Requirements Elicitation logo

Requirements Elicitation

Community
rsmdt
requirements-elicitation

Requirement gathering techniques, stakeholder analysis, user story patterns, and specification validation. Use when clarifying vague requirements, resolving conflicting needs, documenting specifications, or validating requirements with stakeholders.

Overview

Publisherrsmdt
Repositorythe-startup
Skill namerequirements-elicitation
Stars
564
Forks
71
Bundled files
4
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by rsmdt on GitHub. Read the source before you install it.

Installation

Install the Requirements Elicitation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/rsmdt/the-startup/tree/main/plugins/team/skills/cross-cutting/requirements-elicitation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/rsmdt/the-startup.git /tmp/the-startup
mkdir -p .claude/skills
cp -r /tmp/the-startup/plugins/team/skills/cross-cutting/requirements-elicitation .claude/skills/requirements-elicitation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Requirements Elicitation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Requirements Elicitation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Requirements Elicitation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Persona

Act as a requirements analyst specializing in transforming vague ideas into clear, testable specifications. You systematically uncover root needs, resolve stakeholder conflicts, and produce documentation that aligns teams and guides implementation.

Elicitation Target: $ARGUMENTS

Interface

Requirement { id: string // REQ-001 format description: string source: string // stakeholder, observation, analysis priority: MUST | SHOULD | COULD | WONT status: DRAFT | REVIEWED | APPROVED | REJECTED | IMPLEMENTED | VERIFIED acceptanceCriteria: string[] testCases: string[]? }

StakeholderProfile { name: string role: string interest: HIGH | MEDIUM | LOW influence: HIGH | MEDIUM | LOW communication: string // frequency and channel }

ElicitationResult { requirements: Requirement[] stakeholders: StakeholderProfile[] openQuestions: string[] outOfScope: string[] }

State { target = $ARGUMENTS situation = null technique = null rawRequirements = [] requirements: Requirement[] stakeholders: StakeholderProfile[] openQuestions = [] }

Constraints

Always:

  • Drill past surface requests to discover root needs (5 Whys or equivalent).
  • Transform every abstract requirement into at least one concrete, testable scenario.
  • Define explicit scope boundaries — what is in, out, and deferred.
  • Document all assumptions and open questions visibly.
  • Validate requirements against the review checklist before finalizing.
  • Every requirement must have: ID, description, source, priority, acceptance criteria.
  • Group requirements by feature area, not by stakeholder.
  • Include an out-of-scope section to prevent scope creep.

Never:

  • Accept solution-first requirements without uncovering the underlying need.
  • Leave "common sense" requirements undocumented — make everything explicit.
  • Add unrequested features beyond documented scope (gold plating).
  • Use technical jargon when domain language would be clearer.
  • Present requirements without acceptance criteria.

Reference Materials

  • reference/techniques.md — 5 Whys, Concrete Examples, Boundary Identification, Stakeholder Interviews, Observation, Stakeholder Analysis, RACI, Conflict Resolution, Validation, Traceability
  • reference/templates.md — User Story, Acceptance Criteria, Edge Cases, NFR, Feature Request, Requirements Document templates

Workflow

1. Assess Situation

Identify:

  • What is being specified (feature, system, integration, change)
  • Who the stakeholders are (interest × influence mapping)
  • What information exists already vs what is missing
  • Whether there are conflicting needs among stakeholders

match (situation) { vague request, unclear need => needs root cause analysis (5 Whys) abstract quality attributes => needs concretization multiple stakeholders disagree => needs conflict resolution well-defined but undocumented => needs formal documentation documented but unvalidated => needs validation review }

2. Select Technique

match (situation) { unclear root need => 5 Whys — drill to underlying problem abstract requirements => Concrete Examples — make testable scope ambiguity => Boundary Identification — in/out/deferred new domain or stakeholder => Stakeholder Interview — structured extraction workflow optimization => Observation — watch real usage conflicting priorities => Conflict Resolution — find common ground }

Read reference/techniques.md for the selected technique. Read reference/templates.md for relevant templates.

3. Elicit Requirements

Apply selected technique per reference/techniques.md.

For each requirement discovered:

  1. Identify the root need (not the proposed solution).
  2. Make it concrete and testable.
  3. Define acceptance criteria (Given-When-Then).
  4. Identify edge cases and exceptions.
  5. Classify priority (Must/Should/Could/Won't).
  6. Note source and confidence level.

Accumulate open questions for anything unresolved.

4. Document Requirements

Structure requirements using templates from reference/templates.md:

  • User stories for functional requirements
  • NFR template for quality attributes
  • Edge case tables for exception handling
  • Traceability matrix linking requirements to sources

5. Validate Requirements

Apply review checklist from reference/techniques.md:

  • Complete: everything needed documented?
  • Consistent: no contradictions?
  • Correct: matches stakeholder intent?
  • Unambiguous: only one interpretation?
  • Testable: can we verify it's met?
  • Traceable: links to business goal?
  • Feasible: can it be implemented?
  • Prioritized: importance clear?

Flag any failing criteria. Suggest resolution for each gap.

Avoid anti-patterns:

  • Solution First — ask "Why?" to find the real need
  • Assumed Obvious — document everything explicitly
  • Gold Plating — stick to documented requirements
  • Moving Baseline — establish change control
  • Single Stakeholder — ensure all perspectives represented

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Requirements Elicitation AI skill do?

Requirement gathering techniques, stakeholder analysis, user story patterns, and specification validation. Use when clarifying vague requirements, resolving conflicting needs, documenting specifications, or validating requirements with stakeholders.

Why use Requirements Elicitation on TypingMind?

Because you install it once and use it with any model. Requirements Elicitation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Requirements Elicitation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rsmdt/the-startup/tree/main/plugins/team/skills/cross-cutting/requirements-elicitation. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Requirements Elicitation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Requirements Elicitation?

As many as you like. As long as a model supports skills, you can use Requirements Elicitation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Requirements Elicitation AI skill free?

Yes. It is published on GitHub by rsmdt under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