verify
Verify turns uncertain claims into concrete proof by running existing tests, type checks, and targeted validation commands. It reports exactly what passed, what failed, and what remains unverified—ensuring changes are genuinely complete before you move on.
Verify provides evidence that code changes work by running tests and validation commands before completion.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-27
Verify provides evidence that code changes work by running tests and validation commands before completion. Verify turns uncertain claims into concrete proof by running existing tests, type checks, and targeted validation commands. It reports exactly what passed, what failed, and what remains unverified—ensuring changes are genuinely complete before you move on.
Use it when
- Verify this works means running automated checks—tests, linters, type checkers.
- Verify can identify test coverage gaps by running your existing test suite and reporting which parts of your code lack coverage.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
zereight/gitlab-mcp/verify · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I verify my code changes work?
Verify helps you turn uncertain claims into concrete proof by running existing tests, type checks, and targeted validation commands. Run your test suite, check types, and execute any domain-specific validators tied to your change. Verify reports exactly what passed, what failed, and what remains unverified—so you know your changes are genuinely complete before moving on.
What does verify this works actually mean?
Verify this works means running automated checks—tests, linters, type checkers, and custom validators—to prove your code behaves as intended. Verify collects the results and shows you the evidence: which checks passed, which failed, and which gaps remain. This transforms a vague claim into measurable, documented proof.
Can verify check for test coverage gaps?
Verify can identify test coverage gaps by running your existing test suite and reporting which parts of your code lack coverage. Once gaps are found, you can write targeted tests to fill them. This ensures your changes are backed by concrete test evidence before you mark the task complete.
How does verify validate behavior with concrete evidence?
Verify validates behavior by executing your tests, type checks, and validation commands, then documenting the results. It shows you what passed, what failed, and what wasn't tested. This concrete evidence proves your implementation works—or reveals exactly where it doesn't—before deployment.
What happens when verify finds failures?
When Verify finds failures, it reports them clearly: which checks failed, why they failed, and what needs fixing. This documentation helps you understand what's broken and what to fix next. Verify ensures you see all failures before marking work complete, not after deployment.
Does verify run before task completion?
Yes, Verify is designed to run before you mark a task complete. It proves your code changes work by running tests, checks, and validators. This verification step ensures you have concrete evidence of functionality—and a record of what was checked—before you move forward.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Verify
Turn vague "it should work" claims into concrete evidence.
Workflow
- Identify the exact behavior that must be proven
- Prefer existing tests first
- If coverage is missing, run narrowest direct verification commands
- If direct automation not enough, describe manual validation steps
- Report only what was actually verified
Verification Order
- Existing tests
- Typecheck / build
- Narrow direct command checks
- Manual or interactive validation
Rules
- Do not say a change is complete without evidence
- If a check fails, include the failure clearly
- If no realistic verification path exists, say so explicitly
- Prefer concise evidence summaries over noisy logs
Output
- What was verified
- Which commands/tests were run
- What passed
- What failed or remains unverified
File tree — 1 file
.github/skills/verify/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Verify code changes work before marking task complete”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
UltraQA automates the test-fix loop by running quality checks, analyzing what broke, and applying corrections across up to 5 cycles. Choose your goal—tests, build, lint, or type checking—and let it work toward success. It tracks progress, detects repeated failures, and exits when the goal is met or max cycles reached.
Trace systematically investigates why something happened by generating competing hypotheses and evaluating evidence for and against each one. It's built for ambiguous causal questions—runtime bugs, performance regressions, and architecture issues—where you need to explain the most likely explanation. The skill structures your investigation through observation, hypothesis generation, evidence gathering, and discriminating probes.
Status displays which OMG mode is running and reports its current progress, including active phases, task completion, and agent states. Use it to verify what's executing, monitor advancement through workflows, or confirm state after resuming operations.
UltraQA automates quality assurance by cycling through test execution, failure diagnosis, and targeted fixes until your specified goal succeeds. It supports tests, builds, linting, type checking, or custom verification patterns, with a maximum of five cycles and early exit on repeated failures. The workflow coordinates diagnosis and remediation across multiple agents to streamline the path to passing quality gates.
jat-complete wraps up your active task by running verification checks (tests, lint, type checking), staging and committing your changes with proper formatting, recording context for future agents, and marking the task closed in the system. It handles customer-facing replies when applicable and emits a completion signal to your IDE.
tdd guides you through strict test-driven development using the red-green-refactor cycle: write a failing test, implement minimal code to pass it, then refactor. The skill enforces the discipline of writing tests before production code and provides framework-specific commands for multiple languages.
More skills verification-mastery (MIT) · Fraimz (NOASSERTION)