audit-core-loop

Core Loop Audit

Audit the Core Loop phase (Phase 1) of a Game Design Bible for quality, completeness, and correctness. Each issue is presented to the user one at a time with multiple resolution options, always including a research option that forks parallel web research agents.

Input

$ARGUMENTS

Parse Arguments

Extract from $ARGUMENTS:

• Bible Directory: First non-flag argument (default: docs/game-design-bible/)
• Context File Path: --context <path> (optional, enables context fidelity checks)

Process

Phase 1: Load Documents

1. Read <bible-dir>/01-core-loop/core-loop.md.
2. Read <bible-dir>/01-core-loop/prototype-spec.md.
3. Read <bible-dir>/DESIGN-PILLARS.md — extract all pillar names.
4. If --context provided, read the context file.
5. Read the audit checklist at ${CLAUDE_SKILL_DIR}/references/checklist.md.

If core-loop.md does not exist, inform the user: "No core loop documents found at <bible-dir>/01-core-loop/. Generate them first with /game-design-bible:core-loop-generate." — then STOP.

Phase 2: Run All Checks

Run every check from the checklist against the core loop documents. For each check, record:

• Check name and category
• Status: PASS, WARN, or FAIL
• Details: What was found (or not found)
• Severity: 🔴 CRITICAL, 🟡 WARNING, or 🔵 INFO
• Suggested fix: How to resolve

Also scan for open questions: TODO, TBD, FIXME, [ASSUMPTION], vague/placeholder text, or any unresolved items.

Build a prioritized issue queue ordered:

1. 🔴 CRITICAL issues first
2. 🟡 WARNING issues next
3. 🔵 INFO issues last
4. ❓ Open Questions last

Phase 3: Present Summary

Show the user the full breakdown before diving in:

## Core Loop Audit Summary: [Game Name]

**Bible Directory:** [bible-dir]
**Context file:** [path or "not provided"]

Found **N issues** and **M open questions**:
- 🔴 CRITICAL: [count] — must fix before proceeding
- 🟡 WARNING: [count] — should fix
- 🔵 INFO: [count] — optional improvements
- ❓ Open Questions: [count]

Starting sequential resolution...