Das bedeutet null Laufzeit-Overhead, keine Abhängigkeitskonflikte und volle Transparenz: Sie können jede Anweisung vor der Installation lesen und prüfen.

Kompatibilität

Dieser Skill funktioniert mit jedem KI-Coding-Agenten, der das skills.sh-Format unterstützt, einschließlich Claude Code (Anthropic), Cursor, Windsurf, Cline, Aider und anderen Tools, die projektbezogene Kontextdateien lesen. Skills sind auf Transportebene framework-agnostisch — der Inhalt bestimmt, für welche Sprache oder welches Framework er gilt.

Data sourced from the skills.sh registry and GitHub. Install counts and security audits are updated regularly.