gsd-workstreams — Claude Code skill for workstreams
A Claude Code skill for managing parallel workstreams: it creates them, changes the active one, and reports status and progress. Run /gsd-workstreams to archive finished work or resume a workstream.
MIT 569 installs ★ 11,761 updated 2026-11-16
npx skills add open-gsd/gsd-core --skill gsd-workstreams -a claude-codeWhat gsd-workstreams does
This skill manages parallel workstreams for concurrent milestone work. It lists each workstream with its status, current phase, and progress, or shows a detailed phase breakdown for one. Running the command without a subcommand displays the list.
After creating a workstream, it prints its path and suggests a command to set up a milestone. Switching workstreams sets the active one and GSD_WORKSTREAM when the runtime supports that variable. If a session identifier is available, the active workstream is stored per session so concurrent sessions do not overwrite each other. Operations run through gsd_run with workstream.* queries.
What it helps with
- list the status of every workstream
- create a workstream for a milestone
- change the active workstream
- inspect phase details or cross-workstream progress
- archive finished work and resume a workstream
Example prompts for the agent
- List the workstreams with
/gsd-workstreams list - Create a workstream named
releasewith/gsd-workstreams create release - Make
releaseactive with/gsd-workstreams switch release
How to install gsd-workstreams
1Skills CLI (Vercel)
npx skills add open-gsd/gsd-core --skill gsd-workstreams -a claude-code2Manually: put the files in place
~/.claude/skills/gsd-workstreams/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/gsd-workstreams/
1Skills CLI (Vercel)
npx skills add open-gsd/gsd-core --skill gsd-workstreams -a codex2Manually: put the files in place
.agents/skills/gsd-workstreams/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add open-gsd/gsd-core --skill gsd-workstreams -a cursor2Manually: put the files in place
.cursor/skills/gsd-workstreams/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install open-gsd/gsd-core skills/gsd-workstreams2Manually: put the files in place
.github/skills/gsd-workstreams/SKILL.md1Skills CLI (Vercel)
npx skills add open-gsd/gsd-core --skill gsd-workstreams -a gemini-cli2Platform CLI
gemini skills install https://github.com/open-gsd/gsd-core --path skills/gsd-workstreamsManually: put the files in place
.devin/skills/gsd-workstreams/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add open-gsd/gsd-core --skill gsd-workstreams -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about gsd-workstreams
How do I install gsd-workstreams in Claude Code?
Run npx skills add open-gsd/gsd-core --skill gsd-workstreams -a claude-code, then use ~/.claude/skills/gsd-workstreams/SKILL.md.
What does gsd-workstreams do?
It creates and switches workstreams, reports status and progress, archives completed work, and resumes workstreams.
Which operations can I run with gsd-workstreams?
Use list, create, status, switch, progress, complete, or resume. With no subcommand, it lists the workstreams.
Source text
SKILL.md · MIT
---
name: gsd-workstreams
description: "Manage parallel workstreams — list, create, switch, status, progress, complete, and resume"
allowed-tools:
- Read
- Bash
- Grep
---
# /gsd-workstreams
Manage parallel workstreams for concurrent milestone work.
## Usage
`/gsd-workstreams [subcommand] [args]`
### Subcommands
| Command | Description |
|---------|-------------|
| `list` | List all workstreams with status |
| `create <name>` | Create a new workstream |
| `status <name>` | Detailed status for one workstream |
| `switch <name>` | Set active workstream |
| `progress` | Progress summary across all workstreams |
| `complete <name>` | Archive a completed workstream |
| `resume <name>` | Resume work in a workstream |
## Step 1: Parse Subcommand
Parse the user's input to determine which workstream operation to perform.
If no subcommand given, default to `list`.
## Step 2: Execute Operation
### list
Run: `gsd_run query workstream.list --raw --cwd "$CWD"`
Display the workstreams in a table format showing name, status, current phase, and progress.
### create
Run: `gsd_run query workstream.create <name> --raw --cwd "$CWD"`
After creation, display the new workstream path and suggest next steps:
- `/gsd-new-milestone --ws <name>` to set up the milestone
### status
Run: `gsd_run query workstream.status <name> --raw --cwd "$CWD"`
Display detailed phase breakdown and state information.
### switch
Run: `gsd_run query workstream.set <name> --raw --cwd "$CWD"`
Also set `GSD_WORKSTREAM` for the current session when the runtime supports it.
If the runtime exposes a session identifier, GSD also stores the active workstream
session-locally so concurrent sessions do not overwrite each other.
### progress
Run: `gsd_run query workstream.progress --raw --cwd "$CWD"`
Display a progress overview across all workstreams.
### complete
Run: `gsd_run query workstream.complete <name> --raw --cwd "$CWD"`
Archive the workstream to milestones/.
### resume
Set the workstream as active and suggest `/gsd-resume-work --ws <name>`.
## Step 3: Display Results
Format the JSON output from gsd-tools query into a human-readable display.
Include the `${GSD_WS}` flag in any routing suggestions.
© open-gsd · MIT · open-gsd/gsd-core