verification-loop

Runs build, type, lint, test, security, and diff checks to produce a verification report.

Updated Mar 25, 2026
One-click install
npx skills add https://github.com/Femad-6/my-skills --skill verification-loop-femad-6
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: verification-loop
Source: https://github.com/Femad-6/my-skills/tree/main/.github/skills/verification-loop
Command: npx skills add https://github.com/Femad-6/my-skills --skill verification-loop-femad-6

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After finishing a feature or refactor, it is easy to miss broken builds, type errors, failing tests, or leaked secrets before opening a pull request. This Skill runs a structured multi-phase verification pass so quality issues are caught before code review. ## Core Features & Use Cases - Six-Phase Verification: Sequentially checks build success, type errors (tsc/pyright), lint issues (npm lint/ruff), test results with coverage, security scans for secrets and console.log statements, and a git diff review. - Standardized Report Output: Produces a PASS/FAIL summary across all phases with an overall READY/NOT READY verdict and a list of issues to fix. - Continuous Mode: Supports recurring verification checkpoints during long coding sessions, complementing PostToolUse hooks with deeper review. - Use Case: Before creating a PR for a TypeScript feature, run the verification loop to confirm the build passes, tests meet the 80% coverage target, and no API keys were accidentally committed. ## Quick Start Run the verification loop on my current changes and tell me if the code is ready for a pull request.

Frequently Asked Questions about verification-loop

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

FAQPage Schema
How do I verify my code is ready for a pull request?

Run a verification loop that checks the build, type errors, lint warnings, test results with coverage, security issues, and the git diff. The process ends with a READY or NOT READY verdict plus a list of issues to fix.

What checks should I run before creating a PR?

At minimum run the project build, a type check with tsc or pyright, a lint pass with npm run lint or ruff, the test suite with coverage, a scan for leaked secrets, and a review of changed files via git diff.

Does this verification workflow support Python projects?

Yes. The type check phase uses pyright and the lint phase uses ruff for Python codebases, while JavaScript and TypeScript projects use tsc and npm run lint. Test and security phases apply to both.

How do I check for leaked API keys in my code?

Use grep to search source files for patterns like sk- or api_key across .ts and .js files. The security phase also flags leftover console.log statements that should be removed before merging.

What test coverage threshold should I target before merging?

The verification loop targets a minimum of 80% coverage. Run the test suite with the coverage flag and report total tests, passed, failed, and the coverage percentage in the final report.