CtrlK
BlogDocsLog inGet started
Tessl Logo

sharaf/software-architecture-audit

Run an evidence-grounded software architecture audit workflow that builds a repo brief, selects single-auditor or specialist-panel mode, inspects boundary, layering, dependency, composition, cohesion, and testability risks, writes required finding blocks, and sequences incremental refactors. Use when asked for an architecture audit, architecture review, repo-structure review, software architecture report, audit_report.md, structural issue findings, or specialist-panel synthesis across multi-module systems.

100

1.85x
Quality

100%

Does it follow best practices?

Impact

100%

1.85x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Software Architecture Audit

Run an evidence-grounded software architecture audit workflow that turns the highest-leverage findings into an ordered, incremental improvement sequence.

What this skill does

This skill reviews a repository, subsystem, or specific path for architecture problems grounded in direct code evidence. It builds a factual repo brief, selects single-auditor or specialist-panel mode, inspects boundary integrity, dependency direction, cohesion, composition roots, testability, architecture smells, report structure, and refactor sequencing.

The workflow starts with a factual repo brief, chooses single-auditor or specialist-panel mode based on scope, gathers direct evidence, and produces a structured report with category-specific findings and a concrete improvement sequence.

When to use

Use this skill for prompts such as:

  • "Audit this repo's architecture"
  • "Write an architecture audit report"
  • "Produce audit_report.md"
  • "Architecture review for this package"
  • "Review the structure of this subsystem"
  • "Find boundary and layering problems"
  • "Inspect dependency direction and composition roots"
  • "Identify architecture smells and testability gaps"
  • "Plan an incremental architecture refactor"
  • "Use specialist-panel synthesis for a multi-module system"

Install

tessl install sharaf/software-architecture-audit

How it's organized

LayerWherePurpose
Entry pointSKILL.mdFull audit workflow, guardrails, decision logic, and output requirements
Tile manifesttile.jsonRegistry metadata and skill entrypoint

Output format

The final audit report must use these headings, in order:

## Repo Brief
## Highest-Leverage Structural Issues
## Boundary and Layering Problems
## Dependency and Composition Problems
## Testability and Change Friction
## Improvement Sequence
## Open Evidence Gaps

Each full finding includes severity, evidence, why it matters, recommended improvement, and likely refactor surface. The improvement sequence is ordered by leverage and dependency, not abstract architectural purity.

Eval results

Tested across three generated scenarios:

ScenarioWhat it checks
scenario-0Required report section structure and finding format
scenario-1Single-auditor mode selection and repo brief completeness
scenario-2Specialist-panel synthesis, deduplication, and forbidden recommendations
ModelBaseline avgWith-context avgUplift
claude-haiku-4-550%99%1.98x
claude-sonnet-4-652%99%1.90x
claude-opus-4-650%99%1.98x

Per-scenario with-context scores:

Modelscenario-0scenario-1scenario-2
claude-haiku-4-5100%100%96%
claude-sonnet-4-6100%98%100%
claude-opus-4-6100%100%98%

Activation after the routing fix: 3/3 generated scenarios fired tessl__software-architecture-audit.

Built from

Migrated from the legacy flat skill skills/software-architecture-audit.md in this repository.

Research lineage:

  • Domain: software-architecture
  • Sub-domains: anti-patterns-code-smells, clean-layered-architecture, dependency-management-inversion, structural-patterns, testing-architecture, system-evolution-migration
  • Research date: 2026-04-01
Workspace
sharaf
Visibility
Public
Created
Last updated
Publish Source
CLI
Badge
sharaf/software-architecture-audit badge