steering-specs-generator

Generate standardized steering documents from context-aware engineering interviews.

8|Updated Nov 5, 2025

Search Tags:#documentation #patterns #interviews #steerings #team-practices #tacit-knowledge

Ready to run

npx skills add https://github.com/timurkhakhalev/cc-plugins --skill steering-specs-generator

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: steering-specs-generator
Source: https://github.com/timurkhakhalev/cc-plugins/tree/main/plugins/steerings-specs-generator/skills/steering-specs-generator
Command: npx skills add https://github.com/timurkhakhalev/cc-plugins --skill steering-specs-generator

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill conducts context-aware interviews to extract tacit engineering knowledge and generate agent-readable steerings in the standard Intent → Rules → Practices → Meta format.

Core Features & Use Cases

Interview-driven knowledge capture: Guides stakeholders through interviews to surface rules, conventions, and practices.
Output as steerings: Produces steerings that encode intent, rules, and practices for agents to follow.
Flexible topic support: Includes predefined packs and supports custom topics for team-specific conventions.

Quick Start

Start a new steering session by configuring output paths, selecting topics, and launching the interview flow as described in the skill documentation. This will generate steerings in the steerings/ directory and related backlog items as you progress.

Frequently Asked Questions about steering-specs-generator

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

FAQPage Schema

How do I extract and document tacit engineering knowledge from my team?▼

Tacit knowledge capture uses structured interviews to surface undocumented rules, conventions, and practices. This Skill guides stakeholders through context-aware interviews, extracting engineering knowledge and generating standardized steerings in Intent → Rules → Practices → Meta format that agents can follow and enforce.

What's the best way to generate steerings from codebase conventions and architecture?▼

Generate steerings by configuring output paths, defining topics, and running parallel discovery across repository context, code conventions, architecture invariants, and business domain contracts. The Skill spawns sequential pack-interview agents that produce steerings documents and backlog items in your configured directories.

Can I create custom steerings for team-specific practices and quality standards?▼

Yes. The Skill supports both predefined packs and custom topics, letting you encode team-specific conventions for quality, style, testing, security, compliance, and delivery lifecycle. Each interview generates structured steerings applicable to your codebase topology and business requirements.

How do I capture risk history and security compliance in steerings?▼

The interview workflow covers risk history, security, and compliance as built-in discovery dimensions alongside code topology and quality standards. Interview agents extract these concerns and encode them into steerings that provide context for decision-making and compliance verification.

What output does the steering generation process produce?▼

The Skill outputs steering documents in Intent → Rules → Practices → Meta format and generates corresponding backlog items. Steerings are written to a configured steerings directory and backlog items to a backlog directory, both ready for agent consumption and team reference.