Design and run bounded procedures in environments where current conditions are uncertain. The skill separates agent judgment from precise tool actions, verifies each effect, and records checkpoints so interrupted work can resume from observed evidence.
中文简介正在准备中。当前显示英语简介。
Use when a bounded real-world procedure has a deterministic happy path but brownfield, variable, or partially knowable state; when an operation must resume from verified evidence; or when deciding whether agent judgment or ordinary code should own a procedure's control loop.
安装前可以查看交给 AI 代理的指令内容。
An Agent-Operated Workflow is a bounded procedure whose control loop belongs to an agent. The agent observes, interprets, sequences bounded actions, verifies their effects, adapts, and escalates genuine ambiguity. Deterministic code remains the exact substrate; it does not pretend to understand every state of a brownfield world.
agent-operated-software.Calling a model is not enough. A deterministic program that consults a model still owns its loop.
Use an agent when the happy path is deterministic but the environment is brownfield, variable, partially knowable, or disproportionately expensive to model exhaustively. The judgment is in discovering what is true and choosing the next safe act.
Prefer ordinary code when the state space is closed and code is simpler and more reliable than judgment. A parser, fixed data transformation, or fully enumerated state machine does not become better because an agent drives it.
| Owner | Responsibility |
|---|---|
| Runbook | owns policy, the mental model, checkpoints, stop conditions, and escalation rules |
| Deterministic tools | own context gathering and bounded exact actions |
| Agent | owns interpretation, sequencing, adaptation, and effect verification |
| Human | owns destructive ambiguity and product policy |
The runbook guides judgment; tools enforce the invariants that must not be arguable.
An interrupted or timed-out mutation is indeterminate, never failed by assumption and never safe to retry blind. Where a compatibility period is safer, separate reversible preparation from the destructive finalizer. Idempotence is a claim to prove per action, not a label for the whole run.
Expose composable verbs, not an optimistic end-to-end controller. Help is inert. Read and plan modes are explicit. Mutations are narrow and independently readable. A failure should say what was observed, why the tool stopped, what remains unchanged, the safe next choices, and where its evidence lives. Keep checkpoints durable, effects observable, and recovery possible without private developer knowledge.
A capability composition is a reusable recipe; this is the execution architecture that operates capabilities toward an outcome. Promote a proven workflow to the composition shelf only after use.
Public example: load skills/core/openrig-upgrade/SKILL.md with
rig context get for the upgrade runbook. Its adjacent scripts/ directory
contains the bounded inspection, backup, plugin-refresh and migration helpers.
Follow that runbook for the procedure; this skill carries the reusable contract.
还没有评价。欢迎分享你的使用感受。
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。
Automate website interactions through a command-line browser tool. Navigate pages, fill forms, extract text, save screenshots or PDFs, reuse login sessions, and compare page states to check the effects of actions or website changes.
中文简介正在准备中。当前显示英语简介。
Design and maintain applications where OpenRig agents help run the system. Organize instructions, shared state, and artifact checks, then trace unexpected behavior to the code, skill, or schema that needs repair.
中文简介正在准备中。当前显示英语简介。
Create reusable starting configurations that combine an agent’s role, startup context, and source history. The skill guides registry entries, checks whether their sources are current, and manages their progression from initial capture to recommendation or retirement.
中文简介正在准备中。当前显示英语简介。
Guides the design and review of agent startup context, including role files and links to authoritative records. It helps identify stale guidance, missing updates, overloaded startup files, and instructions that lose the purpose of the work.
中文简介正在准备中。当前显示英语简介。
Configure selected OpenRig command permissions in Claude Code or Codex at the agreed project or user scope. Preserve existing restrictions, verify that settings load and behave as intended, and record additions so they can be removed later.
中文简介正在准备中。当前显示英语简介。
Turn rough meeting notes, customer requests, and product ideas into structured backlog entries, a list of possible improvements. Capture who needs each idea and why, categorize it, and update matching entries with new evidence.
中文简介正在准备中。当前显示英语简介。