SanderMuller

Self-directed eval loop: review own implementation, fix issues found, re-evaluate until clean, then run code review. Fix yourself; only ask the user for decisions. Activates when: evaluating implementation, self-reviewing code, checking for issues, or when…

Requests an independent code review from OpenAI Codex CLI, critically evaluates its findings, applies warranted fixes, and re-reviews until clean. Activates when: the user says /codex-review, asks for a Codex review, or wants an external AI review of changes.

Pre-push / pre-release checklist. Runs Rector, Pint, full test suite, PHPStan, and audits README, the docs site (docs/ pages, index sync, local build), and `.ai/` docs for staleness. Activate before: pushing to remote, tagging a release, writing release…

Author and maintain a high-quality README for a Composer package. Covers stub, comprehensive, and docs-site shapes (thin README + a docs/ site, for example VitePress on GitHub Pages), voice, staleness audits, and docs index/link sync.

Command-only — invoke with `/eye-verification`; never activates on its own. Drives a frontend change in a real browser as the whole job, not one step of a quality gate: resolves the testables (PR body, tracker issue, spec edge cases, or gathered from the…

Frontend quality checks: TypeScript type check, linting, and the JS test suite (Vitest/Jest). Activate after editing JS/TS files. Triggers: eslint, typescript, tsc, type check, lint, vitest, jest, test:js, frontend tests, frontend checks.

Applies PR review feedback with critical evaluation, then replies to and resolves the threads. Covers automated reviewers (Copilot, CodeRabbit, etc.). Activates when applying review comments, addressing PR feedback, responding to code review, or resolving…

Creates and manages your own GitHub PRs via the gh CLI — analyze commits, write the PR description, create, verify, request review, route by risk. Activates when: creating or opening a PR, submitting work for review, writing or updating a PR description, or…

Use when prepping package release, `.gitattributes` missing/thin, or keeping `composer archive` / Packagist `--prefer-dist` tarballs lean. Activates: lean dist, gitattributes, export-ignore, dist size, packagist tarball, composer archive bloat,…

Use when developing Laravel packages with Orchestra Testbench. Activates: writing package code, running package tests, working with testbench, configuring service providers; mentions: package, testbench, package development, service provider.

MUST USE when authoring an AI skill — creating a new SKILL.md, naming a skill, or deciding where one lives. Covers namespacing across host/vendor/shipped skills, auto-activating frontmatter, `.ai/skills/` vs `resources/boost/skills/` choice, and `boost sync`…

Pre-push / pre-release checklist. Local quality gates → docs audit → commit + push → watch CI → draft release notes once CI is green. Activate before: pushing release-bound commits, tagging a release, drafting release notes, or when user mentions:…

Use when CI matrix has gone red and needs diagnosis. Activates: ci matrix fail, matrix red, prefer-lowest fail, prefer-stable fail, dependency conflict, composer resolve, version excluded, security-advisories floor, testbench phpunit interlock, matrix cell…

Use when writing/reviewing package code spanning multiple Laravel or PHP majors. Activates: adding dependency, framework API across range, composer constraints, version-guarded code; mentions: composer constraint, illuminate/support version, laravel version…

Use when writing or improving README files. Covers required sections, structure, voice, staleness-audit pattern. Laravel-package conventions in `references/laravel-package.md`. Activates: writing a README, improving an existing README, auditing a README for…

Use when drafting GitHub release bodies from a tag range or staged changes. Default: GitHub's auto-generated format; override only on major/breaking. Laravel notes in `references/laravel-package.md`. Activates: writing release notes, drafting a release…

Pre-push / pre-release checklist. Runs Rector, Pint, Pest, PHPStan, audits README + `.ai/` docs for staleness, then commits + pushes, watches CI for green, and drafts release notes against the verified SHA. Activate before: pushing to remote, tagging a…

Profile a slow request, command, or code path with sandermuller/stopwatch. Activate when the user mentions: slow request, slow endpoint, slow page, slow query, slow job, slow command, slow API call, slow HTTP, performance issue, profile this, why is this…

MUST USE when creating, updating, or managing AI skills and guidelines. Activates when: creating a new skill, editing existing skills, updating coding guidelines, modifying AI instructions, working with .ai/ directory, or when user mentions: skill, CLAUDE.md,…

Autonomous performance optimization loop. Iteratively reduces query count and execution time by modifying code, benchmarking, and keeping/reverting changes. Activates when: optimizing performance, reducing overhead, improving execution time, benchmarking, or…

Runs backend code quality checks in two tiers: Pint + related tests (every change), PHPStan + full suite (completion only). Activate after making changes to PHP files, or when user mentions: phpstan, pint, code quality, static analysis, code style, run checks.

