Verify
- 311 installs
- 38.3k repo stars
- Updated August 4, 2026
- yeachan-heo/oh-my-claudecode
verify is a Claude Code skill from oh-my-claudecode that forces agents to prove a feature, fix, or refactor works by running tests, builds, and targeted commands before claiming completion.
About
verify is a completion-gate skill from yeachan-heo/oh-my-claudecode that replaces vague it-should-work claims with concrete evidence. The SKILL.md defines a five-step workflow: identify the exact behavior to prove, prefer existing tests first, run the narrowest direct verification command if coverage is missing, gather manual validation steps when automation is insufficient, and report only what was actually verified. The verification order runs existing tests, then typecheck or build, then narrow direct commands, then manual checks. Developers and agents invoke verify when a user wants confidence that a feature, fix, or refactor truly works before marking a task done or opening a pull request.
- Tool support
- Integration
Verify by the numbers
- 311 all-time installs (skills.sh)
- +16 installs in the week ending Jul 20, 2026 (Skillselion tracking)
- Ranked #139 of 782 Skill Development skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/yeachan-heo/oh-my-claudecode --skill verifyAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 311 |
|---|---|
| repo stars | ★ 38.3k |
| Last updated | August 4, 2026 |
| Repository | yeachan-heo/oh-my-claudecode ↗ |
How do you verify a code change actually works?
Extend Claude Code
Who is it for?
Developers and coding agents who need a structured pre-completion checklist so fixes are backed by test, build, or command evidence.
Skip if: Greenfield exploration with no defined expected behavior or tasks where the user only wants architectural advice without runnable verification.
When should I use this skill?
The user wants confidence a feature, fix, or refactor works, or before claiming a coding task is complete.
What you get
Test run logs, build or typecheck results, direct command output, and a report listing only verified behaviors.
- Verification evidence report
- Test and build command output
By the numbers
- Defines a 5-step verification workflow
- Uses a 4-tier verification order: tests, typecheck/build, direct commands, manual checks
Files
Verify
Use this skill when the user wants confidence that a feature, fix, or refactor actually works.
Goal
Turn vague “it should work” claims into concrete evidence.
Workflow
1. Identify the exact behavior that must be proven. 2. Prefer existing tests first. 3. If coverage is missing, run the narrowest direct verification commands available. 4. If direct automation is not enough, describe the manual validation steps and gather concrete observable evidence. 5. Report only what was actually verified.
Verification order
1. Existing tests 2. Typecheck / build 3. Narrow direct command checks 4. 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 that explicitly instead of bluffing.
- Prefer concise evidence summaries over noisy logs.
Output
- What was verified
- Which commands/tests were run
- What passed
- What failed or remains unverified
Related skills
Find SkillsSo their agent can intelligently recommend and install the right modular skills from the open ecosystem when they ask how to do something.3M27.9k
Lark Skill MakerRapidly create custom skills for Lark (Feishu) that can be invoked by their AI agents and automation workflows.513k
Skill CreatorGenerate, test, and iterate on new reusable agent skills directly inside their Claude or Cursor workflow.337k166k
BrainstormingTurn vague product ideas into clear, approved designs and specifications through guided collaborative dialogue before writing any code.307k265k
Writing Great SkillsCreate high-quality, reusable agent skills that other developers can discover and install from the Skillselion catalog.290k200k
Find SkillsInstantly surface the best relevant agent skills, MCP servers, and workflows across multiple registries before starting any new project.226k12How it compares
Pick verify over generic testing skills when you need a lightweight completion gate that sequences existing tests and builds before claiming done.
FAQ
What is the verify skill verification order?
verify runs existing tests first, then typecheck or build, then the narrowest direct verification command available. If automation is insufficient, verify documents manual validation steps and collects observable evidence before reporting.
When should verify activate in Claude Code?
verify activates when a user wants confidence that a feature, fix, or refactor actually works. The skill turns vague completion claims into a structured evidence-gathering workflow before the agent reports done.
What does verify require in the final report?
verify mandates reporting only what was actually verified—test passes, build success, command output, or documented manual checks. Unverified assumptions must not be presented as completed work.