Back to Details

dynamic-workflow-mode

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Dynamic Workflow Mode

动态工作流模式

Use this skill when a coding agent can generate or adapt a task-local harness instead of only following a static command flow. The goal is to turn dynamic workflow mode into a disciplined system: temporary harnesses for one-off work, shared skill extraction for repeated work, and observable control pane checkpoints for teams.
当编码Agent可以生成或适配任务专属工具包，而非仅遵循静态命令流程时，可使用此技能。目标是将动态工作流模式转化为一套规范化系统：用于一次性工作的临时工具包、用于重复工作的共享技能提取，以及面向团队的可观测控制面板检查点。

When To Activate

激活场景

  • The user mentions dynamic workflows, custom harnesses, harness-per-task, adaptive workflows, or Claude Code dynamic workflow mode.
  • A task needs a custom loop, evaluator, crawler, fixture generator, watcher, or local dashboard.
  • Multiple agents need the same repeatable process but the process is not yet captured as a shared skill.
  • A workflow needs durable handoff artifacts, eval evidence, or operator approval before merge.
  • 用户提及动态工作流、自定义工具包、单任务专属工具包、自适应工作流或Claude Code动态工作流模式。
  • 任务需要自定义循环、评估器、爬虫、测试数据生成器、监控器或本地仪表盘。
  • 多个Agent需要执行相同的可重复流程，但该流程尚未被提炼为共享技能。
  • 工作流在合并前需要持久化的交接工件、评估证据或操作员审批。

Core Contract

核心约定

Dynamic workflow mode should produce a task-local harness only when the harness is cheaper and safer than manually driving the same steps. The harness must have:
  • Objective: the outcome it owns and the outcome it explicitly does not own.
  • Inputs: files, URLs, prompts, data sources, credentials policy, and user-provided constraints.
  • Outputs: commits, reports, screenshots, status files, or control pane snapshots.
  • Eval: at least one pass/fail check tied to the task, not only "it ran".
  • Handoff: a short artifact that tells the next operator what happened, what is blocked, and how to resume.
只有当任务专属工具包比手动执行相同步骤更经济、更安全时，动态工作流模式才应生成该工具包。工具包必须包含：
  • 目标：它负责达成的结果，以及明确不负责的结果。
  • 输入：文件、URL、提示词、数据源、凭证策略和用户提供的约束条件。
  • 输出：提交记录、报告、截图、状态文件或控制面板快照。
  • 评估：至少一个与任务绑定的通过/失败检查，而非仅检查“是否运行”。
  • 交接：一份简短的工件，告知下一位操作员已完成的工作、阻塞点以及恢复方式。

Dynamic Harness Decision Tree

动态工具包决策树

  1. One-shot task: keep it inline. Do not invent a harness.
  2. Repeated task with changing inputs: create a task-local harness and keep it under a temp or project-local working area.
  3. Repeated task across teammates or repos: extract the pattern into a shared skill.
  4. Task with external state, queueing, or approvals: add control pane visibility before adding more automation.
  5. Task with safety risk: add an eval gate and a human merge gate before autonomous execution.
  1. 一次性任务：直接内联处理，无需创建工具包。
  2. 输入可变的重复任务：创建任务专属工具包，并将其保存在临时或项目本地工作区下。
  3. 跨团队成员或仓库的重复任务：将该模式提炼为共享技能。
  4. 涉及外部状态、队列或审批的任务：在添加更多自动化前，先增加控制面板可见性。
  5. 存在安全风险的任务：在自动执行前添加评估关卡和人工合并关卡。

Task-Local Harness Template

任务专属工具包模板

Use this structure before writing code:
markdown
undefined
编写代码前请使用以下结构：
markdown
undefined

Dynamic Workflow Harness

动态工作流工具包

Objective:
  • Ship:
  • Do not ship:
Inputs:
  • Repo or workspace:
  • External systems:
  • Credentials policy:
Loop:
  1. Discover current state.
  2. Generate or update the smallest useful artifact.
  3. Run eval checks.
  4. Record status and handoff.
  5. Stop on failed gate, unclear ownership, or unsafe external action.
Eval:
  • Command:
  • Expected pass signal:
  • Failure owner:
Handoff:
  • Status:
  • Evidence:
  • Next action:
undefined
目标:
  • 交付:
  • 不交付:
输入:
  • 仓库或工作区:
  • 外部系统:
  • 凭证策略:
循环:
  1. 发现当前状态。
  2. 生成或更新最小可用工件。
  3. 运行评估检查。
  4. 记录状态和交接信息。
  5. 遇到失败关卡、所有权不明确或不安全的外部操作时停止。
评估:
  • 命令:
  • 预期通过信号:
  • 失败负责人:
交接:
  • 状态:
  • 证据:
  • 下一步操作:
undefined

