Menu
Quick project health check — git state, test results, lint status, build status. One-shot overview.
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 | status |
| description | Quick project health check — git state, test results, lint status, build status. One-shot overview. |
| argument-hint | [optional: specific check — 'tests', 'lint', 'git', or blank for all] |
| user_invocable | true |
| tools | Read, Glob, Grep, Bash |
| model | sonnet |
Run a quick health check on the current project. Reports git state, test results, lint status, and build status in one shot.
$ARGUMENTS
If $ARGUMENTS is empty, run all checks. If a specific check is named, run only that one.
git status --short
git log --oneline -5
git branch --show-current
git stash list
Report: branch, uncommitted changes count, recent commits, any stashes.
Auto-detect and run the appropriate test command:
Cargo.toml → cargo test 2>&1pyproject.toml / pytest.ini → pytest -v 2>&1package.json (test script) → npm test 2>&1go.mod → go test ./... 2>&1*.bats → bats test/ 2>&1Report: pass/fail/skip counts, any failures summarized in one line each.
cargo clippy -- -D warnings 2>&1ruff check . 2>&1shellcheck scripts/*.sh hooks/*.sh 2>&1 (if applicable)Report: clean or number of warnings/errors.
cargo build 2>&1python -m py_compile on changed filesnpm run build 2>&1 (if build script exists)Report: success or failure with error summary.
## Project Status: [project name]
| Check | Status | Details |
|--------|--------|---------|
| Git | OK/WARN | [branch], [N uncommitted], [N stashes] |
| Tests | PASS/FAIL | [X pass, Y fail, Z skip] |
| Lint | CLEAN/WARN | [N issues] |
| Build | OK/FAIL | [summary] |
### Issues (if any)
1. [issue summary]
Keep it concise — this is a dashboard, not a deep dive. Under 30 lines of output.
Commit all changes, push to remote, and open a pull request in one shot. The most common inner-loop workflow.
Clean start for a new task. Saves important decisions, clears context, and re-reads project config.
Resume work from a previous session. Reads MEMORY.md and continues autonomously.
Adversarial code review — stress-tests recent changes by hunting for bugs, edge cases, security holes, and design flaws. Spawns parallel attack agents, consolidates into a severity-rated report.
Debug and investigate issues — trace symptoms to root cause. Use when something is broken, a test fails mysteriously, or behavior is unexpected.
Prove that the current implementation works. Runs tests, diffs behavior, validates correctness. Use after implementing a feature or fix to verify before marking complete.