sdd-explore

Investigates codebases and returns structured exploration analysis for proposed changes.

Updated Apr 10, 2026
One-click install
npx skills add https://github.com/Balthael/ciberbal-ai --skill sdd-explore-balthael
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sdd-explore
Source: https://github.com/Balthael/ciberbal-ai/tree/main/internal/assets/skills/sdd-explore
Command: npx skills add https://github.com/Balthael/ciberbal-ai --skill sdd-explore-balthael

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Before committing to a code change, teams need to understand the current architecture, affected files, and trade-offs between approaches. This Skill performs that investigation as a dedicated exploration sub-agent and returns a structured analysis instead of ad-hoc notes. ## Core Features & Use Cases - Codebase Investigation: Reads entry points, related functionality, tests, and dependencies to map current behavior and affected files. - Approach Comparison: Compares multiple implementation options with pros, cons, and effort estimates in a consistent table format. - Artifact Persistence: Saves exploration results to Engram, OpenSpec, hybrid, or prompt-only modes depending on the configured artifact store. - Use Case: An orchestrator receives a feature request, launches this Skill to investigate the codebase, and gets back a structured report with affected files, approach options, risks, and a recommendation ready for the proposal phase. ## Quick Start Ask the orchestrator to explore how a proposed feature would affect the codebase and return a structured analysis with recommended approaches.

Frequently Asked Questions about sdd-explore

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

FAQPage Schema
How do I explore a codebase before making a change?

Launch this Skill through the orchestrator with a topic or feature to investigate. It reads relevant code, identifies affected files, compares approaches, and returns a structured analysis with a recommendation and risks.

What does the exploration report include?

The report contains current state, affected files with reasons, compared approaches with pros, cons, and effort estimates, a recommendation, risks, and a readiness verdict for the proposal phase.

Which artifact storage modes are supported?

Four modes are supported: engram persists to a topic key like sdd/{change-name}/explore, openspec follows the OpenSpec convention, hybrid writes to both, and none returns the result only in the prompt.

Can this Skill modify code during exploration?

No. The Skill is read-only by design and may only create an exploration.md file inside the change folder when a change name is provided. It never modifies existing code or files.

What happens if the exploration request is too vague?

The Skill states clearly what clarification is needed instead of guessing. It always reads real code and reports when insufficient information is available to complete the analysis.