discovery

Automate interactive discovery sessions into a structured markdown document.

Updated Feb 8, 2026
One-click install
npx skills add https://github.com/Xalior/agent-skills --skill discovery-xalior
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: discovery
Source: https://github.com/Xalior/agent-skills/tree/main/discovery
Command: npx skills add https://github.com/Xalior/agent-skills --skill discovery-xalior

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Interactive requirement discovery before planning starts. Use when the user has an idea or loose requirement and wants to sharpen the goal, scope, and approach before anyone plans tasks or writes code. Produces a single markdown document that survives context reset.

Core Features & Use Cases

  • Preflight — new doc: confirm the path, derive a slug. Resume: read the existing doc in full, investigate everything it references, identify the next open question. Brownfield sweep either way: README, manifest, docs, directory tree, recent commits.
  • The Doc — create docs/discovery/discovery_<slug>.md with the skeleton.
  • Discovery conversation — section-by-section: Goal → Scope (in) → Scope (out) → Approach / Hypothesis → Open Questions. One question at a time; write the user's answer in immediately.
  • Finalise — user signals done → honest review → flip Status to Ready for Planning. Hand off to /plan.
  • Brownfield discovery: spawn sub-agents for research in parallel exactly as the main loop requires for brownfield discovery. Wait for all to complete.
  • Research rigor: verify claims, spawn sub-agents in parallel; surface context the user may not know and surface evidence in the doc.
  • Finalising: when the user signals discovery is done, review the doc honestly before accepting the call. Surface remaining vagueness and let the user decide how to address it.

Quick Start

Create a new discovery doc for your idea and follow the Goal, Scope in, Scope out, Approach, and Open Questions steps.

Frequently Asked Questions about discovery

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I shape loose ideas into a concrete discovery brief before planning starts?

To shape loose ideas into a concrete discovery brief, interactive requirement discovery automates section-by-section conversations to define your goal, scope, and approach, producing a single markdown document.

What is the best way to document project scope and open questions during early kickoff sessions?

Documenting project scope and open questions during early kickoff sessions is best handled by creating a formal discovery skeleton that captures goals, scope boundaries, approach, and open questions within a markdown file.

Can I resume requirement discovery sessions after a context reset without losing scope details?

You can resume requirement discovery after a context reset by reading the existing markdown discovery document in full, investigating its references, and identifying the next open question to continue the section-by-section loop.

How do I capture out-of-sscope boundaries and approach hypotheses for new software features?

To capture out-of-scope boundaries and approach hypotheses for new features, a discovery conversation guides you step-by-step through scope exclusions and approach formulation, immediately recording your answers into the document.

Does brownfield discovery investigate existing project files and recent git commits before defining requirements?

Brownfield discovery does investigate existing project files before defining requirements by spawning parallel sub-agents to research READMEs, manifests, directory trees, and recent commits, surfacing unknown context.

When should I not use an automated discovery process for requirement gathering?

You should not use an automated discovery process when your requirements are already fully defined, as the tool is designed to sharpen loose ideas and surface vagueness before finalizing a ready-to-plan document.