How do I install the Verification Loop skill?

Run npx skillmds@latest add tomevault-io/verification-loop-4 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Verification Loop safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Verification Loop?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Verification Loop free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Verification Loop?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Verification Loop by tomevault-io — Agent Skill

Name: Verification Loop
Author: tomevault-io

File contents

Verification Loop (Rust)

When to Use

After completing a feature or significant code change
Before creating a PR
After refactoring
When you want to ensure all quality gates pass

Verification Phases

Phase 1: Build Verification

cargo check 2>&1 | tail -20

If build fails, STOP and fix before continuing.

Phase 2: Format Check

cargo fmt -- --check 2>&1 | head -20

If formatting issues found, run cargo fmt to fix.

Phase 3: Lint Check

cargo clippy -- -D warnings 2>&1 | head -30

All clippy warnings are errors in this project. Fix before continuing.

Phase 4: Test Suite

# Run all tests with nextest
cargo nextest run 2>&1 | tail -50

# Also run doc tests (nextest doesn't run these)
cargo test --doc 2>&1 | tail -20

Report:

Total tests: X
Passed: X
Failed: X

Phase 5: Coverage Check

cargo llvm-cov --summary-only 2>&1 | tail -10

Target: 85%+ coverage. If below threshold, identify uncovered code.

Phase 6: Security Audit

cargo audit 2>&1 | tail -20

Phase 7: Diff Review

git diff --stat
git diff HEAD --name-only

Review each changed file for:

Unintended changes
Missing error handling (.unwrap(), direct indexing)
Files exceeding 500-600 line guideline
Missing tests for new code paths

Output Format

After running all phases, produce a verification report:

VERIFICATION REPORT
==================

Build:     [PASS/FAIL]
Format:    [PASS/FAIL]
Clippy:    [PASS/FAIL] (X warnings)
Tests:     [PASS/FAIL] (X/Y passed)
Doc Tests: [PASS/FAIL]
Coverage:  [X%] (target: 85%)
Audit:     [PASS/FAIL] (X advisories)
Diff:      [X files changed]

Overall:   [READY/NOT READY] for PR

Issues to Fix:
1. ...
2. ...

Quick Verification (Pre-commit)

For fast checks during development:

just ci-check

This runs the project's standard CI validation suite.

Full CI Verification

Matches what runs in GitHub Actions:

cargo fmt -- --check && cargo clippy -- -D warnings && cargo nextest run && cargo test --doc && cargo audit

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: verification-loop-4description: Comprehensive verification for Rust projects. Runs cargo check, clippy, fmt, tests, coverage, and security audit in sequence. Use when this capability is needed.---# Verification Loop (Rust)## When to Use- After completing a feature or significant code change- Before creating a PR- After refactoring- When you want to ensure all quality gates pass## Verification Phases### Phase 1: Build Verification```bashcargo check 2>&1 | tail -20```If build fails, STOP and fix before continuing.### Phase 2: Format Check```bashcargo fmt -- --check 2>&1 | head -20```If formatting issues found, run `cargo fmt` to fix.### Phase 3: Lint Check```bashcargo clippy -- -D warnings 2>&1 | head -30```All clippy warnings are errors in this project. Fix before continuing.### Phase 4: Test Suite```bash# Run all tests with nextestcargo nextest run 2>&1 | tail -50# Also run doc tests (nextest doesn't run these)cargo test --doc 2>&1 | tail -20```Report:- Total tests: X- Passed: X- Failed: X### Phase 5: Coverage Check```bashcargo llvm-cov --summary-only 2>&1 | tail -10```Target: 85%+ coverage. If below threshold, identify uncovered code.### Phase 6: Security Audit```bashcargo audit 2>&1 | tail -20```### Phase 7: Diff Review```bashgit diff --statgit diff HEAD --name-only```Review each changed file for:- Unintended changes- Missing error handling (`.unwrap()`, direct indexing)- Files exceeding 500-600 line guideline- Missing tests for new code paths## Output FormatAfter running all phases, produce a verification report:```VERIFICATION REPORT==================Build: [PASS/FAIL]Format: [PASS/FAIL]Clippy: [PASS/FAIL] (X warnings)Tests: [PASS/FAIL] (X/Y passed)Doc Tests: [PASS/FAIL]Coverage: [X%] (target: 85%)Audit: [PASS/FAIL] (X advisories)Diff: [X files changed]Overall: [READY/NOT READY] for PRIssues to Fix:1. ...2. ...```## Quick Verification (Pre-commit)For fast checks during development:```bashjust ci-check```This runs the project's standard CI validation suite.## Full CI VerificationMatches what runs in GitHub Actions:```bashcargo fmt -- --check && cargo clippy -- -D warnings && cargo nextest run && cargo test --doc && cargo audit```---> Converted and distributed by [TomeVault](https://tomevault.io/claim/evilbit-labs) — claim your Tome and manage your conversions.

Frequently asked questions

Verification Loop