Menu
Review, test, slop-check, then commit and optionally open a PR. The ship pipeline: one command from "code complete" to "committed and reviewed."
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | uvs-commit |
| description | Review, test, slop-check, then commit and optionally open a PR. The ship pipeline: one command from "code complete" to "committed and reviewed." |
| argument-hint | [commit-message or 'pr'] |
| user-invocable | true |
| allowed-tools | ["Read(*)","Grep(*)","Glob(*)","Write(*)","Bash(git *)","Bash(npm test *)","Bash(npm run test *)","Bash(npm run lint *)","Bash(npx jest *)","Bash(npx vitest *)","Bash(pytest *)","Bash(go test *)","Bash(cargo test *)","Bash(gh pr *)"] |
$ARGUMENTS
!git status --short 2>/dev/null | head -30 || echo "not a git repo"
!git diff --cached --stat 2>/dev/null || echo "nothing staged"
!git diff --stat 2>/dev/null || echo "no unstaged changes"
Find and run the project's test command. If tests fail, fix the failures before continuing. If they can't be fixed in 2 attempts, stop and report.
If a lint command exists (npm run lint, ruff check, etc.), run it. Fix auto-fixable issues.
Scan changed files for the most obvious patterns:
toBeTruthy() / toBeDefined() in test filesexcept: pass in PythonDon't run the full /uvs-review --slop agent — just grep for mechanical patterns.
Read the full diff. Check for:
If you find issues, fix them. If they need human input, stop and ask.
.env, not node_modules, not build artifacts)If the user said "pr" in their arguments, or if on a feature branch:
gh pr createAfter committing, write a checkpoint to latest.md in this session's checkpoint
directory (shown below) with what was committed:
!"${CLAUDE_PROJECT_DIR:-.}"/.claude/hooks/checkpoint-helper.sh dir
!cat DANGER-ZONES.md 2>/dev/null || echo "No DANGER-ZONES.md"
Design system architecture and decompose work into Acts with tasks, dependencies, and cycle budgets. Use after a spec is approved, before coding begins.
Show all UV Suite skills, agents, hooks, guardrails, and personas. Use when you want to know what's available or how to use a specific feature.
Systematic root-cause debugging. Traces data flow, tests hypotheses, narrows scope. Stops after 3 failed attempts and escalates. Use when something is broken and you don't know why.
Toggle lite mode — instructs the assistant to be terse (no preamble, no summaries, no decorative formatting). Use when tokens are limited or you just want shorter answers. Persists across turns until disabled.
Build an interactive prototype as a static React site. For concept exploration, stakeholder demos, presentations, and documentation websites.
Browser-based QA: exercises the running app via Playwright MCP, captures console errors and visual evidence, optionally fixes source bugs with atomic commits and generates regression tests. Three tiers (quick / standard / exhaustive). Writes uv-out/qa-state.md so /uvs-commit and /ship can detect completion and read the health score.