This is the antidote to "looks good to me" without actually checking. It enforces a verification workflow before claiming anything is done: run existing tests first, fall back to typechecks or narrow commands, and if you have to verify manually, document what you actually observed. The four-tier hierarchy (tests, build, direct commands, manual validation) keeps you honest about what was proven versus what was assumed. Useful when you're working on unfamiliar codebases or want to avoid the classic "it works on my machine" followed by immediate bug reports. It won't let you or Claude hand-wave completion without concrete evidence.

skills.sh installs
698
GitHub stars
40.7K
last updated
Aug 21, 2026

Install

$ npx -y skills add yeachan-heo/oh-my-claudecode --skill verify --agent claude-code

Installs into .claude/skills of the current project.

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

Sponsors

Details

Repository
github.com/yeachan-heo/oh-my-claudecode
First seen
Jun 3, 2026

More from yeachan-heo/oh-my-claudecode

All 37

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs