用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/Chorus-AIDLC/Chorus --skill quick-dev命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Optional divergent-then-convergent dialogue for fuzzy ideas. Invoked from the idea skill as a prelude to structured elaboration; produces one ElaborationRound of decision-point Q&A and returns control. Never writes files, never posts comments, never validates elaboration.
Chorus AI Agent collaboration platform — overview, common tools, setup, and routing to stage-specific skills.
Final ship-time review of an Idea's aggregate code change — the whole feature across all its tasks, not one task. Read the integrated code, check cross-task integration / architecture / security / regression / coverage, run tests. Invoke after the last task of an idea-rooted proposal is verified; ends with a VERDICT comment on the Idea.
基于 SOC 职业分类
| name | quick-dev |
| description | Quick Task workflow — skip Idea→Proposal, create tasks directly, execute, and verify. |
| license | AGPL-3.0 |
| metadata | {"author":"chorus","version":"0.16.4","category":"project-management","mcp_server":"chorus"} |
Skip the full AI-DLC pipeline (Idea → Elaboration → Proposal → Approval) and create tasks directly. Ideal for small, well-understood work. The goal is for agents to autonomously record their development work and verify task completion through structured acceptance criteria.
The standard AI-DLC flow ensures quality through structured planning, but adds overhead that slows down small tasks. Quick Dev provides a lightweight alternative:
check explicit task:admin permission → create/claim → implement → self-check AC → submit → independent task review → verify or hand off
Use Quick Dev when:
Do NOT use Quick Dev when:
For complex work, use /idea + /proposal instead.
Call chorus_checkin and inspect the active agent's effective permissions. Set canVerifyTask to true only when chorus_checkin().agent.permissions.task explicitly contains "admin" (the task:admin permission).
Never infer verification authority from the agent's name, persona, preset/role label, task ownership, or tool availability. Do not ask whether to self-verify: the explicit permission determines the terminal path.
| Tool | Purpose |
|---|---|
chorus_create_tasks | Create task(s) — omit proposalUuid for standalone Quick Task, or pass it to attach to an existing proposal |
chorus_update_task | Edit task fields (title, description, priority, AC, dependencies) or change status |
chorus_claim_task | Claim a task (open → assigned) |
chorus_report_work | Report progress with optional status update |
chorus_report_criteria_self_check | Self-check acceptance criteria before submitting |
chorus_submit_for_verify | Submit for admin verification |
chorus_admin_verify_task | (admin only) Verify task — use when self-verification is approved |
acceptanceCriteriaItems is required — chorus_create_tasks rejects any task without at least one non-blank criterion (and rejects the whole batch if any task is missing them). These are also the foundation for self-checking in Step 6. Write specific, testable criteria that you can objectively verify after development. Vague AC like "works correctly" defeats the purpose; prefer "returns 200 on GET /api/foo with valid token".
chorus_create_tasks({
projectUuid: "<project-uuid>",
tasks: [{
title: "Fix login redirect loop on Safari",
description: "Safari loses session cookie after redirect...",
priority: "high",
storyPoints: 1,
acceptanceCriteriaItems: [
{ description: "Login works on Safari 17+", required: true },
{ description: "Existing Chrome/Firefox behavior unchanged", required: true }
]
}]
})
proposalUuid is optional:
chorus_claim_task({ taskUuid: "<task-uuid>" })
Use chorus_update_task to refine the task after creation. Tasks always have AC (creation requires them), but update them when your understanding changes during development. Passing acceptanceCriteriaItems replaces the task's criteria with the provided non-empty set; omit the field to leave them unchanged (it cannot be used to clear AC).
chorus_update_task({
taskUuid: "<task-uuid>",
description: "Updated with more details...",
acceptanceCriteriaItems: [
{ description: "Login works on Safari 17+", required: true },
{ description: "Added CSRF token handling", required: true }
],
addDependsOn: ["<other-task-uuid>"]
})
chorus_update_task({ taskUuid: "<task-uuid>", status: "in_progress" })
Sub-agents: pass sessionUuid for attribution:
chorus_update_task({ taskUuid: "<task-uuid>", status: "in_progress", sessionUuid: "<session-uuid>" })
chorus_report_work({
taskUuid: "<task-uuid>",
report: "Fixed Safari cookie issue:\n- Root cause: SameSite=Strict incompatible with redirect\n- Changed to SameSite=Lax\n- Commit: abc1234",
sessionUuid: "<session-uuid>"
})
chorus_report_criteria_self_check({
taskUuid: "<task-uuid>",
criteria: [
{ uuid: "<ac-uuid-1>", devStatus: "passed", devEvidence: "Tested on Safari 17.2" },
{ uuid: "<ac-uuid-2>", devStatus: "passed", devEvidence: "Chrome/Firefox regression tests pass" }
]
})
chorus_submit_for_verify({
taskUuid: "<task-uuid>",
summary: "Fixed Safari login redirect loop. Changed SameSite cookie policy. All AC passed."
})
Submitting is not final verification. Spawn the required task-reviewer agent with subagent_spawn as described in /skill:develop, wait for it, and read the newest VERDICT: Task comment. PASS and PASS WITH NOTES continue. On FAIL, do not verify or hand off: fix every unresolved BLOCKER, repeat AC self-check and submission, then run a fresh independent task review.
With explicit task:admin, after every required AC self-check passes and independent review has no unresolved BLOCKER, verify and continue autonomously:
chorus_admin_verify_task({ taskUuid: "<task-uuid>" })
Without explicit task:admin, do not call the admin tool. Post an evidence-rich comment on the Task containing AC results, test evidence, the latest independent-review verdict, and the exact requested action. @mention the responsible human (prefer chorus_checkin().agent.owner) to perform admin verification, then end the current turn.
This handoff applies in interactive and headless daemon sessions. Do not use an interactive prompt, poll for the human response, or rely only on generic notifications.
Quick Tasks work with Pi subagents just like proposal-based tasks:
sessionUuid to chorus_update_task and chorus_report_work/proposalchorus_create_tasks rejects tasks without them. They are your self-check contract; specific, testable AC enables autonomous verification and makes the entire workflow self-containedchorus_update_task to refine tasks (including AC) after creation rather than deleting and recreatingproposalUuid to attach follow-up or gap-filling tasks to an existing proposal — this keeps related work grouped in the same project context and DAGtask:admin continue autonomously after AC and independent review pass; all others use the evidence-rich asynchronous human handoff/develop/review/idea and /proposal/chorus