FlorianBruniaux

Autonomous improvement loop: scan codebase metrics, scaffold experiment files, run agent-driven iterations until metric improves

Post-deploy monitoring: watch production after a deploy and alert on regressions

Systematic root-cause debugging: find the cause before writing any fix

Strategic product gate: challenge the brief, find the 10-star product hiding inside the request, before writing any code

Engineering architecture gate: lock architecture, diagrams, edge cases, and test matrix before writing implementation code

Orchestrates the complete planning pipeline: product direction (ceo-review) -> architecture (eng-review) -> implementation plan (start) -> validation (validate) -> execution (execute). Run stages individually or let the orchestrator coordinate the full flow.

Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop

Clean up stale git worktrees with merged branch detection and disk usage report

Guides and best practices for working with Neon Serverless Postgres. Covers setup, connection methods, branching, autoscaling, scale-to-zero, read replicas, connection pooling, Neon Auth, and the Neon CLI, MCP server, REST API, TypeScript SDK, and Python SDK. Use when users ask about "Neon setup", "connect to Neon", "Neon project", "DATABASE_URL", "serverless Postgres", "Neon CLI", "neonctl", "Neon MCP", "Neon Auth", "@neondatabase/serverless", "@neondatabase/neon-js", "scale to zero", "Neon autoscaling", "Neon read replica", or "Neon connection pooling".

| Production-tested setup for Tailwind CSS v4 with shadcn/ui, Vite, and React. Use when: initializing React projects with Tailwind v4, setting up shadcn/ui, implementing dark mode, debugging CSS variable issues, fixing theme switching, migrating from Tailwind v3, or encountering color/theming problems. Covers: @theme inline pattern, CSS variable architecture, dark mode with ThemeProvider, component composition, vite.config setup, common v4 gotchas, and production-tested patterns.

Audit and improve web accessibility following WCAG 2.1 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".

Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".

Optimize Core Web Vitals (LCP, INP, CLS) for better page experience and search ranking. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS", "optimize INP", "page experience optimization", or "fix layout shifts".

Orchestrate a 4-agent cyber defense pipeline to analyze log files for threats. Use when investigating security logs, detecting anomalies in access patterns, classifying breach severity, or generating incident reports from nginx/auth/syslog files.

Use when analyzing a codebase for GoF design patterns, or when refactoring and needing pattern suggestions. Stack-aware (TypeScript/React/Next.js adaptations).

Optimize web performance for faster loading and better user experience. Use when asked to "speed up my site", "optimize performance", "reduce load time", "fix slow loading", "improve page speed", or "performance audit".

Build terminal UIs in Rust with Ratatui. Use when creating TUI applications, immediate-mode rendering, high-performance terminal interfaces, or production Rust CLIs.

Expert Rust idiomatique pour développement CLI/système. Ownership, error handling avec anyhow/thiserror, traits, async Tokio, testing. Utiliser pour coder, reviewer ou refactorer du Rust.

Analyze Rust codebase for design patterns, idioms, and anti-patterns. Provides detection, suggestion, and evaluation modes for Rust code quality. Keywords: rust, patterns, analysis, idioms, anti-patterns, code-quality

Security audit toolkit for the ccboard project (Rust/Leptos/Axum stack). Use when auditing authentication flows, API endpoints, WASM security, or reviewing Rust code for unsafe usage and memory safety issues.

Optimize web performance for faster loading and better user experience. Use when asked to "speed up my site", "optimize performance", "reduce load time", "fix slow loading", "improve page speed", or "performance audit".

Expert senior en architecture backend pour accompagner le développement (conception, implémentation, review, refactoring). Architecture hexagonale, DDD, SOLID, clean code, tests. Utiliser pour concevoir de nouvelles features, développer du code, reviewer, refactorer, ou résoudre des problèmes architecturaux.

Store a fix, pattern, or context note in Brain knowledge base (~/.ccboard/insights.db). Use when you want to remember a fix, pattern, decision, or context note across sessions.

Simplifie et raffine le code pour clarté, cohérence et maintenabilité. AUTO-SUGGEST: Activer quand détection de code complexe (imbrication >3, fonctions >50 lignes, ternaires imbriqués, DRY violations).

