re0-workflow
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseTurn one stated intent into an ordered skill graph, show it, and run the steps the session may run.
将一个明确陈述的意图转换为有序 Skill 图,展示该图,并执行当前会话有权执行的步骤。
Goal
目标
Someone who does not know this suite's catalog should be able to say what they want and see it done. Select and order the installed skills that serve the human's stated intent, show the order before anything runs, run each step the session holds authority for, and stop at the first step that needs the human, with a report of what ran.
不了解本套件目录的用户应能说明自己想要什么,并看到任务被完成。选择并排序能够满足人类明确意图的已安装 Skill,在任何内容运行之前展示顺序,执行当前会话有权运行的每个步骤,并在第一个需要人工介入的步骤停止,同时报告执行了什么。
Workflow
工作流
-
Read the human's stated intent and the installed roster from the host catalog or skill directories. If given only live state without a stated intent, ask for the intent rather than infer it. Read each candidate's contract and invocation lane:means user-only; otherwise it is model-invoked.
disable-model-invocation: true -
Select only skills whose triggers and outputs serve the intent. A frozen pipeline (a skill whose own contract runs a fixed sequence of other skills) that already serves the intent is one node, never expanded; read its members only to type it, so the node counts as writing when any member writes and is awhen any member is user-only. If none fits, show zero steps and say so; if one suffices, use exactly one node and say ordering is trivial. A skill the intent or a selected contract calls for that the roster lacks stays as a
user-handoffstep, and when a selected step needs its output the run ends with the stop condition unmet, never as a silent skip. Do not pad the graph, require an orientation skill, invent a pipeline skill, or substitute another skill for a missing one.skip -
Order the selected steps by their contracts' prerequisites: a step depends on another when its firing precondition needs that step's output. Detect cycles before showing the graph; if one exists, the whole result is anaming the cycle, such as
reject, with no steps and no partial order. Give the graph one observable stop condition, the state that means the intent was served; zero steps or askill-a -> skill-b -> skill-aends at its own report.reject -
Give every step an identifier, a target (the skill that acts, or the question when the step is a human decision no skill makes), predecessor identifiers, exactly one type, firing precondition, expected output limited to the target's own contract, skippable condition, and cost owner. Assign its type by the first row below that applies, so a missing user-only skill is a. Where a contract does not say whether its skill writes, count it as writing; where its lane cannot be read, count it as user-only. A step whose type depends on a predecessor's output is shown as conditional with the types it can take, and typed once that output exists.
skipType Meaning and precondition Cost owner skipThe step does not run, and the graph goes on without it: condition not applicable, skill not installed, or no authority that anyone present could grant. A step that depends on it is skipped too, with the same reason. None. user-handoffThe human acts: the target is user-only, the step is destructive or irreversible, a human decision is needed, or the work needs authority the human holds and the session does not. The human's time, at their discretion. invoke-model-skillThe router runs it: none of the rows above applies, so the target is installed and model-invoked, the session already holds authority for the work, and the step is neither destructive nor irreversible. This run's budget. rejectNot a step: the whole result when the request cannot be served as a graph, naming the cycle when cyclic. None. -
For each, say what the human does and what result to bring back: for a skill, the exact invocation they type, in the host's syntax with the installed name (a destructive step whose skill is model-invoked is still typed by the human); for a decision, the question and the answers that change the next step. If the host's invocation syntax is unknown, ask instead of inventing it.
user-handoff -
Before any step runs, show the whole typed graph in order, every field of every step, why each sits where it does, and the stop condition; ask here for any host invocation syntax step 5 could not find. If the human asked only for the order, stop here. If anystep anywhere in the graph, before or after a handoff, writes a file, record or artifact, ask once, now, for approval of the shown plan. That approval accepts the plan and every write it shows, across a resume, until the plan changes; it grants no authority a step lacked, so it never turns a
invoke-model-skillinto a run step. If no step to run writes, run right after showing the plan. If the human edits the plan, order it again, check for cycles again, and show it again before running.user-handoff -
Run in order. For eachstep, call the Skill tool with that step's target, once for that step, passing the intent and its predecessors' outputs. Before starting the next step, check its expected output: the file or record exists, or the skill's own report states the result. If a step fails, stop there; if its output breaks a later step's precondition, stop there or mark that later step
invoke-model-skillwith the reason. Never retry by swapping in another skill.skip -
Stop at the first. The stop report is the state a resume reads: the graph as shown, whether approval was given, every step run with its result, the handoff and what to bring back, and the steps still waiting. When the human returns with that result in the same conversation, a new invocation reads that report and checks the result against the handoff step's expected output: a match becomes that step's output and the run goes on from the next step under the same approval, while a changed or failed result re-plans from that step and shows the new graph before running. If the report is out of reach, start again from step 1.
user-handoff -
End with the graph as shown, each step's outcome (ran with its result, skipped with its reason, handed off, or waiting behind a stop), and whether the stop condition was reached or the run stopped early at a named step (a handoff or a failure). When a skipped or missing step's output is one the stop condition needs, say the run ended with the stop condition unmet.
