dependency-boundary-review
Use when reviewing dependencies between modules, packages, services, layers, schemas, frontend components, or infrastructure boundaries to reduce coupling and…
Skill by WangYao-GoGoGo
Chalk Labs
Need help deploying dependency-boundary-review?
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/wangyao-gogogo-dependency-boundary-review
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
Use cases: frontend, devops
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/dependency-boundary-review
What's inside
- Skill name
dependency-boundary-review- Description
- Use when reviewing dependencies between modules, packages, services, layers, schemas, frontend components, or infrastructure boundaries to reduce coupling and clarify ownership.
- License
- MIT
- Instructions
- 41 lines in SKILL.md · view on GitHub
Files (2)
- README.md
- SKILL.md
SKILL.md (first lines)
# Dependency Boundary Review Use this skill to check whether dependencies point in maintainable directions. ## When To Use - A change crosses packages, layers, services, UI components, database access, or infrastructure. - Business logic depends directly on frameworks, vendors, persistence, transport, or UI details. - Tests are hard because dependencies cannot be substituted. - Cycles or hidden dependencies make changes risky. ## Workflow 1. Map the current dependency direction. 2. Identify the stable core: domain rules, policies, contracts, or data ownership. 3. Identify volatile edges: frameworks, vendors, transport, persistence, UI, cache, external APIs. 4. Check whether volatile edges depend inward instead of the core depending outward. 5. Recommend boundary changes only where they reduce change cost or test friction. 6. Provide verification steps. ## Boundary Rules - Domain rules should not know transport or persistence details unless the project deliberately chooses an active record style. - UI state should not leak into domain or persistence logic. - Database schemas should be owned by a clear service, module, or migration process. - Cache access should sit behind a policy or repository boundary when consistency matters. - Framework dependencies are acceptable at the edge; they are risky in reusable core logic. ## Output Format ```markdown Boundary review: - Current dependency shape: - Boundary violations: - Recommended direction: - Minimal changes: - Verification: - Tradeoffs: ```
From WangYao-GoGoGo/architecture-agent-skills, MIT.
More from WangYao-GoGoGo/architecture-agent-skills
- 0.409score
cache-invalidation-review
WangYao-GoGoGo
Use when reviewing cache invalidation rules, stale data risk, TTLs, event-based invalidation, versioned keys, write paths, and consistency tradeoffs.
SkillDFreshness: DClaude Code +9 - 0.409score
cache-strategy-review
WangYao-GoGoGo
Use when reviewing or designing cache strategy, including cache-aside, write-through, write-behind, TTLs, consistency, stampede prevention, key design, and…
SkillDFreshness: DClaude Code +9 - 0.409score
redis-data-structure-review
WangYao-GoGoGo
Use when choosing Redis data structures such as string, hash, list, set, sorted set, stream, bitmap, or HyperLogLog based on access patterns and consistency…
SkillDFreshness: DClaude Code +9 - 0.409score
wide-column-modeling-review
WangYao-GoGoGo
Use when reviewing wide-column or column-family data models for row keys, column families, access patterns, partitioning, hot spots, time-series data, and…
SkillDFreshness: DClaude Code +9 - 0.409score
anti-overengineering-review
WangYao-GoGoGo
Use when a proposed architecture, design pattern, abstraction, framework, cache, service split, or refactor may be more complex than the current problem needs.
SkillDFreshness: DClaude Code +9 - 0.409score
architecture-before-coding
WangYao-GoGoGo
Use before implementing a new feature or non-trivial code change when the agent should design responsibilities, boundaries, interfaces, data flow, and…
SkillDFreshness: DClaude Code +9 - 0.409score
architecture-decision-review
WangYao-GoGoGo
Use when evaluating or documenting an architecture decision, including pattern choice, service boundary, database choice, cache strategy, frontend state…
SkillDFreshness: DClaude Code +9 - 0.409score
design-pattern-selector
WangYao-GoGoGo
Use when choosing whether a design pattern is appropriate for new or existing code, especially around object-oriented design, Java, Python, large…
SkillDFreshness: DClaude Code +9 - 0.409score
new-project-scaffolding
WangYao-GoGoGo
Use when generating a new project from scratch.
SkillDFreshness: DClaude Code +9 - 0.409score
data-modeling-review
WangYao-GoGoGo
Use when reviewing entity relationships, document shapes, normalization, denormalization, aggregate boundaries, ownership, and query-driven data model…
SkillDFreshness: DClaude Code +9 - 0.409score
runtime-error-diagnosis
WangYao-GoGoGo
Use when code fails to run, throws an exception, produces an error log, or a build/test command fails — diagnose the root cause and suggest the smallest safe…
SkillDFreshness: DClaude Code +9 - 0.409score
api-architecture-review
WangYao-GoGoGo
Use when reviewing API design, request/response shape, versioning, error contracts, pagination, idempotency, compatibility, and client/server boundaries.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 27, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from WangYao-GoGoGo
- 0.409score
design-pattern-selector
WangYao-GoGoGo
Use when choosing whether a design pattern is appropriate for new or existing code, especially around object-oriented design, Java, Python, large…
SkillDFreshness: DClaude Code +9 - 0.409score
new-project-scaffolding
WangYao-GoGoGo
Use when generating a new project from scratch.
SkillDFreshness: DClaude Code +9 - 0.409score
architecture-before-coding
WangYao-GoGoGo
Use before implementing a new feature or non-trivial code change when the agent should design responsibilities, boundaries, interfaces, data flow, and…
SkillDFreshness: DClaude Code +9 - 0.409score
anti-overengineering-review
WangYao-GoGoGo
Use when a proposed architecture, design pattern, abstraction, framework, cache, service split, or refactor may be more complex than the current problem needs.
SkillDFreshness: DClaude Code +9 - 0.409score
architecture-decision-review
WangYao-GoGoGo
Use when evaluating or documenting an architecture decision, including pattern choice, service boundary, database choice, cache strategy, frontend state…
SkillDFreshness: DClaude Code +9 - 0.409score
runtime-error-diagnosis
WangYao-GoGoGo
Use when code fails to run, throws an exception, produces an error log, or a build/test command fails — diagnose the root cause and suggest the smallest safe…
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 dependency-boundary-review 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
dependency-boundary-review skill. Agent Mart. https://agentmart.dev/skills/wangyao-gogogo-dependency-boundary-review (last updated 2026-10-24)