Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From r-skills
Run full R verification loop before committing. Checks build, lint, style, test coverage, and code quality.
npx claudepluginhub ab604/claude-code-r-skills --plugin r-skillsHow this command is triggered — by the user, by Claude, or both
Slash command
/r-skills:verifyThe summary Claude sees in its command listing — used to decide when to auto-load this command
# /verify - R Verification Loop Run all quality gates before committing code. Produces a READY or NOT READY verdict. ## When to Use - Before every commit - After implementing a feature or fix - Before opening a pull request - Any time you want a full quality check ## Verification Phases Run each phase in order. A failure in any phase blocks the verdict. ### Phase 1: Build Check Pass criteria: 0 errors, 0 warnings, 0 notes (or only expected notes). ### Phase 2: Style Check Auto-fixes style. Re-check for any manual fixes needed. ### Phase 3: Lint Check Pass criteria: 0 lints....
/verifyRuns full verification pipeline: build, type check, lint, tests, security scan, git status. Outputs structured phased PASS/FAIL report with next steps.
/verifyVerifies code changes before completion claims by auto-detecting stack, running tests/lints/type-checks/builds, and providing checklists with actual outputs.
/verifyRuns a structured verification pass across implementation, quality, and risk, producing structured results with assumptions, risks, open questions, and follow-ups.
/double-checkVerifies recent code changes via git status/diffs and runs ecosystem-specific quality gates (tests, lint, typecheck, build), reporting results in a table. Supports --deep multi-agent review.
/fire-double-checkVerifies work completion claims by running npm build, test, typecheck, and lint checks on current work or specified target, reporting results with evidence and exit codes.
/verifyVerifies branch code via tests, lint (auto-fix option), type-check, visual review, and simplification. Produces phase statuses (passed/failed/skipped), overall status, and evidence paths.
Share bugs, ideas, or general feedback.
Run all quality gates before committing code. Produces a READY or NOT READY verdict.
Run each phase in order. A failure in any phase blocks the verdict.
devtools::check(quiet = TRUE)
Pass criteria: 0 errors, 0 warnings, 0 notes (or only expected notes).
styler::style_pkg()
Auto-fixes style. Re-check for any manual fixes needed.
lintr::lint_package()
Pass criteria: 0 lints. Fix all flagged issues before proceeding.
covr::package_coverage()
Pass criteria: ≥80% overall coverage. Critical paths (validation, stats) require 100%.
Invoke the code-reviewer agent to check uncommitted changes:
/code-review
Pass criteria: No CRITICAL or HIGH issues.
git diff --stat HEAD
git diff HEAD
Manually confirm:
print()/cat() left in## Verification Report
| Phase | Status | Notes |
|----------------|--------|--------------------------------|
| Build check | ✅ PASS | 0 errors, 0 warnings |
| Style check | ✅ PASS | Auto-fixed 3 files |
| Lint check | ✅ PASS | 0 lints |
| Test coverage | ✅ PASS | 87% overall |
| Code review | ✅ PASS | No CRITICAL/HIGH issues |
| Diff review | ✅ PASS | Changes look correct |
## Verdict: ✅ READY TO COMMIT
Next step: commit with a descriptive message.
Or if issues found:
## Verdict: ❌ NOT READY
**Blocking issues:**
1. [Phase] - [specific issue]
2. [Phase] - [specific issue]
Fix all blocking issues and re-run /verify.
| Code Type | Required |
|---|---|
| General logic | ≥80% |
| Statistical calculations | 100% |
| Input validation | 100% |
| Error handling | 100% |
/plan - Plan before implementing/tdd - Write tests first/code-review - Standalone code review