-
读取人类明确陈述的意图,并从宿主目录或 Skill 目录读取已安装 Skill 清单。如果只提供了实时状态而没有明确意图,则询问意图,不要推断。读取每个候选 Skill 的 contract 和 invocation lane:表示仅限用户调用(user-only);否则为模型调用(model-invoked)。
disable-model-invocation: true -
仅选择触发条件和输出能够服务于该意图的 Skill。如果某个冻结流水线(某个 Skill 自身的 contract 会按固定顺序运行其他 Skill)已经可以满足该意图,则将其作为一个节点,绝不展开;只读取其成员以确定该节点的类型,因此,只要任一成员会写入,该节点就计为写入型(writing);只要任一成员为 user-only,该节点就计为。如果没有任何 Skill 适合,显示零个步骤并说明情况;如果一个 Skill 已经足够,则恰好使用一个节点并说明排序很简单。如果意图或所选 contract 调用了清单中不存在的 Skill,则将其保留为
user-handoff步骤;当某个所选步骤需要它的输出时,运行应以停止条件未满足结束,绝不能静默跳过。不要为图填充内容、强制加入 orientation Skill、虚构流水线 Skill,也不得用另一个 Skill 替代缺失的 Skill。skip -
按照各 Skill contract 中的前置条件对所选步骤排序:如果某一步的触发前提需要另一步的输出,则该步骤依赖另一步。在显示图之前检测循环;如果存在循环,整个结果应为,并命名该循环,例如
reject,且不包含任何步骤或部分顺序。为整个图设置一个可观察的停止条件,即表示意图已得到满足的状态;零步骤或skill-a -> skill-b -> skill-a均以各自的报告结束。reject -
为每个步骤指定标识符、目标(执行操作的 Skill,或没有 Skill 能作出决定时由人决定的问题)、前置步骤标识符、恰好一种类型、触发前提、预期输出(仅限目标自身的 contract)、可跳过条件和成本承担方。按照下表中第一个适用的行分配类型,因此,缺少 user-only Skill 应归为。如果 contract 未说明其 Skill 是否会写入,则视为会写入;如果无法读取 invocation lane,则视为 user-only。类型取决于前置步骤输出的步骤应显示为 conditional,并列出其可能采用的类型;待该输出产生后再确定具体类型。
skip类型 含义与前提 成本承担方 skip该步骤不运行,图在没有它的情况下继续:条件不适用、Skill 未安装,或现场任何人都无法授予所需权限。依赖它的步骤也会被跳过,原因相同。 无。 user-handoff由人执行:目标为 user-only、步骤具有破坏性或不可逆性、需要人工决策,或工作需要由人掌握而当前会话不掌握的权限。 由人自行支配其时间。 invoke-model-skill由 router 执行:上述各行均不适用,因此目标已安装且可由模型调用,当前会话已拥有执行该工作的权限,并且该步骤既不具破坏性也不可逆。 本次运行的预算。 reject不是步骤:当请求无法作为图来满足时,作为整个结果;若存在循环,则在其中命名该循环。 无。 -
对于每个,说明人要做什么以及要带回什么结果:对于 Skill,给出应输入的确切调用命令,使用宿主语法和已安装名称(即使具有破坏性的步骤所对应 Skill 可由模型调用,也仍由人输入);对于决策,给出问题以及会改变下一步的答案。如果不知道宿主的调用语法,则询问,不得编造。
user-handoff -
在任何步骤运行之前,按顺序展示整个已定类型的图、每个步骤的每个字段、每个步骤为何位于当前位置,以及停止条件;在此处询问步骤 5 未能找到的任何宿主调用语法。如果人类只要求给出顺序,则在此停止。如果图中的任何步骤——无论位于人工交接之前还是之后——会写入文件、记录或 artifact,则此时一次性询问是否批准所示计划。该批准接受此计划及其所展示的每次写入,并跨 resume 持续有效,直至计划发生变化;它不授予步骤原本没有的权限,因此绝不会将
invoke-model-skill变成运行步骤。如果没有要运行的步骤会写入,则在展示计划后立即运行。如果人类编辑计划,则重新排序、再次检查循环,并在运行前再次展示。user-handoff -
按顺序运行。对于每个步骤,使用该步骤的目标调用 Skill 工具一次,并传入意图及其前置步骤的输出。在开始下一步之前,检查其预期输出:文件或记录已存在,或者 Skill 自身的报告声明了结果。如果某一步失败,则在该处停止;如果其输出破坏了后续步骤的前提条件,则在该处停止,或将后续步骤标为
invoke-model-skill并说明原因。绝不通过替换成另一个 Skill 来重试。skip -
在第一个处停止。停止报告是 resume 读取的状态:所示的图、是否已批准、每个已运行步骤及其结果、交接内容及需要带回的内容,以及仍在等待的步骤。当人类在同一会话中带着该结果返回时,新调用会读取该报告,并将结果与交接步骤的预期输出核对:匹配时,该结果成为此步骤的输出,并在同一批准下从下一步继续;结果发生变化或失败时,从该步骤重新规划,并在运行前展示新图。如果无法读取该报告,则从步骤 1 重新开始。
user-handoff -
最终以所示的图结束,列出每个步骤的结果(已运行及其结果、已跳过及其原因、已交接,或在停止点之后等待),并说明是否已达到停止条件,或运行是否在某个具名步骤(交接或失败)提前停止。如果被跳过或缺失的步骤所产生的输出是停止条件所需的内容,则说明运行以停止条件未满足而结束。
Rules
规则
- Never select itself or its alias
