create-verification-skill
Generate the project's own verify skill: build/test/lint commands discovered by running them, a feature map of what each covers, manual checks, and an earned first verdict. Run once per repo.
How do I install this agent skill?
npx skills add https://github.com/yeachan-heo/oh-my-claudecode --skill create-verification-skillIs this agent skill safe to install?
- Gen Agent Trust Hubpass
This skill automates the creation of a verification workflow by discovering and executing build, test, and lint commands found within a repository. While useful for developers, it introduces a risk of indirect prompt injection because the agent will execute any command it finds in project configuration files (like package.json or Makefiles). Users should only run this skill on trusted repositories.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Create Verification Skill
The bundled verify skill demands evidence but cannot know this repo's
commands. This skill generates the project-local verify skill that makes
verification concrete — by discovering the commands through execution, not
by guessing from a README.
When to use
- a repo has no
.claude/skills/verify/and work will be verified here more than once - the generic verification flow keeps guessing commands wrong for this repo
Workflow
- Discover by running. For each candidate surface — build, test, lint,
typecheck, format, dev server, e2e — find the command (package scripts,
Makefile, CI config) and run it. Record the real invocation, the
expected passing output shape, the runtime, and the known gotchas
(env vars, seed data, order dependence). A command you have not run is a
hypothesis, not a check. Write-mode formatters (
prettier --write,eslint --fix) mutate tracked files — record the read-only check form (prettier --check,eslint --check) as the verification command, never the mutating one. - Record the manual surface. What cannot be checked by command here:
the pages or flows a human (or
run/visual-verdict) exercises, and what "looks right" means for each. - Write the feature map. A table of what each check actually covers — which entry points, which layers, what it cannot see. The map is the skill's honesty: verification strength is knowable, not assumed.
- Generate
.claude/skills/verify/SKILL.mdcontaining: the exact commands with expected outcomes, the manual checks, the feature map, and the escalation path (which failure means what, who owns it). Keep it short enough that a fresh session reads it whole. If a verify skill already exists at the canonical root (.omc/skills/verify/SKILL.mdor.claude/skills/verify/SKILL.md), respect it: update its commands and feature map in place rather than overwriting, and say what changed. - Prove it. Run the generated skill's own flow once end to end on a
real change and record the result through the ledger's locked writer —
appendLedgerEntryanddefaultLedgerPathfrom the installed package'sdist/features/verification-ledger/index.js(babysit's ledger step demonstrates the exact invocation); never append raw rows to.omc/state/verification-ledger.tsv— the writer owns header creation, locking, and cell sanitization. The verdict is the one the flow actually earned: a real UI exercised islive-ui-verified, a test suite run isunit-test-verified, only build/lint/typecheck passed istype-check-only, and nothing runnable is no positive row at all.
Rules
- Every command in the generated skill was executed this session, or is marked unverified with the reason.
- The generated skill verifies; it never fixes. Fixes route to
execute. - When the repo's commands change shape,
maintain-verification-skillre-syncs this artifact.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/yeachan-heo/oh-my-claudecode/create-verification-skill">View create-verification-skill on skillZs</a>