MUST USE when creating, updating, or managing AI skills and guidelines. Activates when: creating a new skill, editing existing skills, editing any SKILL.md file, editing any file in .ai/ or .claude/skills/ or .github/skills/, updating coding guidelines, modifying AI instructions, or when user mentions: skill, CLAUDE.md, AGENTS.md, guidelines, AI configuration. ALSO activates when about to write or edit a file matching .claude/skills/**/* or .github/skills/**/* — these are generated files that must not be edited directly.
This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.
Install skill "ai-guidelines" with this command: npx skills add hihaho/skillsmp-hihaho-hihaho-ai-guidelines
This source entry does not include full markdown content beyond metadata.
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related by shared tags or category signals.
Runs backend code quality checks in two tiers: Pint + related tests (every change), Pint + PHPStan + Rector + full suite (completion only). Activate after making changes to PHP files, or when user mentions: pint, phpstan, rector, code quality, static analysis, code style, run checks.
Requests an independent code review from OpenAI Codex CLI, critically evaluates its findings, and applies warranted fixes. Activates when: the user says /codex-review, asks for a Codex review, or wants an external AI review of changes.
Evaluate the entire implementation and fix any issues that you find. If you find any issues, please fix them yourself. Only ask the user when you need a decision. Activates when: evaluating implementation, self-reviewing code, checking for issues, or when user mentions: evaluate, check implementation, self-review, verify implementation.
Applies PR review feedback with critical evaluation. Activates when: applying review comments, addressing PR feedback, responding to code review, or when user mentions: review feedback, PR comments, apply feedback, address comments, reviewer feedback.