Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →chorus-aidlc/yolo-chorus
Full-auto AI-DLC pipeline — drive a single prompt from Idea through Proposal, Execution, and Verification to Done.
Passed 14 of 20 test cases with the skill, and 2 of 20 without it.
and 13 more in the full report
14 fixed3 passed either way8 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/2/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
When attaching task drafts to proposal `prop-3310` in Step 1.4 using `chorus_pm_add_task_draft`, what field is mandatory on every call to prevent server-side rejection?
| Checked | Without skill | With skill |
|---|---|---|
| Includes non-empty acceptanceCriteriaItems on every task draft call. | Missed | Passed |
The instructions your model reads when the skill loads.
Full-auto AI-DLC pipeline. User provides a prompt; agent drives the entire lifecycle: Idea -> Elaboration -> Proposal -> Review -> Execute -> Verify -> Done.
Tool namespace: Chorus tools are exposed by the connected MCP server under a
mcp__chorus__prefix on dsh (e.g.mcp__chorus__chorus_pm_create_proposal). Bare names are used below for readability — prependmcp__chorus__when invoking. Seechorusfor the full rule.
dsh adaptations summarized (details inline below): (1) elaboration is self-answered with no user interaction; (2) reviewers run inline after each submit by loading the exact reviewer through the
skilltool in a foregroundsubagent(run_in_background: false, so the call waits for the reviewer to finish; the verdict is then read from the Chorus comment), with a read-only self-review fallback; (3) sessions are manual if you dispatch sub-agents; (4) task execution dispatches onesubagentper unblocked task (run_in_background: true, whole wave in one message), falling back to sequential main-agent waves whensubagentis unavailable or workers fail repeatedly — there is no team object to create first.
yolo-chorus automates the complete AI-DLC workflow. You provide a natural language description of what you want built, and the agent handles everything:
/yolo <prompt>
|
v
Project + Idea + Elaboration (self-answered) + Proposal
|
v
Proposal Reviewer (inline, up to maxProposalReviewRounds)
|
v
Admin Approve --> Tasks materialize
|
v
Wave execution (loop chorus_get_unblocked_tasks; one subagent per task,
or sequential main-agent fallback)
| (implement task + task-reviewer per task)
v
Admin Verify each task --> unblock next
|
v
test cases passed, vs 2 / 20 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.