跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
搜索与研究

openrig-software-factory

Use when a user wants a continuing software team for a real repository, or has a first OpenRig team and needs a repeatable path for reviewed work and later tasks.

mvschwarz · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add mvschwarz/openrig --skill openrig-software-factory

技能说明


name: openrig-software-factory description: >- Use when a user wants a continuing software team for a real repository, or has a first OpenRig team and needs a repeatable path for reviewed work and later tasks. metadata: cli_surfaces_referenced: - context get - context list - context show - grow - queue create - queue handoff - workflow compile - workflow instantiate-lifecycle openrig: stage: WIP transfer_test: pending

OpenRig Software Factory

Start with a useful repository outcome and add coordination when it earns its cost. A beginner can complete reviewed work without Workflow. These are choices using existing capabilities, not stages everyone must graduate through.

Choose how the team works

NeedStart hereAdd more when…
One change, close human guidanceManual/team work: give an owner the outcome, use repository instructions, implement and obtain the chosen independent check.Work must survive turns or move between seats.
Continuing work with visible ownershipQueue-supported orchestration: use rig queue create, claim work, then rig queue handoff with the candidate/evidence to the next owner. Record real blockers and the continuation. No Workflow instance is needed.Repeated steps need an explicit dependency graph and permitted exits.
An explicit execution contractWorkflow: inspect rig workflow compile, then deliberately use rig workflow instantiate-lifecycle. Advance its packets through the workflow projection mechanism.The actual project needs reusable profiles, additional roles or gates.

For the concrete queue loop, wake behavior and optional two-slice Workflow, read references/worked-example.md. Installed copy: rig context get skills/core/openrig-software-factory/references/worked-example.md. A roadmap, YAML file or wake does not execute work or authorize a new outcome.

Establish the working agreement

Read the repository instructions, current work and desired user-visible result. Verify the intended instance, code/work roots, real seat addresses and native readiness. Reuse a suitable small team; an existing agent can bootstrap it. A kernel operator is optional and is not automatically the project owner.

Agree the work boundary, time/spend limit, who answers unresolved choices, and when to stop: checked result, no authorized next work, exhausted budget, or a real user/permission/provider blocker. Background daemon checks are not themselves model turns, but delivered wakes and resumed work can spend tokens. Prefer an event-driven wait to frequent empty reminders. Wakes cannot answer a user question, clear a permission prompt or guarantee progress.

Choose permissions before launching or assigning work. Offer ordinary prompts, persistent rules for selected commands, or deliberately broader access. Follow Applying a permission policy to perform the user's choice and verify it in the target conversation. Preserve restrictions and unrelated settings. A whole rig allowance covers every verb, not just reads; it does not grant new product authority or change everyone else's defaults.

Keep purpose, acceptance, decisions and evidence in existing project files. Deliver selected context and obtain each seat's scope reaction; retrieval alone is not peer delivery. The owner carries the candidate through the chosen check and bounded repairs, reports how to try it, and retains the next authorized task or explicitly reports none. Preserve work and custody before a supported stop.

Grow your factory

Choose the team size separately from the coordination method above:

  1. Use the two-agent starter. Keep the existing owner and independent checker while that pair meets the workload. The owner can implement and coordinate.
  2. Add one or two seats to the running rig. This is the usual next step. Follow Grow the running team for rig grow commands, readiness/context/work assignment, and saving the expanded topology. Existing sessions need no rebuild or down/up cycle solely to add capacity.
  3. Author a custom rig when you want a different structure. Read OpenRig Architect, available through rig context get skills/core/openrig-architect/SKILL.md. Request: “Design a user-owned rig for [outcome] using the compatible RigSpec/AgentSpec guidance. Reuse suitable agents, define responsibilities and context, and validate the files. Preserve the existing rig and agree any new launch.”

As independent work grows, the original owner can concentrate on orchestration, multiple builders can implement separate outcomes, and the checker can retain independent review capacity. Record that division explicitly; adding seats does not assign work, change permissions or create parallelism. Agree file/worktree boundaries and integration ownership, follow the project's existing review policy, and keep active concurrency within the user's time/spend budget. Two seats are an entry point, not a finished factory or a maximum.

Read compatible guidance

Before installation, use this file and companion at the same published tag or commit as the selected package. After installation:

rig --version
rig context list --json
rig context show skills/core/openrig-software-factory --json
rig context get skills/core/openrig-software-factory/SKILL.md

Compare build identity as well as version. Preserve missing, unreadable or older recipe results; do not silently substitute newer main or skip a missing companion.

Find the compatible permission guide

Retrieve the maintained procedure with rig context get skills/applying-a-permission-policy/SKILL.md. For source or archive readers, locate it below; the companion getting-started guide contains optional broader launch-mode recipes un

阅读完整来源 ↗