Autonomous improvement loop: scan codebase metrics, scaffold experiment files, run agent-driven iterations until metric improves

Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when onboarding to a project with existing agents, after adding new agents to a fleet, or when an orchestrator consistently selects the wrong agent.

Post-deploy monitoring: watch production after a deploy and alert on regressions

Clean up stale git worktrees with merged branch detection and disk usage report

Safely remove a git worktree with branch cleanup and safety checks

Create isolated git worktrees for feature development without switching branches

Check status of background verification tasks running in a git worktree

Display native sandbox status, configuration, and recent violations

Measure how Google AI Overviews are cannibalizing organic CTR. Use when asked about AI Overview impact, SGE cannibalization, or why CTR is dropping despite stable rankings.

Detect keyword cannibalization, meaning queries where multiple pages compete for the same rankings. Use when asked about competing pages, keyword overlap, or cannibalization.

Find content optimization targets across two zones: striking distance

Audit indexing status with a site-wide overview first, then per-page deep-dive on top pages. Use when asked about crawling, indexing issues, or whether pages are indexed by Google.

Full diagnostic for a single URL combining indexing status, search performance, Core Web Vitals, and query breakdown. Use when asked to analyze a specific page or diagnose why a particular URL is underperforming.

Audit structured data (schema markup) across the top pages to surface errors blocking rich results eligibility. Use when asked about rich results, schema errors, or structured data health.

Generate a complete weekly SEO performance report for a site, including alerts, anomalies, and period-over-period comparison. Use when asked for a site summary, performance overview, or weekly report.

Audit sitemap health and coverage across all submitted sitemaps. Use when asked about sitemap issues, submitted vs. indexed counts, or sitemap errors.

Use when turning a GitHub profile analysis into an actionable score. Produces a /100 grade weighted by the author's detected objective, a green/orange/red signal table, ready-to-paste corrective prompts, and a shareable score card. Triggers on "note ce profil", "score my github", "is my profile good for getting hired".

Use when evaluating the quality of a GitHub README, judging whether it reads as human-written or AI-generated, and producing concrete fixes. Triggers on requests like "eval this README", "is this readme AI-generated", "review my repo readme".

Use when analyzing a GitHub profile through the lens of its author's objective (build a flagship, raise funds, get hired, run a business). Reads repos, pinned items, contribution timeline and commits, then produces a structured profile sheet. Triggers on "analyse ce profil GitHub", "what does this GitHub profile say", "audit my github".

Use when turning a GitHub/LinkedIn analysis into a concrete next-step plan, branching on the user's goal. Two tracks, getting hired and spreading a project. Triggers on "et maintenant je fais quoi", "what next", "je cherche du taf", "je veux diffuser mon projet".

Use when improving the findability of a GitHub profile and its repos. Generates keyword-rich repo descriptions and topics, optimizes the profile bio for search, and proposes cross-platform linking. Triggers on "améliore mes keywords", "make my repo findable", "seo for my github".

Use when analyzing a LinkedIn profile that the user provides themselves (screenshots and pasted text), and cross-checking it with their GitHub. Never scrapes LinkedIn. Triggers on "analyse mon LinkedIn", "is my linkedin aligned with my github", "review my linkedin profile".

Entry point skill file

Audit .claude/rules/ files for structural correctness, glob validity, and real-world usefulness. Resolves each paths: pattern against actual project files, then asks whether each rule is still relevant. Can update rules in-place. Use when setting up rules for the first time, debugging rules that fire too often or never, or doing a periodic rules hygiene pass.

Audit all skills in .claude/skills/ for frontmatter completeness, effort level appropriateness, allowed-tools scoping, and content quality. Produces a scored report with effort-level recommendations for each skill. Use when onboarding, reviewing skill quality before shipping, or adding effort fields to an existing skill library.

Audit Claude Code configuration to measure fixed-context token overhead and produce a prioritized action plan. Use when sessions feel slow, context compresses early, or after adding many rules files.

Sync Codex Cowork releases from local CHANGELOG to guide YAML + landing TypeScript

Product watch — trouve les features Codex desktop non documentées, génère des entrées CHANGELOG