trellis-check

Verifies code changes against specs, lint, tests, and cross-layer consistency checklists.

Updated Sep 5, 2026
One-click install
npx skills add https://github.com/jiozhaoyue/ST-BgLoader --skill trellis-check-jiozhaoyue
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: trellis-check
Source: https://github.com/jiozhaoyue/ST-BgLoader/tree/main/.cursor/skills/trellis-check
Command: npx skills add https://github.com/jiozhaoyue/ST-BgLoader --skill trellis-check-jiozhaoyue

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After writing code, it is easy to miss spec violations, failing tests, leftover debug logging, or inconsistencies across architectural layers. This Skill runs a structured quality verification pass over recently changed code before it is committed, catching drift between implementation and documented specifications. ## Core Features & Use Cases - Spec Compliance Review: Reads task artifacts (prd.md, design.md, implement.md) and per-layer spec indexes to verify the change matches documented conventions. - Project Checks: Runs lint, type-check, and test commands and requires all failures to be fixed before proceeding. - Cross-Layer Analysis: Traces data flow across Storage, Service, API, and UI layers, checks code reuse, import correctness, and same-layer consistency. - Use Case: After implementing a feature spanning the API and UI layers, run this check to confirm types propagate correctly, tests cover new functions, and no out-of-scope files were modified. ## Quick Start Ask the assistant to run the trellis-check quality verification on the current uncommitted changes before committing.

Frequently Asked Questions about trellis-check

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

FAQPage Schema
How do I verify code quality before committing changes?▼

Run this check after writing code: it inspects git diff output, reads the relevant task artifacts and specs, executes the project's lint, type-check, and test commands, then reviews the change against a structured checklist before you commit.

What does a spec compliance check for code changes include?▼

It reads prd.md, design.md, and implement.md task artifacts plus per-layer spec indexes, then confirms the implementation follows documented conventions. It also prompts updating specs when a bug fix or non-obvious lesson should be recorded.

When should I run a cross-layer data flow review?▼

Run it when a change touches three or more layers, such as Storage, Service, API, and UI. The check traces read and write flows in both directions, verifies types pass correctly between layers, and confirms errors propagate to callers.

Does this check work for single-layer changes?▼

Yes. The cross-layer analysis step is explicitly skipped when the change is confined to a single layer, while lint, type-check, test, and scope discipline checks still apply to every change.

What happens when the check finds a design-level problem?▼

Mechanical issues like lint errors or wrong imports are fixed in place and checks re-run. Design or judgment issues, such as module boundaries or public interfaces, are reported with evidence and a recommendation, but not rewritten silently.