
Onboard a project repository to the Codemate VPS multi-project hosting stack (vps-infra, Hetzner-hosted, shared Traefik + per-project rootless Docker). Use when the user asks to "deploy this project to the vps", "onboard on codemate-vps", "add this repo to the production VPS", "setup GHA deploy to my VPS", or when the user is clearly preparing a project (PHP/Symfony, Node, Python, Go, static) for hosting on codemate.consulting. Produces a production compose.yml, a GitHub Actions deploy workflow, and a clear out-of-repo checklist covering Ansible inventory, DNS (Gandi), GitHub secrets, and VPS .env seeding. Do NOT use for the vps-infra repo itself (which hosts the Ansible roles) — this skill is for the downstream project repos.
Analyse-Explore-Plan methodology for thorough analysis and planning before development. Use when starting a new feature, investigating a problem, or needing to understand a codebase before making changes. Provides structured workflow with parallel exploration agents and clarification questions. Integrates with Architect skill for high-quality implementation plans. Do NOT use for ticket-based planning (use /resolve <ticket> --plan-only instead) or when a saved plan is needed (use /create-plan instead).
Synchronize the markdown test plan in docs/qa/ with the current state of the codebase. Use after adding or modifying features to keep the plan up to date, or to bootstrap a test plan for the first time. Do NOT use to execute tests (use /qa-run instead) and do NOT use to design product specs (use /express-need instead).
Internal helper called by /resolve. Analyzes ticket complexity (SIMPLE, MEDIUM, COMPLEX) to determine exploration depth and planning approach. Not intended for direct invocation.
Create a project-scoped MCP server that exposes Docker Compose services as named tools. Use when a project has a docker-compose.yml and the user wants to create MCP tools for running commands like linting, testing, database queries, or any docker compose exec operation. Triggers: "create MCP tools", "expose docker tools", "setup project tools", "mcp server for docker", "docker tools for Claude".
Interactive wizard for configuring ticket resolution workflow. Creates .claude/ticket-config.json with source, branch, and complexity settings.
Create a ticket in YouTrack or GitHub based on project config. Use when the user asks to create a ticket, new issue, or add a task, or provides a structured spec. Can invoke product-analyst agent to structure raw ideas before submission. Do NOT use for unstructured need expression (use express-need skill instead).
Comprehensive PR review (product + technical) with optional GitHub inline comments. Use when user asks to "review PR", "review pull request", gives a PR number to review, or says "review #123". Works on any PR state: open, draft, merged, closed. Fetches linked ticket/issue, runs product and technical review, then optionally posts the review with inline comments to GitHub. Do NOT use for reviewing current branch changes (use deep-review skill instead).
Method to diagnose and raise the Lighthouse performance score of a public page (landing, marketing, home). Use when asked to improve Lighthouse/PageSpeed scores, when auditing the first uncached paint of a public page, or when a landing embedded in a SPA must reach a top score. Do NOT use for in-app screen performance (data loading, rendering). For a brand-new landing, the first recommendation is static HTML with no framework runtime — most of this skill exists for when that is not an option.
Transform a raw need into a well-defined spec, break it into atomic tickets, and create them. Delegates to product-analyst agent with scout/interview/synthesis flow, then proposes task breakdown with /create-ticket. Use when the user has a raw idea, feature request, or unstructured need. Do NOT use when the user already has a clear ticket spec (use /create-ticket directly).
Resolve git rebase conflicts methodically. Classifies each conflict (imports/namespace cleanup vs real logic clash), analyzes the commit introducing the change against the current ticket context, auto-fixes only trivial cases with a per-file summary, and asks the user when ambiguous. Verifies static analysis tools pass at the end and optionally runs functional tests. Use after `git rebase` triggers conflicts, or when the user asks to "resolve conflicts", "fix rebase", "j'ai des conflits", "aide-moi sur ce rebase".
Bootstrap a new project through a CPO+CTO interview flow. Produces versioned, dated foundational documents (vision, architecture, constraints, roadmap, mvp-features) in ./docs/project/. Also supports 'review' mode to periodically re-validate hypotheses and decisions. Use when starting a greenfield project or when you want to formalize the vision and architecture of an existing project. Do NOT use for single feature analysis (use /express-need instead).
Coaching workflow orchestrator. Guides the developer through implementation without writing code.
