globalcoder-workflow

Use when executing an implementation plan with four or more independent tasks touching different files, via the experimental agent-teams flag — parallel implementer teammates plus continuous async reviewers. Higher token cost; requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1.

Use when starting creative work — adding features, building components, adding functionality, modifying existing behavior, or any time the user describes a new idea or capability they want to build.

Use when adding, modifying, or removing database tables, columns, indexes, views, functions, or RLS policies — any schema change targeting a shared or production database

Use when facing two or more independent investigations or research tasks in the current session — debugging multiple unrelated failures, exploring different solution approaches, or running parallel reads. Not for executing implementation plans (use subagent-driven-development, agent-team-development, or tmux-parallel-development for those).

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when the app is slow, a specific operation takes too long, bundle size is too large, or you need to optimize resource usage — requires a measurable problem, not premature optimization

Use when shipping a release — version bump, CHANGELOG entry, tag, push, suggested reinstall. Especially when the project has multiple manifest files that must stay version-synced (e.g., plugin.json + marketplace.json, package.json + Cargo.toml in workspaces, version.txt + setup.py). Triggers on "ship it," "cut a release," "tag v…," "bump version."

Use when establishing the foundational MD files for a project — CLAUDE.md (workflow contract), memory.md, tech_stack.md, style_guide.md, backlog.md, tech_docs.md. Works for both empty directories (interview from scratch) and existing codebases (scan first, then ask only the gaps). Triggers on "set up a new project," "scaffold project docs," "init project context," "bootstrap project," "add the workflow files to this repo."

Use when receiving code review feedback, before implementing any of the suggestions, especially when feedback seems unclear, technically questionable, or pressures you toward immediate compliance.

Use when undertaking any refactoring that touches more than a single function — restructuring modules, renaming across files, extracting components, changing data flow patterns, or migrating between patterns

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when merging features that handle user input, authentication, authorization, payments, or sensitive data, or for periodic security audits and vulnerability reports

Use when executing an implementation plan sequentially in the current session — one fresh subagent per task with spec and quality reviews between each. Default for plans with fewer than four tasks or any sequential dependencies.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when executing an implementation plan with two or more independent tasks via tmux processes — separate claude instances per task, no inter-worker messaging, no experimental flag required. Requires tmux installed.

Use when starting UI/visual work in any project — landing pages, dashboards, marketing sites, design-system-heavy components, or anything where visual consistency matters. Triggers on signals like "polished," "intentional," "high-end," "design system," "investor-ready," "brand," or fresh frontend scaffolds without an existing design contract.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when you have a spec or requirements for a multi-step task, before touching code

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Use when creating or refining a brand - guides naming, voice and tone, brand story, visual direction, and brand principles

Use when building marketing campaigns - creates email sequences, social media post series, and ad copy with platform-specific formatting and constraints

Use when planning what content to create for a launch - defines content pillars, formats, calendar, distribution plan, and repurposing strategy

Use when you need to define target buyers - builds detailed personas with pain points, goals, channels, and objections grounded in market research

Use when starting marketing for a new product or brand from scratch - guided workflow through all marketing phases from research to launch

Use when creating a landing page - guides copy, page structure, CTA strategy, and optionally generates code using the project's UI framework

Use when planning a product launch - builds a phased timeline with channels, milestones, owners, and KPIs

Use after a product launch to review results - structured analysis of metrics, what worked, what didn't, and concrete next actions

Use when launching a new product or entering a new market - guides competitor analysis, target audience identification, market sizing, and opportunity mapping

Use when crafting product messaging - builds value proposition, differentiators, messaging matrix per persona, competitive positioning, and elevator pitches

Use when starting any conversation involving marketing, branding, product launches, positioning, content creation, or go-to-market strategy - routes to the correct marketing skill