assess-findings

Render codebase assessment reports from deterministic run-context data and layer-specific scorecards.

30|5|Updated Jan 13, 2026
One-click install
npx skills add https://github.com/bjcoombs/ai-native-toolkit --skill assess-findings
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: assess-findings
Source: https://github.com/bjcoombs/ai-native-toolkit/tree/main/skills/assess-findings
Command: npx skills add https://github.com/bjcoombs/ai-native-toolkit --skill assess-findings

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the inconsistency of AI-generated reports by separating deterministic data gathering from prose generation, ensuring that codebase assessments are reproducible, objective, and actionable.

Core Features & Use Cases

  • Deterministic Reporting: Assembles complex data from the assess-engine into a standardized, high-integrity report format.
  • Cross-Layer Analysis: Surfaces critical findings like hidden coupling, lying maps, and complexity hotspots that are invisible to single-axis scans.
  • Use Case: Use this after running the assess-engine to generate a professional-grade readiness report that highlights the top three technical debt priorities for your engineering team.

Quick Start

Trigger the assess-findings skill to assemble the final report once the deterministic orchestrator has completed the data collection phase.

Frequently Asked Questions about assess-findings

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

FAQPage Schema
How do I generate reproducible codebase assessment reports?

Reproducible codebase assessment reports are generated by synthesizing deterministic run-context data and layer-specific scorecards into a structured Markdown format, separating objective data gathering from prose generation to ensure consistency.

What is deterministic technical debt reporting?

Deterministic technical debt reporting assembles complex data into a high-integrity format, ensuring codebase assessments remain objective and reproducible by preventing AI-generated prose from altering the underlying factual findings.

How do I identify hidden coupling and complexity hotspots in a codebase?

Hidden coupling and complexity hotspots are identified through cross-layer analysis that surfaces critical findings invisible to single-axis scans, synthesizing the results into layer-specific scorecards within a comprehensive readiness report.

Can I track architectural readiness across software development lifecycles?

Architectural readiness tracking across software development lifecycles is supported by rendering comprehensive assessment reports that balance high-level executive summaries with granular technical findings.

Do I need an orchestrator to produce standardized codebase readiness reports?

A deterministic orchestrator must complete the data collection phase first, after which the assessment findings are assembled into a standardized, professional-grade report highlighting the top three technical debt priorities.

What is the best way to format technical debt findings for an engineering team?

The best way to format technical debt findings is using a structured, fold-based Markdown output that balances high-level executive summaries with granular technical findings, directly highlighting priority action items for engineering teams.