跳到正文
cccskills
免费在 GitHub 公开

pipeline

[OMX] Configurable pipeline orchestrator for sequencing stages

中文简介正在准备中。当前显示原文说明。

digris/openbroadcast.org星标 9(GitHub 9 + cccskills 0)

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md4.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Pipeline Skill

$pipeline is the configurable pipeline orchestrator for OMX. It sequences stages through a uniform PipelineStage interface, with state persistence and resume support.

Default Autopilot Pipeline

The default Autopilot pipeline sequences:

deep-interview -> ralplan -> ultragoal (+ team if needed) -> code-review -> ultraqa

$team is conditional: use it only inside an active Ultragoal story when independent lanes or broad verification make coordinated parallel execution useful. Explicit legacy Ralph pipelines remain available through custom stages, but Ralph is not the advertised default Autopilot loop.

Configuration

Pipeline parameters are configurable per run:

ParameterDefaultDescription
maxRalphIterations10Quality-gate retry ceiling; legacy option name retained for compatibility
workerCount2Number of Codex CLI team workers
agentTypeexecutorAgent type for team workers

Stage Interface

Every stage implements the PipelineStage interface:

interface PipelineStage {
  readonly name: string;
  run(ctx: StageContext): Promise<StageResult>;
  canSkip?(ctx: StageContext): boolean;
}

Stages receive a StageContext with accumulated artifacts from prior stages and return a StageResult with status, artifacts, and duration.

Built-in Stages

  • deep-interview: Requirements clarification and ambiguity gate.
  • ralplan: Consensus planning (planner + architect + critic). Skips only when both prd-*.md and test-spec-*.md planning artifacts already exist and durable consensus evidence records Architect approval followed by Critic approval. Plan/test-spec files alone are not consensus evidence. If either review is missing, blocked, out of order, or non-approving, the stage remains in ralplan or fails with an explicit blocker/max-iteration outcome instead of progressing to execution. Carries any deep-interview-*.md spec paths forward for traceability.
  • ultragoal: Durable goal-mode execution with .omx/ultragoal ledgers. Launch $team only from inside an Ultragoal story when parallel lanes are warranted.
  • code-review: Merge-readiness review gate.
  • ultraqa: Adversarial QA gate after a clean review; docs-only/trivially non-runtime changes may record an explicit skip reason.
  • team-exec and ralph-verify: Legacy/custom pipeline adapters retained for explicit non-default pipelines.

State Management

Pipeline state persists via the ModeState system at .omx/state/pipeline-state.json. The HUD renders pipeline phase automatically. Resume is supported from the last incomplete stage.

  • On start: omx state write --input '{"mode":"pipeline","active":true,"current_phase":"stage:ralplan"}' --json
  • On stage transitions: omx state write --input '{"mode":"pipeline","current_phase":"stage:<name>"}' --json
  • On completion: omx state write --input '{"mode":"pipeline","active":false,"current_phase":"complete"}' --json

API

import {
  runPipeline,
  createAutopilotPipelineConfig,
  createDeepInterviewStage,
  createRalplanStage,
  createUltragoalStage,
  createCodeReviewStage,
  createUltraqaStage,
} from './pipeline/index.js';

const config = createAutopilotPipelineConfig('build feature X', {
  stages: [
    createDeepInterviewStage(),
    createRalplanStage(),
    createUltragoalStage(),
    createCodeReviewStage(),
    createUltraqaStage(),
  ],
});

const result = await runPipeline(config);

Relationship to Other Modes

  • autopilot: Autopilot can use pipeline as its execution engine (v0.8+)
  • team: Pipeline delegates execution to team mode (Codex CLI workers)
  • ultragoal: Autopilot delegates durable execution to Ultragoal by default
  • team: Optional execution engine inside an Ultragoal story when parallel lanes are needed
  • ralph: Available only for explicit legacy/custom pipelines
  • ralplan: Pipeline planning runs RALPLAN consensus planning

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

[OMX] Run an anti-slop cleanup/refactor/deslop workflow

中文简介正在准备中。当前显示原文说明。

digris/openbroadcast.org92026年8月31日 更新

analyze

免费

[OMX] Run read-only deep repository analysis and return a ranked synthesis with explicit confidence, concrete file references, and clear evidence-vs-inference boundaries. Use when a user says 'analyze', 'investigate', 'why does', 'what's causing', or needs grounded cross-file explanation before any changes are proposed.

中文简介正在准备中。当前显示原文说明。

digris/openbroadcast.org92026年8月31日 更新

ask

免费

[OMX] Ask a local external advisor CLI (Claude or Gemini) and capture a reusable artifact

中文简介正在准备中。当前显示原文说明。

digris/openbroadcast.org92026年8月31日 更新

autopilot

免费

[OMX] Strict autonomous loop: $deep-interview -> $ralplan -> $ultragoal (+ $team if needed) -> $code-review -> $ultraqa

中文简介正在准备中。当前显示原文说明。

digris/openbroadcast.org92026年8月31日 更新

[OMX] Stateful validator-gated research loop with native-hook persistence

中文简介正在准备中。当前显示原文说明。

digris/openbroadcast.org92026年8月31日 更新

[OMX] Durable professor-critic research workflow over Codex goal mode without reviving deprecated omx autoresearch

中文简介正在准备中。当前显示原文说明。

digris/openbroadcast.org92026年8月31日 更新

查看 digris 的全部技能

报告此技能的问题