kanban

Use this skill working with Phoenix Framework. Consult this when working with the web layer, controllers, views, liveviews etc.

Use when writing ANY code in the Stride project (this Phoenix/Elixir kanban application). Invoke BEFORE implementing features, fixing bugs, or making UI changes. Invoke BEFORE marking any development task as complete.

Integration instructions for Stride kanban platform with AI-human collaboration workflows, client-side hooks, and task management API

INTERNAL — invoked only by stride:stride-workflow. Do NOT invoke from a user prompt. Contains the claim API contract (POST /api/tasks/claim payload and required before_doing_result shape) and the before_doing hook execution pattern, used during the orchestrator's claim phase.

INTERNAL — invoked only by stride:stride-workflow. Do NOT invoke from a user prompt. Contains the completion API contract (PATCH /api/tasks/:id/complete required fields including completion_summary, actual_complexity, after_doing_result, before_review_result, explorer_result, reviewer_result), used during the orchestrator's completion phase.

INTERNAL — invoked only by stride:stride-workflow. Do NOT invoke from a user prompt. Contains the goal/batch creation contract (POST /api/tasks/batch root key MUST be "goals" not "tasks", dependency index format), used during the orchestrator's goal-decomposition phase.

INTERNAL — invoked only by stride:stride-workflow. Do NOT invoke from a user prompt. Contains the work-task and defect creation contract (POST /api/tasks field formats — verification_steps and key_files as object arrays, testing_strategy arrays), used during the orchestrator's goal-decomposition and task-creation phases.

INTERNAL — invoked only by stride:stride-workflow. Do NOT invoke from a user prompt. Contains the task enrichment procedure (codebase exploration to populate key_files, testing_strategy, verification_steps for sparse tasks), used during the orchestrator's enrichment phase before claiming.

INTERNAL — invoked only by stride:stride-workflow. Do NOT invoke from a user prompt. Contains the Claude Code subagent decision matrix (when to dispatch stride:task-explorer, stride:task-reviewer, stride:task-decomposer, stride:hook-diagnostician), used during the orchestrator's exploration and review phases.

Single orchestrator for the complete Stride task lifecycle. Invoke when the user asks to claim a task, work on the next stride task, work on stride tasks, complete a stride task, enrich a stride task, decompose a goal, or create a goal or stride tasks. Replaces invoking stride-claiming-tasks, stride-completing-tasks, stride-creating-tasks, stride-creating-goals, stride-enriching-tasks, or stride-subagent-workflow directly — those are dispatched from inside this orchestrator. Walks through prerequisites, claiming, exploration, implementation, review, hooks, and completion. Handles both Claude Code (with subagent dispatch) and other environments (Cursor/Windsurf/Continue without subagents).

Use when writing ANY code in the Stride project (this Phoenix/Elixir kanban application). Invoke BEFORE implementing features, fixing bugs, or making UI changes. Enforces module design, UI/UX, dark mode, quality, and security standards.