--- name: review-code description: Performs code review via an isolated fresh agent to prevent confirmation bias. Use when the user asks to "review code", "review changes", or "code review", or when invoked by /resolve step 08. Do NOT use for reviewing PRs from GitHub (use review-pr skill instead). argument-hint: [--ticket <id>] [--base <branch>] [--fix] [--severity <level>] allowed-tools: Read, Glob, Grep, Bash, Edit, Write, AskUserQuestion, Agent --- # Code Review Skill Orchestrates code rev
Disciplined methodology for code architecture refactoring. Use when the user asks to refactor architecture, decouple code, restructure a family of classes, redesign an interface, or rename/reorganize a set of related components. Forces a big-picture analysis before any code is written. Do NOT use for simple bug fixes, feature additions, or single-file refactoring.
Analyse-Explore-Plan methodology for thorough analysis and planning before development. Use when starting a new feature, investigating a problem, or needing to understand a codebase before making changes. Provides structured workflow with parallel exploration agents and clarification questions. Integrates with Architect skill for high-quality implementation plans. Do NOT use for ticket-based planning (use /resolve <ticket> --plan-only instead) or when a saved plan is needed (use /create-plan instead).
Disciplined methodology for code architecture refactoring. Use when the user asks to refactor architecture, decouple code, restructure a family of classes, redesign an interface, or rename/reorganize a set of related components. Forces a big-picture analysis before any code is written. Do NOT use for simple bug fixes, feature additions, or single-file refactoring.
Coaching workflow orchestrator. Guides the developer through implementation without writing code.
Execute the markdown test plan in docs/qa/ via Playwright MCP and create a ticket on each failing scenario. Use after /qa-sync, before a release, or to validate a feature end-to-end. Do NOT use to design or update scenarios (use /qa-sync instead) and do NOT use for visual regression (use visual-verify agent instead).
Audits a project's Claude Code setup against real usage — mines the project's conversations (worktrees included), confronts the project's skills/agents/CLAUDE.md with best practices, and proposes adjustments or new skills/agents/rules. Use when the user asks to audit the project config, analyze project conversations, or find automation opportunities for the current project. Do NOT use for the global ~/.claude configuration (use /audit-config instead).
Guide for creating effective skills. Use when the user asks to create a new skill, update an existing skill, or package specialized knowledge/workflows. Do NOT use for creating agents (write agent file directly) or for creating slash commands (write command file directly).
Internal helper called by /resolve. Provides state-machine and coordination logic across fetch-ticket, analyze-ticket, AEP, and Architect. Not intended for direct invocation.
Internal helper called by /resolve. Retrieves tickets from YouTrack, GitHub, or file (auto-detected from ticket ID pattern) and outputs normalized markdown. Not intended for direct invocation.
Fetch PR details from GitHub (reviews, inline comments, conversations, diff). Use when user asks to view a PR, check PR comments, review PR feedback, or when any workflow needs to read PR data. Provides reliable repo-aware commands. Do NOT use for creating PRs (use create-pr skill instead).
Polish and refine code by delegating to a framework-aware simplifier subagent (auto-detected or specified). Use proactively after implementation phases, when asked to "simplify", "clean up", "polish", or "refactor" code. Do NOT use for architectural refactoring or for code review (use deep-review instead).
Modular ticket resolution workflow orchestrator. Loads steps dynamically based on mode and current state.
Performs deep code review via an isolated fresh agent (anti-bias). Works in two modes - ticket mode (reads ticket + plan, invoked by /resolve step 08) and standalone mode (reviews the current working diff with no ticket, for changes made outside a ticket flow). Use when the user asks for an in-depth review of current changes. Do NOT use for reviewing PRs from GitHub (use review-pr skill instead) or for a quick correctness scan with effort levels (use bundled /code-review instead).
Automatiser les demandes RGPD (suppression, accès, portabilité des données personnelles). Utiliser ce skill quand l'utilisateur souhaite exercer ses droits RGPD auprès d'une entreprise, notamment pour la suppression de données marketing, le droit à l'oubli, ou l'accès à ses données personnelles. Déclenché par des demandes comme "supprimer mes données", "RGPD", "désabonnement", "droit à l'oubli", "mes données personnelles".
Software architecture skill for designing high-quality implementation plans. Provides universal patterns, quality checklists, and architectural guidelines. Use during planning phase to ensure plans are well-structured, atomic, and follow best practices. Do NOT use for architectural refactoring of existing code.
Skill for pushing branch and creating pull requests with proper target branch detection and draft support. Use when user asks to "create PR", "push and create PR", "open a pull request", or says "/create-pr". Also invoked by /resolve workflow finalization phase. Do NOT use for reviewing PRs (use review-pr skill instead).