Install any skill in seconds. Free to start, no credit card required.
Get Started Free →open-gsd/gsd-headless
Orchestrate GSD (Git Ship Done) projects programmatically via headless CLI.
Passed 24 of 25 test cases with the skill, and 10 of 25 without it.
and 21 more in the full report
15 fixed9 passed either way0 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
When reading the state snapshot JSON returned by instant query commands, which JSON property under `.state` indicates the current project execution phase, and which property indicates what action auto-mode would run next?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies .state.phase for current phase | Passed | Passed |
| Identifies .next for next action | Missed | Passed |
The instructions your model reads when the skill loads.
Run GSD commands without TUI via gsd headless. Spawns an RPC child process, auto-responds to UI prompts, streams progress.
gsd headless [flags] [command] [args...]
Flags:
--timeout N — overall timeout in ms; auto has no overall timeout unless this flag is set--json — JSONL event stream ending with the authoritative headless_result--model ID — override LLM model--thinking LEVEL — override thinking level (off, minimal, low, medium, high, xhigh, max)--resume <id> — resume a prior headless session by ID--bare — start with minimal context for CI/ecosystem use--verbose — show tool calls in progress output--supervised — forward interactive UI requests to orchestrator via stdout/stdin--response-timeout N — timeout for orchestrator response in supervised mode (default 30000)--max-restarts N — auto-restart on crash with backoff (default 3, 0 to disable)--answers <path> — pre-supply answers and secrets from JSON file--events <types> — filter JSONL output to specific event types (comma-separated, implies --json)Exit codes: 0=complete, 1=error/timeout, 10=blocked, 11=cancelled
gsd headless new-milestone --context spec.md --auto
Reads spec, bootstraps .gsd/, creates milestone, then chains into auto-mode executing all phases (discuss → research → plan → execute → summarize → complete).
Extra flags for new-milestone: --context <path> (use - for stdin), --context-text <text>, --auto.
test cases passed, vs 10 / 25 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.