skills.rest
dev2019zheng
dev2019zhengCOMMUNITY
Explore all skills by this author →
GitHub

trellis-check

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

Updated Jun 8, 2026
Search Tags:#testing#code review#pre-commit#quality check#spec compliance#lint#type-check
One-click install
npx skills add https://github.com/dev2019zheng/codex-beacon --skill trellis-check-dev2019zheng
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: trellis-check
Source: https://github.com/dev2019zheng/codex-beacon/tree/main/.cursor/skills/trellis-check
Command: npx skills add https://github.com/dev2019zheng/codex-beacon --skill trellis-check-dev2019zheng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After writing code, it is easy to miss spec violations, broken tests, cross-layer type mismatches, or duplicated logic before committing. This Skill runs a structured quality verification pass over recent changes so defects and context drift are caught before they land in the repository. ## Core Features & Use Cases - Change-Scoped Verification: Identifies modified files via git diff, loads the applicable Trellis specs, and runs the project's lint, type-check, and test commands. - Structured Checklists: Covers code quality, test coverage, and spec synchronization with explicit checkbox items. - Cross-Layer Analysis: Traces data flow across Storage, Service, API, and UI layers, checks code reuse, import correctness, and same-layer consistency for multi-layer changes. - Use Case: After implementing a feature spanning the API and UI layers, run this check before committing to confirm types propagate correctly, regression tests exist, and the spec docs reflect any new patterns. ## Quick Start Ask the assistant to run the trellis-check quality verification on the current uncommitted changes and fix any violations it finds.

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 verification workflow on your uncommitted changes. It identifies modified files with git diff, loads the relevant Trellis specs, executes the project's lint, type-check, and test commands, then reviews results against structured quality checklists and fixes violations directly.

How to check cross-layer data flow in a full-stack codebase?▼

The cross-layer dimension traces read flow from Storage through Service and API to UI, and write flow in reverse. It confirms types and schemas pass correctly between layers and that errors propagate to the caller, but only applies when changes touch three or more layers.

What does the Trellis spec check actually verify?▼

It reads the spec index for each changed package or layer using get_context.py, then follows the Quality Check section of each spec. It also prompts spec updates when fixes or non-obvious discoveries should be documented for future sessions.

When should I skip the cross-layer consistency checks?▼

Skip Step 5 when your change is confined to a single layer, such as an isolated UI tweak or a storage-only fix. The data flow, code reuse, import, and consistency dimensions only apply to changes spanning multiple layers or creating new shared utilities.

Does this check require specific project tooling?▼

It expects a git repository, the .trellis directory with spec files, and the get_context.py helper script. Lint, type-check, and test commands are whatever the host project defines, so it adapts to any language or framework.

Related Skills

Explore More Software Engineering Skills→
luanluan
4

refine

Simplify complexity and clean formatting in uncommitted code changes.

Community
Intermediate
tribedotruntribedotrun
8

mando-pr

Create GitHub pull requests and trigger AI reviewers with CI monitoring.

Official
Advanced
johnatas-henriquejohnatas-henrique

regression-suite

Map test coverage to game design document critical paths and closed bug fixes.

Community
Advanced
zh667zh667

verification-loop

Automate end-to-end verification of code changes across builds, tests, linting, and security checks.

Community
Advanced