trellis-check

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

Updated Jun 8, 2026
One-click install
npx skills add https://github.com/SilentFlower/flower-trellis --skill trellis-check-silentflower
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: trellis-check
Source: https://github.com/SilentFlower/flower-trellis/tree/main/.agents/skills/trellis-check
Command: npx skills add https://github.com/SilentFlower/flower-trellis --skill trellis-check-silentflower

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After writing code, it is easy to miss spec violations, broken tests, or inconsistencies across layers before committing. This Skill runs a structured quality verification pass over recently changed code so defects and context drift are caught before they land in the repository. ## Core Features & Use Cases - Spec Compliance Review: Reads task artifacts (prd.md, design.md, implement.md) and per-layer spec indexes to verify the implementation matches documented conventions. - Project Check Execution: Runs the project's lint, type-check, and test commands and requires failures to be fixed before proceeding. - Cross-Layer Checklists: Covers data flow across Storage/Service/API/UI layers, code reuse, import/dependency correctness, and same-layer consistency. - Use Case: Before committing a feature that touches the API and UI layers, run this Skill to confirm tests pass, types align across layers, and any lessons learned are written back into the spec docs. ## Quick Start Ask the AI to run the trellis-check quality verification on the code changes you just made before committing them.

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 a structured check that identifies changed files with git diff, reads the relevant task artifacts and specs, then executes the project's lint, type-check, and test commands. Fix any failures and review the checklist items before committing.

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

Trace read flows from Storage through Service and API to UI, and write flows in the reverse direction. Confirm types and schemas are passed correctly between layers and that errors propagate properly to the caller.

When should cross-layer consistency checks be skipped?▼

Skip the cross-layer dimensions when the change is confined to a single layer. The data flow, code reuse, import, and consistency checklists only apply when a change touches multiple layers or creates shared utilities and new files.

What should I check for test coverage after a code change?▼

Confirm that every new function has a unit test, every bug fix has a regression test, and changed behavior has updated existing tests. Also verify no debug logging or suppressed type-safety warnings remain in the code.

Why update spec documentation after fixing a bug?▼

Documenting non-obvious fixes and newly discovered patterns in the spec directory prevents the same issue from recurring in future work. If a lesson learned would help a future session, it belongs in the relevant spec doc.