karote00/asyra/framework-import-boundary-auditor
Claude Code and agent skill by karote00/asyra
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Audit and fix import-boundary violations with deterministic facade-first rewrites and explicit exceptions. Use when requests mention deep imports, boundary cleanup, or core-facade migration.
Install
npx vskill@latest install karote00/asyra/framework-import-boundary-auditorSKILL.md
Skill: framework-import-boundary-auditor
Trigger Signals
Use this skill when requests include:
- "import boundary"
- "deep import"
- "move import to core"
- "scan for boundary violations"
- "facade-first"
Do Not Use When
- Request is only UI copy/style changes.
- Request is only runtime behavior debugging with no import churn.
Required Inputs
- Scope: file list, folder, package, or full repo.
- Rules:
docs/ai/framework/rules/import-boundaries.mddocs/ai/framework/CODING_STANDARDS.md- Current architecture references in:
docs/ai/framework/API_SURFACES.mddocs/ai/framework/packages/core.md
Preflight
- Capture current dirty state:
git status --short - Scan imports in scope using
rg. - Build a short mapping of allowed facade exports vs package exports.
Deterministic Procedure
- Find violations:
- deep package internal paths (
@asyra/*/src/*) - relative cross-package imports
- app-level direct imports where core facade already exists
- Classify each finding:
must_fix_to_core_facadeallowed_direct_package_importblocked_missing_facade_export
- Apply minimal edits:
- rewrite imports only
- avoid behavior changes unless required by typing
- If blocked by missing core export:
- add curated export in
@asyra/core - avoid wildcard/bulk re-export patterns
- Re-run targeted checks for touched packages/apps:
- lint/type/build commands for affected scope
Validation Matrix
- Boundary scan: no
@asyra/*/src/*in target scope. - Build/type checks: pass for impacted package(s).
- Runtime behavior: unchanged unless explicitly requested.
Required Output Format
Return results with these sections:
Findings
- list each violation category and count
Changes
- list import rewrites and any new facade exports
Validation
- commands run + pass/fail
Open Items
- allowed exceptions or blocked items
Guardrails
- Do not introduce new deep imports while fixing others.
- Do not move app domain logic into core.
- Local commits may close completed, validated steps/stages; never push unless
the user explicitly requests the remote operation. Follow docs/ai/workflows/git-commit-push-policy.md.
Failure Policy
If facade ownership is ambiguous:
- do not guess
- keep current behavior
- output two concrete options with tradeoffs
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingdocs/ai/skills/framework-import-boundary-auditor/SKILL.md
Popularity
- Repository stars
- 44
- Repository forks
- 1
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/karote00/asyra/framework-import-boundary-auditor)