improve-codebase-architecture
Analyze codebase for shallow modules and architectural friction, then propose deepening candidates.
Skill by TheNordicOne
Chalk Labs
Need help deploying improve-codebase-architecture?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/thenordicone-improve-codebase-architecture
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/improve-codebase-architecture
What's inside
- Skill name
improve-codebase-architecture- Description
- Analyze codebase for shallow modules and architectural friction, then propose deepening candidates. Activate when asked to review architecture, find coupling issues, reduce module boundaries, or improve codebase structure.
- License
- MIT
- Instructions
- 69 lines in SKILL.md · view on GitHub
Files (2)
- REFERENCE.md
- SKILL.md
SKILL.md (first lines)
# Improve Codebase Architecture Identify shallow, tightly-coupled modules and propose how to deepen them — merging unnecessary boundaries, simplifying interfaces, and reducing integration risk. ## Process 1. **Scan** — explore the codebase for module boundaries, looking for shallow modules that delegate without adding value 2. **Identify candidates** — find clusters of tightly-coupled shallow modules that could be merged into a single deep module with a clean interface 3. **Classify dependencies** — for each candidate, classify its dependencies using the categories in [REFERENCE.md](REFERENCE.md) (in-process, local-substitutable, ports & adapters, mock) 4. **Design the interface** — propose what the deepened module should expose, hide, and own 5. **Plan testing** — identify boundary tests to write and shallow tests to delete 6. **Write findings** — output all findings to a markdown file using the template below ## Output Write findings to a markdown file (e.g., `architecture-improvements.md`) in the project root. Use one section per candidate, following this structure: ```markdown # Architecture Improvement Proposals > Generated on YYYY-MM-DD ## Candidate: [Name] ### Problem - Which modules are shallow and tightly coupled - What integration risk exists in the seams between them - Why this makes the codebase harder to navigate and maintain ### Proposed Interface - Interface signature (types, methods, params) - Usage example showing how callers use it - What complexity it hides internally ### Dependency Strategy Which category applies and how dependencies are handled: - **In-process**: merged directly - **Local-substitutable**: tested with [specific stand-in] - **Ports & adapters**: port definition, production adapter, test adapter - **Mock**: mock boundary for external services ### Testing Strategy - **New boundary tests to write**: behaviors to verify at the interface - **Old tests to delete**: shallow module tests that become redundant - **Test environment needs**: any local stand-ins or adapters required ### Implementation Recommendations Durable guidance NOT coupled to current file paths: - What the module should own (responsibilities) - What it should hide (implementation details) - What it should expose (the interface contract) - How callers should migrate to the new interface ``` ## Rules - Recommendations must be **durable** — describe responsibilities and interfaces, not file paths that will change - Focus on **observable friction** — don't propose changes for theoretical purity - Each candidate must have a clear **before/after** in terms of interface complexity - Refer to [REFERENCE.md](REFERENCE.md) for dependency classification details and testing philosophy
From TheNordicOne/claude-skills, MIT.
More from TheNordicOne/claude-skills
- 0.479score
css-authoring
TheNordicOne
General CSS authoring conventions — units & values, tokens & custom properties, selectors & specificity, class naming, style architecture, and authoring…
SkillCFreshness: CClaude Code +9 - 0.474score
breaker
Alexander Pahn
A theoretical "try to break it" skill for any target — code, a UI/UX flow, an infra or config change, a design, an API.
SkillCFreshness: CClaude Code +9 - 0.474score
brutal-review
Alexander Pahn
The shared core methodology for brutally scrutinizing code reviews.
SkillCFreshness: CClaude Code +9 - 0.411score
tdd
TheNordicOne
Test-Driven Development workflow — RED/GREEN/REFACTOR cycle with tracer bullets.
SkillDFreshness: DClaude Code +9 - 0.409score
mini-alex
Alexander Pahn
A deliberate problem-solving methodology for debugging, code review, refactoring, feature development, and architectural planning.
SkillDFreshness: DClaude Code +9 - 0.409score
triage-issue
TheNordicOne
Triage a bug by exploring the codebase to find root cause, then write a markdown report with a TDD-based fix plan.
SkillDFreshness: DClaude Code +9 - 0.406score
angular-components
TheNordicOne
Angular v20+ component architecture.
SkillDFreshness: DClaude Code +9 - 0.406score
angular-service-tests
TheNordicOne
Angular service and HTTP testing patterns.
SkillDFreshness: DClaude Code +9 - 0.406score
angular-signals
TheNordicOne
Angular signals, computed properties, and effects.
SkillDFreshness: DClaude Code +9 - 0.406score
css-features
TheNordicOne
Modern CSS features — oklch colors, relative color syntax, container queries, and Baseline 2024.
SkillDFreshness: DClaude Code +9 - 0.406score
css-layout
TheNordicOne
CSS layout rules — Grid vs Flexbox and logical properties.
SkillDFreshness: DClaude Code +9 - 0.406score
angular-services
TheNordicOne
Angular service design, dependency injection, and providedIn strategy.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 16, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/TheNordicOne/claude-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from TheNordicOne
- 0.479score
css-authoring
TheNordicOne
General CSS authoring conventions — units & values, tokens & custom properties, selectors & specificity, class naming, style architecture, and authoring…
SkillCFreshness: CClaude Code +9 - 0.411score
tdd
TheNordicOne
Test-Driven Development workflow — RED/GREEN/REFACTOR cycle with tracer bullets.
SkillDFreshness: DClaude Code +9 - 0.409score
triage-issue
TheNordicOne
Triage a bug by exploring the codebase to find root cause, then write a markdown report with a TDD-based fix plan.
SkillDFreshness: DClaude Code +9 - 0.406score
semantic-html
TheNordicOne
Semantic HTML structure, landmarks, and Baseline 2024 elements.
SkillDFreshness: DClaude Code +9 - 0.406score
angular-component-tests
TheNordicOne
Angular component test patterns.
SkillDFreshness: DClaude Code +9 - 0.406score
a11y-interactive
TheNordicOne
Accessible interactive patterns.
SkillDFreshness: DClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get improve-codebase-architecture running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
improve-codebase-architecture skill. Agent Mart. https://agentmart.dev/skills/thenordicone-improve-codebase-architecture (last updated 2026-10-24)