re0-workflowas a step; the alias only forwards here, so either would loop.paperthin - The router writes nothing of its own; every write comes from a run step's own skill under that skill's contract.
- Destructive or irreversible means deleting, force-pushing, publishing, tagging, sending a message to someone, or spending money. Such a step is a even when its skill is model-invoked.
user-handoff - Never run a user-only skill, and never drop an installed one to make the order runnable; it stays in the graph as a . A step the router cannot run is a
user-handoffor auser-handoff, never a silent recommendation, and a skip never counts as success.skip - picks one next action from live state and runs nothing; this skill orders and runs a graph for one stated intent.
nba - owns a fixed conditional graph for newly changed output; select it as one node when it serves the intent, never reproduce its members.
sip
- 绝不将 本身或其别名
re0-workflow选为步骤;该别名只会转发到此处,因此任一项都会形成循环。paperthin - router 自身不写入任何内容;每次写入都来自某个运行步骤自身的 Skill,并遵循该 Skill 的 contract。
- 破坏性或不可逆是指删除、强制推送、发布、打标签、发送消息或花费金钱。此类步骤始终是 ,即使其 Skill 可由模型调用。
user-handoff - 绝不运行 user-only Skill,也绝不为了使顺序可运行而删除已安装的 Skill;它会作为 保留在图中。router 无法运行的步骤必须是
user-handoff或user-handoff,绝不能只是静默建议,而skip绝不视为成功。skip - 会从实时状态中选取一个下一步操作且不运行任何内容;本 Skill 则针对一个明确意图对图进行排序并运行。
nba - 负责针对新变化输出构建固定的条件图;当它能够满足意图时,将其选作一个节点,绝不重现其成员。
sip
Verification
验证
Before running the first step, and again before the final report:
- Every selected target's trigger, output, installation, invocation lane and authority were read from its own contract.
- Every step carries all its fields and exactly one type; the graph has one observable stop condition, and a cycle was rejected with the whole cycle named.
- Every installed user-only, destructive or decision step is a with the exact invocation or the question, and what to bring back, never
user-handoff.invoke-model-skill - The graph was shown before anything ran, and approval was asked once when a step to run writes.
- Each run step's expected output was checked before the next step started, and the run stopped at the first .
user-handoff - The report gives each step's outcome and whether the stop condition was reached or at which step the run stopped early.
在运行第一个步骤之前,以及生成最终报告之前,均须完成以下核验:
- 已从每个所选目标自身的 contract 读取其触发条件、输出、安装状态、invocation lane 和权限。
- 每个步骤都包含所有字段且恰好有一种类型;图具有一个可观察的停止条件;若存在循环,则已用完整循环名称拒绝该结果。
- 每个涉及已安装的 user-only Skill、破坏性操作或人工决策的步骤都是 ,并提供确切调用命令或问题以及需要带回的内容,绝不是
user-handoff。invoke-model-skill - 在运行任何内容之前已展示图;存在写入步骤时,已一次性询问批准。
- 在开始下一步之前已检查每个运行步骤的预期输出,并在第一个 处停止。
user-handoff - 报告给出了每个步骤的结果,以及是否达到停止条件,或运行在哪个步骤提前停止。