validate

Validates implementations against plans or issue acceptance criteria with automated checks and structured reports.

Updated May 7, 2026
One-click install
npx skills add https://github.com/Pieter-1337/Euricom-tsz --skill validate-pieter-1337
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: validate
Source: https://github.com/Pieter-1337/Euricom-tsz/tree/main/.claude/skills/validate
Command: npx skills add https://github.com/Pieter-1337/Euricom-tsz --skill validate-pieter-1337

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After writing code, it is easy to miss acceptance criteria, leave debug statements behind, or commit with failing tests. This Skill closes that gap by systematically verifying that what was built matches what was planned before anything gets committed. ## Core Features & Use Cases - Automated Check Execution: Discovers and runs lint, type-check, and test scripts from package.json, collecting all failures instead of stopping at the first one. - Source-of-Truth Cross-Referencing: Compares the git diff against issue tracker acceptance criteria (via gh CLI) or a PLAN.md file, marking each item as done, partial, missing, or N/A. - Quality Issue Detection: Flags unhandled promise rejections, unsafe optional property access, leftover console.log statements, and dead code in the changed files. - Use Case: After implementing a feature from issue #42, run the validation step to confirm all acceptance criteria are met, tests pass, and no debug code remains before committing. ## Quick Start Ask the AI to validate your implementation against issue #42 or the PLAN.md at the repo root before committing your changes.

Frequently Asked Questions about validate

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

FAQPage Schema
How do I validate my implementation against acceptance criteria before committing?

Run the validate skill with an issue reference like #42 or a path to a plan file. It fetches the acceptance criteria, runs your test and lint scripts, reviews the git diff, and reports each criterion as done, partial, or missing.

How to check if my code changes match the original plan?

Pass a PLAN.md file or issue URL as the argument. The skill walks each step or acceptance criterion in the source document and assesses whether the git diff addresses it, flagging gaps and untested items.

Does the validation work without an issue tracker or plan file?

Yes, but with reduced coverage. If no argument is given and no PLAN.md exists at the repo root, the skill asks you to describe what you implemented, then still runs automated checks and code quality review on the diff.

What happens if bun commands cannot run due to permissions?

The skill notes that automated checks could not be confirmed and recommends running them manually. It still proceeds with static analysis of the diff, cross-referencing the source-of-truth and surfacing code quality issues.

What are the limitations of automated implementation validation?

Validation assesses intent rather than literal text matching, so it may miss subtle behavioral mismatches not visible in the diff. It also cannot verify runtime behavior beyond what the existing test suite covers.