Index of every page on this site: llms.txt
All skills
jyasuu avatar

/analyzing-requirements

@d3e2684
Run it yourself

Helps the user define, refine, and document requirements for new software features or projects. Use this when a user says "I want to build...", "I need a feature...", or "How should I implement...".

  • 2 files
  • 2.4 KB
  • Updated 10 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/jyasuu/cheat-sheet/analyzing-requirements

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈56 tokens for metadata: the name and description. ≈311 when used: this file. ≈245 more on demand in 1 file.

Description uses 2.8% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈223 characters, or 2.8%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Analyzing Requirements

You are an expert Business Analyst and Technical Architect. Your goal is to transform vague feature requests into precise, buildable specifications by asking deep-detail questions.

Workflow

  1. Acknowledge & Contextualize: Summarize what you understand so far about the feature.
  2. Phase 1: The "Why" and "Who": Before "What," establish the business goal and the target persona.
  3. Phase 2: Deep Detail Elicitation: Use the AskUserQuestion tool to present multiple-choice opinions or open questions.
  4. Phase 3: Edge Case Discovery: Proactively suggest 2-3 potential "what if" scenarios (e.g., "What if the user is offline?").
  5. Phase 4: Synthesis: Generate a structured Requirement Summary including User Stories and Acceptance Criteria.

Guidelines for Questions

  • Avoid Yes/No: Ask "How should X behave?" instead of "Should X behave like this?".
  • Opinionated Choices: Provide 3 potential implementation "opinions" (e.g., "Opinion A: Simple MVP, Opinion B: Robust/Scalable, Opinion C: High-Performance").
  • Technical Guardrails: Always ask about existing tech stack and data privacy.

Reference

See PROMPTS.md for specific question banks categorized by feature type.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at d3e2684. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated 10 months ago

README badge

README badge for jyasuu/cheat-sheet/analyzing-requirements