Test-driven bug fixing workflow. Activates when: fixing bugs, debugging issues, resolving defects, investigating errors, or when user mentions: bug, fix, broken, not working, error, issue, defect, regression.

Reviews recent code changes for improvements across functionality, code quality, security, and testing. Activates when: the user asks to review implementation, review changes, review code, audit code, check for improvements, or when user mentions: review,…

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.

Pre-push / pre-release checklist. Runs Rector, Pint, Pest, PHPStan, audits README + `.ai/` docs for staleness, then commits + pushes, watches CI for green, and drafts release notes against the verified SHA. Delegates README staleness audit to the `readme`…

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,…

Runs backend code quality checks in two tiers: Pint + related tests (every change), PHPStan + full suite (completion only). Activate after making changes to PHP files, or when user mentions: phpstan, pint, code quality, static analysis, code style, run checks.

Implements a specification file phase-by-phase with progress tracking. Activates when: implementing a spec, building from a spec, starting a spec phase, or when user mentions: implement spec, spec file, implement phase, build spec, start phase.

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.

Writes implementation-ready specification files with progress-trackable phases. Activates when: writing a spec, creating a spec file, documenting a feature plan, or when user mentions: write spec, create spec, spec format, spec template.

FluentRule builders for Laravel validation. Activates when: writing/modifying rules in FormRequest, Livewire component, or Validator; user mentions FluentRule, HasFluentRules, HasFluentValidation, fluent validation.

FluentRule in Livewire components via HasFluentValidation trait. Activates when: writing Livewire validate(), rules() in Component, assertHasErrors, or Livewire validation.

Migrate FormRequest `messages(): array` to inline `message:` on fluent chains. Dry-run, then apply. Activates when: user mentions migrate messages, messages array, inline message, remove messages().

Scan validation for fluent upgrades: missing HasFluentRules, convertible string rules, label() and each() opportunities. Activates when: optimizing/migrating validation, converting to fluent rules, validation performance.

Use dependency injection cleanly in PHP applications. Constructor injection, avoiding service locators, what to put in the container.

Add modern PHP code to a legacy 7.x codebase incrementally. Typed properties, readonly, enums — how to introduce them without forcing a big-bang upgrade.

Author a boost.php config file. Covers all five with* methods, when each matters, and what NOT to put in there.

Implement a FileEmitter for boost-core to emit a custom file (e.g. .mcp.json, .editorconfig) into the host project during boost:sync.

Write boost-core skill files — frontmatter shape, skill tags, collision guards, source-dir selection, body content.

Keep the published Composer archive lean by excluding dev/test/AI dirs via .gitattributes.

Implement a FileEmitter for boost-core to emit a custom file (e.g. .mcp.json, .editorconfig) into the host project during boost:sync.

Invoke-only — run with `/richter-setup` or when asked to set up/configure richter; never activates on its own. Inspects a Laravel project and proposes config/richter.php (entry-point roots, dispatch helpers, base branch, frontend, Brain security), and…

Invoke-only — run with `/richter-review` or when asked to review a branch with richter; never activates on its own. Graph-backed branch review: runs richter's change-impact report, triages the reached entry points (unexpected reach, missing test references,…

Contribute to a repository you do NOT own or maintain (open source, an upstream you forked, another team). Use when opening or preparing a PR/patch to a foreign repo, or when the user mentions: contribute upstream, open-source PR, send a patch, fix in someone…

Write or change a static-analysis / refactoring rule in the rector/symplify/Tomas ecosystem — a Rector rule, a PHPStan rule, or a symplify/phpstan-rules rule. Activate when: adding or modifying a rule, "write a rector rule", "add a phpstan rule", "new…

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,…

Pre-push / pre-release checklist for laravel-queue-insights. Runs Rector, Pint, Pest, PHPStan, audits README + `.ai/` docs for staleness, then commits + pushes, watches CI for green, and drafts release notes against the verified SHA. Activate before: pushing…

Pre-push / pre-release checklist. Runs Rector, Pint, full test suite, PHPStan, and audits README + `.ai/` docs for staleness. Activate before: pushing to remote, tagging a release, writing release notes, or when user mentions: pre-release, pre-push, release…

Build Rector PHP rules that transform PHP code via AST. Use when asked to create, modify, or explain Rector rules for PHP code transformations. Rector rules use the PHP-Parser AST and PHPStan type analysis. Triggers on requests like "write a Rector rule…

Pre-push / pre-release checklist for laravel-queue-insights. Runs Rector, Pint, Pest, PHPStan, audits README + the `docs/` site + `.ai/` docs for staleness (including a local VitePress build), then commits + pushes, watches CI for green, and drafts release…