skills/zenith-audit/SKILL.md
High-fidelity quality auditing for the multi-game-engines project. Ensures 100% Zero-Any, security hardening, and physical resilience validation according to 2026 Zenith Tier standards.
npx skillsauth add hdkz-dev/multi-game-engines zenith-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill provides a rigorous, exhaustive auditing protocol to ensure that the codebase meets the absolute highest engineering standards of 2026.
any types in production code.Run this to find illegal manual casts or any usage:
grep -r "as any" packages/*/src
grep -r ": any" packages/*/src
Zenith Rule: No any allowed in production. Use unknown + type guard or branded factory.
Ensure no one is bypassing factories:
grep -r "as (FEN|SFEN|Move|PositionString|PositionId|I18nKey)" packages/*/src
Zenith Rule: All branded types must use createX(...) factories for validation.
Review changed files for the following:
try-catch?positionId?Audit the test coverage and determinism:
# Verify coverage
pnpm test --coverage
# Check for flakiness (deterministic time)
grep -r "performance.now" packages/*/src/__tests__
Zenith Rule: performance.now() must be mocked in tests to ensure deterministic results.
Ensure docs/ and docs/en/ are in sync using the doc-sync skill.
documentation
Maintains 1:1 parity between Japanese and English documentation in the multi-game-engines project. Ensures global architectural alignment.
development
AI-powered code review using CodeRabbit. Default code-review skill. Trigger for any explicit review request AND autonomously when the agent thinks a review is needed (code/PR/quality/security).
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
testing
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).