Stats
Actions
Tags
From smith
Generates dependency-ordered, actionable tasks.md from feature design artifacts (plan.md, spec.md, optionally data-model.md, contracts, research.md). For use inside active top-level workflows (/smith-new, /smith-bugfix, etc.) to decompose features into implementable task lists.
How this skill is triggered — by the user, by Claude, or both
Slash command
/smith:smith-tasksThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> **Workflow requirement (Smith 20+):** This skill must be invoked from inside an active top-level workflow (`/smith-new`, `/smith-bugfix`, `/smith-debug`, `/smith-build`). The workflow-gate hook will block standalone invocation. To use this skill standalone, start a top-level workflow first.
Workflow requirement (Smith 20+): This skill must be invoked from inside an active top-level workflow (
/smith-new,/smith-bugfix,/smith-debug,/smith-build). The workflow-gate hook will block standalone invocation. To use this skill standalone, start a top-level workflow first.
Throughout this action, log significant events to the vault session log. Read the session log path from .smith/vault/.current-session. If the file is missing or the vault is not initialized, skip all logging silently.
Append entries using this format:
### [HH:MM:SS] /smith-tasks <event>
**User Request:**
> <verbatim user message that triggered this action>
**Synthesized Input:** <brief summary>
**Outcome:** <what happened>
**Artifacts:** <files created/modified>
**Systems affected:** <system IDs>
Log at these points:
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Setup: Run .specify/scripts/bash/check-prerequisites.sh --json from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'''m Groot' (or double-quote if possible: "I'm Groot").
Load design documents: Read from FEATURE_DIR:
Execute task generation workflow:
Generate tasks.md: Use .specify/templates/tasks-template.md as structure, fill with:
Report: Output path to generated tasks.md and summary:
Context for task generation: $ARGUMENTS
The tasks.md should be immediately executable - each task must be specific enough that an LLM can complete it without additional context.
CRITICAL: Tasks MUST be organized by user story to enable independent implementation and testing.
Tests are OPTIONAL: Only generate test tasks if explicitly requested in the feature specification or if user requests TDD approach.
Every task MUST strictly follow this format:
- [ ] [TaskID] [P?] [Story?] Description with file path
Format Components:
- [ ] (markdown checkbox)Examples:
- [ ] T001 Create project structure per implementation plan- [ ] T005 [P] Implement authentication middleware in src/middleware/auth.py- [ ] T012 [P] [US1] Create User model in src/models/user.py- [ ] T014 [US1] Implement UserService in src/services/user_service.py- [ ] Create User model (missing ID and Story label)T001 [US1] Create model (missing checkbox)- [ ] [US1] Create User model (missing Task ID)- [ ] T001 [US1] Create model (missing file path)From User Stories (spec.md) - PRIMARY ORGANIZATION:
From Contracts:
From Data Model:
From Setup/Infrastructure:
npx claudepluginhub attckdigital/smithGenerates a dependency-ordered, executable tasks.md from design documents (spec, design, data-model, contracts). For planning implementation steps from specs or design docs.
Breaks a designed feature into atomic ≤1-day tasks with a dependency graph, per-task Definition of Done, and a machine-readable tasks.json for the implement engine. Refuses unless spec.md, sad.md, and an Accepted ADR exist.
Generates structured TASKS.json/md files with phased tasks, dependencies, story points, acceptance criteria, and agent prompts from features, PRDs, and SDDs.