SDD Workflow Management

VerifiedSafe

Manages SDD state, handoffs, and versioning for web-playground projects. Use it to track progress, facilitate multi-session or multi-agent continuity, and propagate changes across documents.

Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude Code
#sdd-workflow#state-tracking#handoff#versioning#multi-agent

Recommended for

Automated summary

Manages SDD state, handoffs, and versioning to ensure continuity across sessions and agents for web playground projects.

Strengths

  • Clear progress tracking per phase and document
  • Structured handoff between agents with handoff file
  • Automatic change propagation via alignment links
  • Semantic versioning tailored to documents

Limitations

  • Requires manual discipline to keep state file accurate
  • No native integration with project management tools
  • Change propagation is not automated
When to use it

Use this workflow when working on a multi-agent or multi-session SDD project that needs rigorous document tracking.

When not to use it

Avoid this workflow for simple or single-agent projects where informal tracking is sufficient.

Security analysis

Safe
Quality score92/100

The skill only uses 'mkdir' to create a directory and reads/writes local YAML/Markdown files for state management. There is no external command execution, data exfiltration, or destructive actions.

No concerns found

How this analysis is made

Examples

Initialize SDD Workflow
Initialize the SDD workflow for a new project. Create the .sdd/state.yaml with current phase 'foundation'.
Show SDD State
Show the current SDD state from .sdd/state.yaml.
Create Handoff Note
Generate a handoff note for the current Claude session. Include ownership, completed tasks, in-progress items, blocked items, and next steps.
Propagate Changes
Propagate changes from foundation to requirements. Update the state file and document status accordingly.

name: sdd-workflow description: | Manage SDD state, handoffs, and versioning for web-playground. Use when: tracking progress, handing off between sessions/agents, propagating changes. Triggers: "sdd workflow", "sdd status", "propagate changes", "handoff"

Web Playground SDD Workflow

Track state and enable multi-agent/session continuity for SDD work.

State File

Location: .sdd/state.yaml

version: 1
updated: 2025-01-15T10:00:00Z
current_phase: requirements  # foundation | requirements | design

documents:
  foundation: { status: verified, version: 1.0.0, owner: human }
  requirements: { status: partial, version: 1.1.0, owner: claude }
  design: { status: draft, version: 0.1.0, owner: unassigned }

packages:
  react-sample: { foundation: verified, requirements: draft }

gaps: []
escalations: []

Status Values

| Status | Meaning | |--------|---------| | draft | Created, not verified | | verified | Passed verification | | blocked | Waiting on escalation resolution | | partial | Some items verified, some draft |

Owner Values

| Owner | Meaning | |-------|---------| | claude | Current Claude session owns this | | human | Human is responsible | | unassigned | Available for next agent |

Instructions

1. Initialize

mkdir -p .sdd

Create .sdd/state.yaml with current_phase: foundation.

2. Claim Ownership

Before modifying a document, update owner:

documents:
  requirements: { status: draft, owner: claude }

3. Track Progress

Update state after completing work:

documents:
  foundation: { status: verified, version: 1.0.0, owner: human }

4. Escalate When Blocked

When needing human decision:

escalations:
  - id: ESC-001
    type: scope_decision
    description: "Should QUALITY-MINIMAL allow lodash?"
    items_affected: [REQ-003]
    status: pending  # pending | resolved

Set affected items to blocked status.

5. Propagate Changes

Foundation change -> Re-verify Requirements (@aligns-to links)
Requirements change -> Re-verify Design (@derives links)

6. Session Handoff

At session end, write .sdd/handoff.md:

# SDD Handoff - 2025-01-15

**From:** claude
**To:** human (or next claude session)

## Ownership Transfer
- requirements: claude -> unassigned

## Completed
- Foundation verified with SCOPE-MONOREPO, QUALITY-TYPESCRIPT anchors

## In Progress
- REQ-002: 50% complete, needs verification criteria

## Blocked
- REQ-003: waiting on ESC-001 (scope decision)

## Next Steps
1. Resolve ESC-001 (human decision needed)
2. Complete REQ-002 verification criteria
3. Run alignment check

Versioning

| Change | Bump | |--------|------| | Anchor/REQ deleted or modified meaning | MAJOR | | New anchor/REQ, clarification | MINOR | | Typo, formatting | PATCH |

Multi-Level

Package specs in packages/{pkg}/spec/. Reference root with root:: prefix:

  • root::SCOPE-MONOREPO
  • root::REQ-001

Verification

  • [ ] State file reflects actual document status
  • [ ] Ownership assigned before modifications
  • [ ] Escalations documented when blocked
  • [ ] Handoff enables next agent to continue without questions

Reference

For full details: .claude/skills/sdd-guidelines/reference/guidelines-v4.4.md sections 4, 5, 8, 10

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/sdd-workflow-management-mmh8qrfd/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/sdd-workflow-management-mmh8qrfd' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/sdd-workflow-management-mmh8qrfd/download' --output '.skill-downloads/sdd-workflow-management-mmh8qrfd/SKILL.md.part' && mv '.skill-downloads/sdd-workflow-management-mmh8qrfd/SKILL.md.part' '.skill-downloads/sdd-workflow-management-mmh8qrfd/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/sdd-workflow-management-mmh8qrfd/SKILL.md' && test -s '.skill-downloads/sdd-workflow-management-mmh8qrfd/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/sdd-workflow' && cp -R '.skill-downloads/sdd-workflow-management-mmh8qrfd' '.claude/skills/sdd-workflow'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/sdd-workflow-management-mmh8qrfd'

openskills read 'sdd-workflow-management-mmh8qrfd'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/sdd-workflow-management-mmh8qrfd/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills