# Verification Loop

> Pre-commit verification with lint, type-check, tests, and security scan

- **Type:** Skill
- **Install:** `agentstack add skill-mshadmanrahman-pm-pilot-verification-loop`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [mshadmanrahman](https://agentstack.voostack.com/s/mshadmanrahman)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [mshadmanrahman](https://github.com/mshadmanrahman)
- **Source:** https://github.com/mshadmanrahman/pm-pilot/tree/main/skills/dev/verification-loop
- **Website:** https://github.com/mshadmanrahman/pm-pilot#readme

## Install

```sh
agentstack add skill-mshadmanrahman-pm-pilot-verification-loop
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Verification Loop

Run all quality gates before committing or creating a PR.

## When to Use

- Before any git commit
- Before creating a pull request
- After completing implementation (before marking done)
- When asked to "verify" or "check everything"

## Procedure

### Step 1: Detect Project Type

Identify available tools from project files:
- `package.json`: npm/yarn scripts (lint, typecheck, test)
- `pyproject.toml` / `setup.py`: Python tooling (ruff, mypy, pytest)
- `go.mod`: Go tooling (golangci-lint, go vet, go test)
- `Cargo.toml`: Rust tooling (clippy, cargo test)

### Step 2: Run Quality Gates

Execute in order (stop on CRITICAL):

| Gate | Command (detect per project) | Severity |
|------|------------------------------|----------|
| Lint | eslint, ruff, golangci-lint | HIGH |
| Type Check | tsc --noEmit, mypy, go vet | HIGH |
| Tests | jest, pytest, go test | CRITICAL |
| Security | npm audit, pip-audit, cargo audit | CRITICAL |
| Coverage | jest --coverage, pytest --cov | HIGH |

### Step 3: Report Results

```
Verification: {project name}

  Lint:       PASS | FAIL ({count} issues)
  Types:      PASS | FAIL ({count} errors)
  Tests:      PASS | FAIL ({pass}/{total})
  Security:   PASS | FAIL ({count} vulnerabilities)
  Coverage:   {percent}% (target: 80%)

Verdict: READY TO COMMIT | BLOCKED ({reason})
```

### Step 4: Actionable Fixes

For each failure, provide:
```
{gate} FAIL:
  {file}:{line} - {error message}
  Fix: {specific suggestion}
```

## Blocking Rules

- CRITICAL failures block commit (tests failing, known vulnerabilities)
- HIGH failures: warn but allow commit with acknowledgment
- MEDIUM/LOW: report only, do not block

## Output Format

```
Verification: lead-scoring-simulator

  Lint:       PASS
  Types:      PASS
  Tests:      PASS (24/24)
  Security:   PASS
  Coverage:   87% (target: 80%)

Verdict: READY TO COMMIT
```

## Rules

- Always run tests with verbose output
- Kill any hung processes after 120s timeout
- If a gate tool is not installed, skip it with a warning
- Never auto-fix lint issues without showing what changed
- Clean up test artifacts after run

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [mshadmanrahman](https://github.com/mshadmanrahman)
- **Source:** [mshadmanrahman/pm-pilot](https://github.com/mshadmanrahman/pm-pilot)
- **License:** MIT
- **Homepage:** https://github.com/mshadmanrahman/pm-pilot#readme

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-mshadmanrahman-pm-pilot-verification-loop
- Seller: https://agentstack.voostack.com/s/mshadmanrahman
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.