Shared Skill Extraction

共享技能提取

Promote a task-local harness into a shared skill only when at least two of these are true:
  • The same workflow appears in multiple sessions, repos, teams, or launches.
  • The workflow needs specific language, tool, or safety sequencing.
  • Failures repeat because operators skip a gate or lose context.
  • The workflow has a stable input/output contract.
  • The workflow benefits from a control pane, status board, or team handoff.
When extracting, write the skill first in 
skills/<name>/SKILL.md
. Add command shims only if a legacy slash-entry surface is still required.
仅当满足以下至少两个条件时，才可将任务专属工具包升级为共享技能：
  • 同一工作流出现在多个会话、仓库、团队或发布流程中。
  • 工作流需要特定的语言、工具或安全序列。
  • 由于操作员跳过关卡或丢失上下文导致失败重复发生。
  • 工作流具有稳定的输入/输出约定。
  • 工作流可从控制面板、状态看板或团队交接中获益。
提取技能时，请先在
skills/<name>/SKILL.md
中编写技能内容。仅当仍需要兼容旧版斜杠入口时，才添加命令垫片。

Control Pane Checkpoints

控制面板检查点

Dynamic workflow mode becomes team-usable when it exposes state. Record these checkpoints whenever the task spans more than one session:
  • Plan: objective, owner, acceptance criteria, and risky external systems.
  • Queue: work items, assigned agent role, branch/worktree, and dependency edges.
  • Run: active harness, current loop step, recent eval result, and token/cost signal if available.
  • Gate: test results, browser screenshots, security review, and merge readiness.
  • Handoff: what is done, what failed, what needs a human decision.
If the repo has ECC2 state enabled, prefer adding or reading checkpoints through the ECC control pane or state-store-backed scripts instead of scattering untracked notes.
当任务跨多个会话时，动态工作流模式需暴露状态才能供团队使用。请记录以下检查点：
  • 计划：目标、负责人、验收标准和存在风险的外部系统。
  • 队列：工作项、分配的Agent角色、分支/工作树以及依赖关系。
  • 运行：当前激活的工具包、当前循环步骤、最近的评估结果，以及可用的令牌/成本信号。
  • 关卡：测试结果、浏览器截图、安全评审和合并就绪状态。
  • 交接：已完成的工作、失败的内容、需要人工决策的事项。
如果仓库已启用ECC2状态，请优先通过ECC控制面板或基于状态存储的脚本添加或读取检查点，而非分散记录未追踪的笔记。

Eval Gates

评估关卡

Every dynamic harness needs a task-specific eval. Pick the cheapest reliable gate:
Work TypeEval Gate
Code featureFocused test, lint, coverage, and one integration path
UI/control paneBrowser smoke with screenshot and overflow/error checks
Agent workflowFixture transcript or seeded work item with expected routing
Research/contentSource-neutral brief, claim checklist, and publish-ready outline
IntegrationDry-run command, config validation, and no-secret scan
Do not claim a dynamic workflow is reusable until the eval can be rerun by another teammate.
每个动态工具包都需要针对任务的专属评估。选择成本最低且可靠的关卡：
工作类型评估关卡
代码功能聚焦测试、代码检查、覆盖率检查以及一条集成路径验证
UI/控制面板浏览器冒烟测试，附带截图及溢出/错误检查
Agent工作流测试用例记录或带有预期路由的种子工作项
研究/内容来源中立的摘要、主张核对清单及可发布的大纲
集成空运行命令、配置验证及无敏感信息扫描
只有当其他团队成员可重新运行评估时，才可声称该动态工作流具备可复用性。

Anti-Patterns

反模式

  • Generating scripts that hide the real decision logic from the operator.
  • Treating dynamic workflow mode as permission to skip tests.
  • Creating one-off docs when a shared skill or status artifact is the real product.
  • Running multiple agents without ownership, merge gate, or conflict policy.
  • Letting raw private research data leak into public docs.
  • 生成对操作员隐藏真实决策逻辑的脚本。
  • 将动态工作流模式视为跳过测试的许可。
  • 当实际需要的是共享技能或状态工件时，却创建一次性文档。
  • 在没有明确所有权、合并关卡或冲突策略的情况下运行多个Agent。
  • 让原始私有研究数据泄露到公开文档中。

Output Standard

输出标准

Finish with:
  • The harness or skill path.
  • The eval commands and results.
  • The control pane or handoff artifact path.
  • The next reusable extraction candidate.
完成工作后需提供：
  • 工具包或技能路径。
  • 评估命令及结果。
  • 控制面板或交接工件路径。
  • 下一个可复用提取候选对象。