writing-verify-script — writing-verify-script install writing-verify-script, agent-loop, community, writing-verify-script install, ide skills, quality checks with writing-verify-script, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for Development Agents requiring streamlined project validation and quality checks through a standardized entry point writing-verify-script is a skill that defines how to create a verification script, a prerequisite for implementation planning, providing a single command for quality checks.

Features

Creates a standardized entry point for project validation using ./scripts/verify.sh
Runs all quality checks, including tests, linting, formatting, and type checking
Provides a single command for implementation planning
Supports project-specific tools, such as linters, formatters, and type checkers
Returns an exit code of 0 for success or non-zero for failure

# Core Topics

noviadi noviadi
[0]
[0]
Updated: 3/8/2026

Agent Capability Analysis

The writing-verify-script skill by noviadi is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for writing-verify-script install, quality checks with writing-verify-script.

Ideal Agent Persona

Ideal for Development Agents requiring streamlined project validation and quality checks through a standardized entry point

Core Value

Empowers agents to run comprehensive quality checks including tests, linting, formatting, and type checking, providing a single command for project validation through the verify.sh script, supporting tools like linters, formatters, and type checkers

Capabilities Granted for writing-verify-script

Automating project validation
Streamlining implementation planning
Running quality checks for tests, linting, and formatting

! Prerequisites & Limits

  • Requires implementation of ./scripts/verify.sh
  • Dependent on project-specific tools and toolchains
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

writing-verify-script

Install writing-verify-script, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Writing the Verification Script

This document defines how to create ./scripts/verify.sh, the standardized entry point for project validation.

Overview

The verification script is a prerequisite for implementation planning. It provides a single command that runs all quality checks (tests, linting, formatting, type checking) regardless of the underlying toolchain.

./scripts/verify.sh
    ↓
[Project-specific tools: tests, linter, formatter, type checker]
    ↓
Exit 0 (success) or non-zero (failure)

Why a Wrapper Script?

BenefitDescription
ConsistencySame command across all projects
DiscoverabilityAgents and humans know where to look
ComposabilityCan run multiple tools in sequence
CI alignmentScript can be reused in CI pipelines

Script Requirements

Location

Always: ./scripts/verify.sh

Behavior

  1. Run all quality checks in sequence
  2. Exit with code 0 if all pass
  3. Exit with non-zero code on first failure
  4. Print clear output indicating what's running

Checks to Include

Check TypePurposeExamples
TestsVerify behaviorcargo test, npm test, go test, pytest
LintingCatch bugs/style issuescargo clippy, eslint, golangci-lint, flake8
FormattingEnsure consistent stylecargo fmt --check, prettier --check, gofmt, black --check
Type checkingCatch type errorstsc --noEmit, mypy, pyright

Not all projects need all checks. Include what's relevant.

Script Constraints

The script must be:

ConstraintReason
Non-interactiveNo prompts, confirmations, or user input; must run unattended
Fail-fastExit on first failure (set -e); don't continue after errors
CI-safeMust work in CI environments without local dependencies
DeterministicSame code state → same result; no flaky tests
No network dependencyUnless explicitly documented; offline-first

Recommended additions:

  • Print tool versions at start (helps debug CI vs local differences)
  • Use set -euo pipefail for strict error handling
  • Treat warnings as errors where applicable (e.g., cargo clippy -- -D warnings)

Examples by Project Type

Rust

bash
1#!/usr/bin/env bash 2set -euo pipefail 3 4echo "==> Running tests..." 5cargo test 6 7echo "==> Running clippy..." 8cargo clippy -- -D warnings 9 10echo "==> Checking formatting..." 11cargo fmt --check 12 13echo "==> All checks passed!"

Node.js / TypeScript

bash
1#!/usr/bin/env bash 2set -euo pipefail 3 4echo "==> Type checking..." 5npm run typecheck # or: npx tsc --noEmit 6 7echo "==> Running tests..." 8npm test 9 10echo "==> Linting..." 11npm run lint # or: npx eslint . 12 13echo "==> Checking formatting..." 14npx prettier --check . 15 16echo "==> All checks passed!"

Go

bash
1#!/usr/bin/env bash 2set -euo pipefail 3 4echo "==> Running tests..." 5go test ./... 6 7echo "==> Running linter..." 8golangci-lint run 9 10echo "==> Checking formatting..." 11test -z "$(gofmt -l .)" || { echo "Files need formatting"; exit 1; } 12 13echo "==> All checks passed!"

Python

bash
1#!/usr/bin/env bash 2set -euo pipefail 3 4echo "==> Running tests..." 5pytest 6 7echo "==> Type checking..." 8mypy . 9 10echo "==> Linting..." 11flake8 12 13echo "==> Checking formatting..." 14black --check . 15 16echo "==> All checks passed!"

Multi-language / Monorepo

bash
1#!/usr/bin/env bash 2set -euo pipefail 3 4echo "==> Backend (Rust)..." 5(cd backend && cargo test && cargo clippy -- -D warnings) 6 7echo "==> Frontend (TypeScript)..." 8(cd frontend && npm test && npm run lint) 9 10echo "==> All checks passed!"

Script Template

bash
1#!/usr/bin/env bash 2set -euo pipefail 3 4# Verify script for [PROJECT_NAME] 5# Runs all quality checks required before committing code. 6 7echo "==> Running tests..." 8# TODO: Add test command 9 10echo "==> Running linter..." 11# TODO: Add lint command 12 13echo "==> Checking formatting..." 14# TODO: Add format check command 15 16echo "==> All checks passed!"

Creating the Script

  1. Create scripts/ directory if it doesn't exist
  2. Create verify.sh using the template above
  3. Fill in project-specific commands
  4. Make executable: chmod +x scripts/verify.sh
  5. Test it: ./scripts/verify.sh
  6. Commit the script

Prerequisite for Plan Writing

Before running gap analysis or writing plans/IMPLEMENTATION_PLAN.md:

  1. Check if ./scripts/verify.sh exists
  2. If missing, stop and notify:
    ⚠️ Verification script not found.
    
    Before creating an implementation plan, create ./scripts/verify.sh
    See docs/writing-verify-script.md for instructions.
    
  3. Once the script exists and passes, proceed with plan writing

Checklist

Before using the verification script:

Setup:

  • Script exists at ./scripts/verify.sh
  • Script is executable (chmod +x)
  • Script uses set -euo pipefail

Checks included:

  • Runs tests
  • Runs linter (if project has one)
  • Checks formatting (if project has formatter)
  • Runs type checker (if applicable)

Constraints met:

  • Non-interactive (no prompts or user input)
  • Fails fast on first error
  • CI-safe (no local-only dependencies)
  • Deterministic (no flaky behavior)
  • Exits 0 on success, non-zero on failure

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is writing-verify-script?

Ideal for Development Agents requiring streamlined project validation and quality checks through a standardized entry point writing-verify-script is a skill that defines how to create a verification script, a prerequisite for implementation planning, providing a single command for quality checks.

How do I install writing-verify-script?

Run the command: npx killer-skills add noviadi/agent-loop/writing-verify-script. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for writing-verify-script?

Key use cases include: Automating project validation, Streamlining implementation planning, Running quality checks for tests, linting, and formatting.

Which IDEs are compatible with writing-verify-script?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for writing-verify-script?

Requires implementation of ./scripts/verify.sh. Dependent on project-specific tools and toolchains.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add noviadi/agent-loop/writing-verify-script. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use writing-verify-script immediately in the current project.

Related Skills

Looking for an alternative to writing-verify-script or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI