Best use case
sdd-workflow — Workflow Status Dashboard is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
## Slash Command
Teams using sdd-workflow — Workflow Status Dashboard 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-workflow/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How sdd-workflow — Workflow Status Dashboard Compares
| Feature / Agent | sdd-workflow — Workflow Status Dashboard | 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
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.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# sdd-workflow — Workflow Status Dashboard
## Slash Command
```
/sdd-workflow [slug]
```
## Purpose
Read-only meta skill. Displays the current state of the SDD workflow — which phases are complete, which is next, and any blockers. Does NOT modify any files.
---
## This Skill is Read-Only
`sdd-workflow` never writes to or modifies any file. It only reads spec files and git history to report status. There is no approval gate for this skill.
---
## Usage: Specific Feature
```
/sdd-workflow <slug>
```
Reads `.claude/specs/<slug>/` and displays the full phase chain with status:
```
SDD Workflow: <slug>
Mode: standard | auto
Branch: feature/<slug> (12 commits ahead of main)
Phase Chain:
[✅] sdd-init — source-notion.md archived
[✅] sdd-requirements — requirements.md: 5 REQs defined
[✅] sdd-review-requirements — review.md: Requirements Review present
[✅] sdd-design — design.md: 8 sections
[✅] sdd-tasks — tasks.md: 12 TASKs defined
[✅] sdd-review-plan — review.md: Plan Review + Traceability ✅
[🔄] sdd-impl — progress: 3/12 done, TASK-004 in-progress
[⏳] sdd-review — waiting for sdd-impl to complete
[⏳] sdd-pr — waiting
Next action: /sdd-impl <slug> TASK-004 (resume in-progress task)
or: CONFIRM sdd-impl (if paused at a gate)
```
Status icons:
| Icon | Meaning |
| ---- | --------------------- |
| ✅ | Phase complete |
| 🔄 | Phase in progress |
| ⚠️ | Phase has a blocker |
| ⏳ | Phase not yet started |
---
## Usage: All Features
```
/sdd-workflow
```
Lists all spec directories under `.claude/specs/` and shows each feature's current phase:
```
SDD Workflow Overview
Specs directory: .claude/specs/
slug | current phase | status
-------------------------|----------------|-----------------------------------
user-authentication | sdd-impl | 🔄 3/8 tasks done
mail-group-bulk-delete | sdd-pr | ✅ PR #42 open
supplier-csv-export | sdd-design | ⏳ not started
```
If `.claude/specs/` is empty or does not exist:
```
No spec directories found under .claude/specs/
Run /sdd-init <slug> to start a new feature.
```
---
## Phase Detection Logic
Each phase is detected by inspecting files inside `.claude/specs/<slug>/`. Detection is sequential: if a phase's condition is not met, all subsequent phases show `⏳`.
| Phase | Detected When |
| ------------------------- | -------------------------------------------------------------------------------------------- |
| `sdd-init` | `source-notion.md` exists OR the `<slug>` directory itself exists |
| `sdd-requirements` | `requirements.md` exists AND contains at least one `## REQ-` heading |
| `sdd-review-requirements` | `review.md` contains a `## Requirements Review` section |
| `sdd-design` | `design.md` exists (any non-empty content) |
| `sdd-tasks` | `tasks.md` exists AND contains at least one `### TASK-` heading |
| `sdd-review-plan` | `review.md` contains `## Plan Review` AND no unchecked `❌` in its Traceability subsection |
| `sdd-impl` | `progress.md` has at least one task marked `done` |
| `sdd-review` | `review.md` contains `## Code Review` |
| `sdd-pr` | `progress.md` contains a `## PR` section with a URL, OR `review.md` contains a GitHub PR URL |
---
## Progress Metrics (sdd-impl)
When `sdd-impl` is the current phase, show task completion metrics by parsing `progress.md`:
```
[🔄] sdd-impl — progress: 3/12 done (25%), 1 in-progress, 8 pending
In-progress: TASK-004 (Create supplier CSV export hook)
Last completed: TASK-003 (Add export button to supplier table)
```
Count tasks by status:
- `done`: lines matching `— done` or `[x]`
- `in-progress`: lines matching `— in-progress`
- `pending`: lines matching `— pending` or `[ ]`
---
## Blocker Detection
For the currently active or blocked phase, surface known blockers:
| Phase | Blocker Condition | Warning Message |
| ------------ | ------------------------------------------------------------ | ------------------------------------------------------- |
| `sdd-impl` | `review.md` has no `## Plan Review` section | ⚠️ Run /sdd-review-plan \<slug\> before implementing |
| `sdd-review` | `progress.md` has tasks still `pending` | ⚠️ N tasks still pending — run /sdd-impl \<slug\> first |
| `sdd-pr` | `review.md` has unchecked `- [ ]` items under `### CRITICAL` | ⚠️ N open CRITICAL issues — resolve before creating PR |
| `sdd-pr` | `review.md` has no `## Code Review` section | ⚠️ Run /sdd-review \<slug\> before creating PR |
Blockers appear with ⚠️ next to the phase name and a `Blocker:` line in the output.
---
## Git Branch Detection
Display the current branch and commit count:
```bash
git branch --show-current
git log main...HEAD --oneline | wc -l
```
Output:
```
Branch: feature/user-authentication (12 commits ahead of main)
```
If the current branch does not match the slug:
```
⚠️ Current branch (feature/other-thing) does not match slug (user-authentication)
Switch to the correct branch before running implementation or review skills.
```
---
## Full Phase Chain Reference
The complete SDD skill chain in order:
```
1. sdd-init — Archive Notion source, create spec directory
2. sdd-requirements — Write requirements.md from source-notion.md
3. sdd-review-requirements — Review requirements, append to review.md
4. sdd-design — Write design.md (architecture, components, API)
5. sdd-tasks — Write tasks.md (TASK-xxx breakdown)
6. sdd-review-plan — Review plan, verify traceability, append to review.md
7. sdd-impl — TDD implementation, one commit per task
8. sdd-review — Code + security review, append to review.md
9. sdd-pr — Create GitHub PR with traceability and test plan
```
---
## Example: Fully Complete Feature
```
SDD Workflow: user-authentication
Mode: auto
Branch: feature/user-authentication (12 commits ahead of main)
Phase Chain:
[✅] sdd-init — source-notion.md archived
[✅] sdd-requirements — requirements.md: 5 REQs (REQ-001 through REQ-005)
[✅] sdd-review-requirements — review.md: Requirements Review present
[✅] sdd-design — design.md: 6 sections
[✅] sdd-tasks — tasks.md: 12 TASKs defined
[✅] sdd-review-plan — review.md: Plan Review, Traceability ✅
[✅] sdd-impl — progress: 12/12 done
[✅] sdd-review — review.md: Code Review (2026-05-26), 0 CRITICAL, 2 HIGH open
[⏳] sdd-pr — waiting
Next action: /sdd-pr user-authentication
```Related Skills
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
tailwind-css-patterns
Provides comprehensive Tailwind CSS utility-first styling patterns including responsive design, layout utilities, flexbox, grid, spacing, typography, colors, and modern CSS best practices. Use when styling React/Vue/Svelte components, building responsive layouts, implementing design systems, or optimizing CSS workflow.