Best use case
sdd-tasks is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
**Slash command**: `/sdd-tasks <slug>`
Teams using sdd-tasks should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/sdd-tasks/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How sdd-tasks Compares
| Feature / Agent | sdd-tasks | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
**Slash command**: `/sdd-tasks <slug>`
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# sdd-tasks **Slash command**: `/sdd-tasks <slug>` **Purpose**: Generate `tasks.md` (TASK-001..N) and `progress.md` from `requirements.md` and `design.md`. --- ## Prerequisites - `.claude/specs/<slug>/requirements.md` must exist - `.claude/specs/<slug>/design.md` must exist (run `/sdd-design` first) --- ## Steps ### 1. Read spec inputs ``` .claude/specs/<slug>/requirements.md .claude/specs/<slug>/design.md ``` Extract: - Every REQ-XXX ID with its acceptance criteria - Every design section (§X.X) with its title - File structure plan (§3) for deriving "Files to modify" - Component responsibilities (§6.1) for scoping tasks ### 2. Decompose requirements into tasks Rules for decomposition: - Each TASK must implement one or more REQ-XXX entries - Each TASK maps to one or more design sections via `Design ref` - One TASK per logical unit of work (one file, one hook, one component, or one test suite) - If a task feels L complexity, split it - Ordering: schemas → API mutations → SWR hooks → nuqs query state → containers → presentation components → MSW handlers → tests → integration/E2E Complexity guidelines: | Size | Meaning | | ---- | ------------------------------------------ | | S | ~30 min — single file, clear scope | | M | ~2 h — multiple related files, clear scope | | L | ~4+ h — warn user; recommend splitting | ### 3. Write `tasks.md` Use the format below for every task. Copy the template from `.claude/skills/sdd-tasks/templates/tasks.md` and fill it in. ```markdown ### TASK-001 — <title> Implements: REQ-001, REQ-002 Design ref: §3.2 Component hierarchy Type: feat | test | refactor | docs | chore Estimated complexity: S | M | L Files to modify: - src/features/<feature>/schemas/<feature>-schema.ts (create) - src/features/<feature>/hooks/use-<feature>.ts (create) Acceptance: matches REQ-001 acceptance criteria ``` Field rules: - `Implements`: comma-separated REQ-XXX IDs; every REQ must appear in at least one task - `Design ref`: `§X.X <section title>` format; every design section must appear in at least one task - `Type`: one of `feat`, `test`, `refactor`, `docs`, `chore` - `Files to modify`: list with `(create)` or `(modify)` suffix - `Acceptance`: copy or paraphrase directly from the REQ acceptance criteria ### 4. Write `progress.md` Copy the template from `.claude/skills/sdd-tasks/templates/progress.md` and fill in: - `slug`: the spec slug - `mode`: read from requirements.md front-matter or default to `standard` - `started`: today's date in YYYY-MM-DD format - Task state table: one row per TASK, all set to `pending` ### 5. Mode-specific behaviour **`--mode standard`**: Present the task breakdown to the user. Discuss granularity and ordering. Allow the user to add, remove, or reorder tasks before writing the files. **`--mode auto`**: Decompose autonomously. If any task has L complexity, add a warning comment directly in `tasks.md` above that task: ```markdown <!-- ⚠️ L-complexity task — consider splitting before implementation --> ``` --- ## Output ``` .claude/specs/<slug>/tasks.md .claude/specs/<slug>/progress.md ``` --- ## Validation before writing Before writing the files, verify: 1. Every REQ-XXX from requirements.md appears in at least one `Implements:` field 2. Every design section §X.X from design.md appears in at least one `Design ref:` field 3. No duplicate TASK-XXX IDs 4. No TASK is missing an `Implements:` field If any check fails, report the gap and ask the user whether to auto-fill or stop. --- ## Phase Gate ``` == PHASE COMPLETE: sdd-tasks == Artifact: .claude/specs/<slug>/tasks.md Artifact: .claude/specs/<slug>/progress.md Summary: - TASK-001 through TASK-NNN generated covering all REQ-XXX entries - All design sections §X.X covered by at least one Design ref - Complexity estimates provided; L tasks flagged for splitting - progress.md initialised with all tasks in pending state - Mode recorded as standard|auto in progress.md header ⏸ WAITING FOR CONFIRMATION Type `CONFIRM sdd-review-plan` to proceed, or describe changes needed. ```
Related Skills
sdd-impl — Implement Tasks (TDD)
## Slash Command
test
Advanced test implementation command with unit/E2E support, auto-execution, and smart fixing capabilities
serena
Token-efficient Serena MCP command for structured app development and problem-solving
project-guidelines-example
Example project-specific skill template based on a real production application.
notion-bug-pr
Skill that pulls bug tickets (titles containing 「不具合」) from a Notion database, investigates root cause in a GitHub repo, applies fixes, and opens draft PRs. Supports three modes — daily recurring schedule, one-shot at a specific time, or immediate on-demand run. Takes three or four args: Notion database URL, repo path or name, and either HH:MM (daily), "once HH:MM" (one-shot), or "now" (immediate).
graphify
any input (code, docs, papers, images, videos) to knowledge graph. Use when user asks any question about a codebase, documents, or project content - especially if graphify-out/ exists, treat the question as a /graphify query.
chrome
Comprehensive Chrome DevTools development system with native Chrome capabilities for debugging, E2E testing, performance analysis, and browser automation
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
typescript-advanced-types
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.
tanstack-start
Full-stack React framework powered by TanStack Router with SSR, streaming, server functions, and deployment to any hosting provider.
tanstack-start-server-fn-testing
Unit-test TanStack Start createServerFn handlers via a global vi.mock that combines two patterns from Discussion #2701