ai-verify
Performs multi-dimensional release-readiness verification to confirm if code is ready to ship.
Install
mkdir -p .claude/skills/ai-verify && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14876" && unzip -o skill.zip -d .claude/skills/ai-verify && rm skill.zipInstalls to .claude/skills/ai-verify
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when verification with evidence is needed — not assumptions. Trigger for 'check my code', 'is this ready to merge', 'run the tests', 'is coverage good enough', 'scan for security issues', 'does this meet our standards', 'prove it works', 'is this ready to ship', 'run the release checks', 'pre-release checklist', 'GO/NO-GO'. Runs 2 specialists post-W3 (deterministic, acceptance) with `normal` implicit and `--full` explicit; the `--release` mode flag aggregates 8-dimension release readiness (coverage, security, tests, lint, dependencies, types, docs, packaging) and emits GO/CONDITIONAL GO/NO-GO. For narrative code review with human judgment, use /ai-review instead.Key capabilities
- →Verify code against 8 dimensions for release readiness
- →Scan code for security issues using gitleaks, semgrep, and pip-audit
- →Check test coverage and linting status
- →Aggregate findings from deterministic and acceptance specialists
- →Provide a GO/CONDITIONAL GO/NO-GO verdict for releases
- →Run quality checks during implementation
How it works
The skill runs a verification protocol that identifies commands per claim, executes them, captures output and exit codes, and classifies results as CONFIRMED or REFUTED. It dispatches specialists to aggregate deterministic evidence into merge-readiness judgments.
Inputs & outputs
When to use ai-verify
- →Verify code for release
- →Run pre-release checks
- →Check code readiness to merge
- →Validate coverage and security
About ai-verify
Runs a multi-specialist verification protocol evaluating coverage, security, tests, and linting. Emits a definitive GO/NO-GO verdict for releases.
Use when verification with evidence is needed — not assumptions. Trigger for 'check my code', 'is this ready to merge', 'run the tests', 'is coverage good enough', 'scan for security issues', 'does this meet our standards', 'prove it works', 'is this ready to ship', 'run the release checks', 'pre-re
When not to use it
- →When narrative code review with human judgment is needed
- →When assuming success without running commands
- →When ignoring warnings despite a zero exit code
Limitations
- →Does not perform narrative code reviews
- →Does not add specialist coverage when using the --full flag, only changes decomposition
- →Does not modify code
How it compares
This skill provides an evidence-based, automated verification protocol for code readiness, unlike manual checks that rely on assumptions.
Compared to similar skills
ai-verify side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ai-verify (this skill) | 0 | 2mo | No flags | Intermediate |
| verify | 6 | 6mo | No flags | Beginner |
| code-change-verification | 4 | 4mo | Review | Beginner |
| springboot-verification | 4 | 4mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by arcasilesgroup
View all by arcasilesgroup →You might also like
verify
Use when you want to validate changes before committing, or when you need to check all React contribution requirements.
code-change-verification
openai
Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository.
springboot-verification
affaan-m
Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
moai-workflow-testing
modu-ai
Comprehensive development workflow specialist combining DDD testing, debugging, performance optimization, code review, PR review, and quality assurance into unified development workflows
resolve-checks
flowglad
Resolve all failing CI checks and address PR review feedback on the current branch's PR. Runs tests locally, fixes failures, incorporates valid review comments, and resolves addressed feedback. Use when CI is red, after receiving PR feedback, or before merging.
verification-quality-assurance
ruvnet
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.