Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Manage parallel workstreams — list, create, switch, status, progress, complete, and resume
.claude/skills/davepoon-gsd-workstreams/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-14 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-12 | ✓→✗ | ▼ Worse | 160% | 0% |
Manage parallel workstreams for concurrent milestone work.
/gsd:workstreams [subcommand] [args]
| 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 |
Parse the user's input to determine which workstream operation to perform. If no subcommand given, default to list.
Run: gsd-sdk query workstream.list --raw --cwd "$CWD" Display the workstreams in a table format showing name, status, current phase, and progress.
Run: gsd-sdk query workstream.create <name> --raw --cwd "$CWD" After creation, display the new workstream path and suggest next steps:
/gsd:new-milestone --ws <name> to set up the milestoneRun: gsd-sdk query workstream.status <name> --raw --cwd "$CWD" Display detailed phase breakdown and state information.
Run: gsd-sdk query workstream.set <name> --raw --cwd "$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.
Run: gsd-sdk query workstream.progress --raw --cwd "$CWD" Display a progress overview across all workstreams.
Run: gsd-sdk query workstream.complete <name> --raw --cwd "$CWD" Archive the workstream to milestones/.
Set the workstream as active and suggest /gsd:resume-work --ws <name>.
Format the JSON output from gsd-sdk query into a human-readable display. Include the ${GSD_WS} flag in any routing suggestions.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | fail→fail | 7,371 | 4,103 | -44% | 1 | 1 | 0% | 841 | 728 | -13% | 0 | 0 | — |
case-01 | fail→fail | 4,097 | 4,840 | +18% | 1 | 1 | 0% | 692 | 770 | +11% | 0 | 0 | — |
case-02 | fail→fail | 3,784 | 7,100 | +88% | 1 | 1 | 0% | 641 | 1,171 | +83% | 0 | 0 | — |
case-03 | fail→fail | 5,609 | 4,411 | -21% | 1 | 1 | 0% | 900 | 774 | -14% | 0 | 0 | — |
case-04 | fail→fail | 4,651 | 3,918 | -16% | 1 | 1 | 0% | 684 | 795 | +16% | 0 | 0 | — |
case-05 | fail→fail | 6,392 | 4,574 | -28% | 1 | 1 | 0% | 1,057 | 682 | -35% | 0 | 0 | — |
case-06 | fail→fail | 5,339 | 4,306 | -19% | 1 | 1 | 0% | 876 | 786 | -10% | 0 | 0 | — |
case-07 | fail→fail | 4,351 | 5,345 | +23% | 1 | 1 | 0% | 710 | 865 | +22% | 0 | 0 | — |
case-08 | fail→fail | 14,865 | 4,135 | -72% | 1 | 1 | 0% | 2,609 | 798 | -69% | 0 | 0 | — |
case-09 | fail→fail | 2,295 | 4,506 | +96% | 1 | 1 | 0% | 385 | 715 | +86% | 0 | 0 | — |
case-10 | fail→fail | 7,354 | 4,826 | -34% | 1 | 1 | 0% | 1,264 | 769 | -39% | 0 | 0 | — |
case-11 | fail→fail | 8,048 | 5,572 | -31% | 1 | 1 | 0% | 1,296 | 835 | -36% | 0 | 0 | — |
case-12 | pass→fail | 2,041 | 5,926 | +190% | 1 | 1 | 0% | 321 | 833 | +160% | 0 | 0 | — |
case-13 | fail→fail | 10,123 | 2,876 | -72% | 1 | 1 | 0% | 1,765 | 1,055 | -40% | 0 | 0 | — |
case-14 | fail→pass | 8,113 | 1,532 | -81% | 1 | 1 | 0% | 1,395 | 801 | -43% | 0 | 0 | — |
case-16 | fail→pass | 16,895 | 7,633 | -55% | 1 | 1 | 0% | 2,730 | 1,970 | -28% | 0 | 0 | — |
case-17 | fail→pass | 5,416 | 3,384 | -38% | 1 | 1 | 0% | 1,173 | 666 | -43% | 0 | 0 | — |
case-18 | fail→pass | 8,972 | 1,598 | -82% | 1 | 1 | 0% | 1,353 | 763 | -44% | 0 | 0 | — |
case-19 | fail→fail | 4,659 | 1,481 | -68% | 1 | 1 | 0% | 751 | 805 | +7% | 0 | 0 | — |
case-20 | pass→pass | 4,293 | 5,232 | +22% | 1 | 1 | 0% | 806 | 1,397 | +73% | 0 | 0 | — |
case-21 | pass→pass | 4,869 | 7,175 | +47% | 1 | 1 | 0% | 873 | 1,829 | +110% | 0 | 0 | — |
case-22 | pass→pass | 3,691 | 3,302 | -11% | 1 | 1 | 0% | 666 | 1,165 | +75% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 9 counted toward the lift figure. The other 13 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +14 percentage points is the difference between those two pass rates over the 9 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.