Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Requirements Elicitation

ASecurity

Facilitate structured requirements gathering. Use when the user says "gather requirements", "elicitation session", "stakeholder interview", "requirements workshop", "what do the users need", "discover requirements", "trawl for requirements", "understand the business need", "conduct interviews", or needs to systematically extract requirements from stakeholders - even if they don't explicitly say "elicitation".

20 stars
0 votes
0 copies
0 views
Added 10/4/2026
ai-agentsgoaws

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 10/4/2026

$npx -y skills add qa-aman/claude-skills --skill requirements-elicitation --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Requirements Elicitation?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Requirements Elicitation
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/qa-aman-requirements-elicitation/badge)](https://www.skillsdirectory.com/skills/qa-aman-requirements-elicitation)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: requirements-elicitation
description: >
  Facilitate structured requirements gathering. Use when the user says "gather requirements",
  "elicitation session", "stakeholder interview", "requirements workshop", "what do the users need",
  "discover requirements", "trawl for requirements", "understand the business need",
  "conduct interviews", or needs to systematically extract requirements from stakeholders -
  even if they don't explicitly say "elicitation".
---

## Reference Files

- `references/elicitation-techniques.md` - Lookup table of 15+ elicitation techniques with when to use, participants, output format, and time needed. Read this in Step 2 when selecting techniques and in Step 3 when planning sessions.

## Overview

Based on the **BABOK Guide v3 (IIBA)** - Elicitation & Collaboration knowledge area, which defines 50 standardized techniques across 6 knowledge areas. Also draws on **Mastering the Requirements Process** by Suzanne & James Robertson for the Volere "trawling" approach - their term for iterative elicitation driven by business events, not document templates. The key insight: elicitation is not a phase you complete; it is a continuous activity that starts with business events and stakeholders, not with a blank requirements template.

## Workflow

### Step 1: Identify stakeholders and business events
List every person, role, and adjacent system that touches the problem space. Use the BABOK's stakeholder categories: customer, end user, sponsor, domain expert, regulator, implementation team. Then list the business events that trigger the process or system under analysis - Robertson's Business Event List is the elicitation backbone.

### Step 2: Select elicitation techniques
Match techniques to stakeholder type and information need (see `references/elicitation-techniques.md`). Use a mix:
- **Interviews** for deep individual knowledge
- **Workshops** for cross-functional alignment and conflict surfacing
- **Observation/Apprenticing** (Robertson) for tacit knowledge users cannot articulate
- **Document Analysis** for existing rules, policies, and constraints
- **Prototyping** for validating understanding with users

### Step 3: Plan and schedule sessions
For each session, define:
```
SESSION: [type - interview / workshop / observation]
STAKEHOLDER(S): [names and roles]
OBJECTIVE: [what you need to learn]
TECHNIQUE: [from reference table]
DURATION: [estimated time]
PREPARATION: [materials, context docs, pre-reads]
```

### Step 4: Conduct elicitation
During sessions:
- Start with open-ended context questions ("Walk me through how you do X today")
- Progress to specific probes ("What happens when Y fails?")
- Capture requirements using Robertson's Volere Snow Card format: requirement number, type, description, rationale, source, fit criterion
- Note assumptions, constraints, and conflicts separately
- Record who said what - source traceability starts here

### Step 5: Confirm and validate
After each session:
- Write up findings within 24 hours
- Send back to stakeholders for confirmation (BABOK's "confirm elicitation results")
- Flag conflicts between stakeholders - do not resolve silently
- Identify gaps that need follow-up sessions

### Step 6: Organize and classify requirements
Classify using BABOK's hierarchy:
- **Business requirements** - why the organization needs this
- **Stakeholder requirements** - what users need to do
- **Solution requirements** - functional + non-functional
- **Transition requirements** - what's needed to move from current to future state

## Anti-Patterns

**1. Template-first elicitation**
Bad: Sending a requirements template to stakeholders and asking them to fill it in.
Good: Conduct interviews and workshops first, then organize findings into a structured format.

**2. Single-technique reliance**
Bad: Only conducting interviews, missing tacit knowledge that observation would reveal.
Good: Use at least 3 techniques per project - interviews for depth, workshops for alignment, observation for reality.

**3. Eliciting solutions instead of needs**
Bad: "The user wants a dropdown menu." (That's a solution.)
Good: "The user needs to select from a constrained set of valid values." (That's a requirement.)

**4. No source traceability**
Bad: Requirements listed without noting who requested them or why.
Good: Every requirement links back to a stakeholder, business event, or document source.

**5. One-pass elicitation**
Bad: Running a single round of interviews and declaring requirements "complete."
Good: Iterative trawling - each round reveals gaps that drive the next round.

## Quality Checklist

- [ ] All stakeholder categories identified (users, sponsors, domain experts, regulators)
- [ ] Business events listed as elicitation drivers
- [ ] At least 3 elicitation techniques selected
- [ ] Each session has a defined objective and preparation
- [ ] Requirements captured with source attribution
- [ ] Findings confirmed with stakeholders
- [ ] Conflicts between stakeholders flagged (not silently resolved)
- [ ] Requirements classified by BABOK hierarchy
- [ ] Gaps identified with follow-up sessions planned

Attribution

qa-amanqa-aman
View sourceSee grades on GitHubMore from qa-aman →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →