evanflow

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

EvanFlow

A TDD-driven iterative feedback loop for software development with Claude Code. 16 cohesive skills + 2 custom subagents walk an idea from brainstorm → plan → execute → tdd → iterate, with checkpoints throughout. Vertical-slice TDD, parallel coder/overseer review, executable cohesion contracts, context compaction. Never auto-commits — the user controls every git op.

一种基于TDD驱动的、与Claude Code配合使用的软件开发迭代反馈循环。16个内聚技能+2个自定义子Agent将想法从头脑风暴→规划→执行→TDD→迭代全程落地，过程中设置多个检查点。包含垂直切片TDD、并行编码/监督审核、可执行内聚契约、上下文压缩等特性。绝不自动提交——所有Git操作均由用户掌控。

Single Entry Point:

evanflow-go

单一入口：

evanflow-go

When the user says "let's evanflow this", "use evanflow", "evanflow this idea", "run this through evanflow", or anything similar — invoke

evanflow-go

. It's the orchestrator that walks the entire loop end-to-end (brainstorm → plan → execute → tdd → iterate → STOP), announces each step, respects checkpoints (design approval, plan approval), and hands off to the right sub-skill at each phase. The user gets the full EvanFlow workflow without having to remember which sub-skill applies when.

evanflow-go

is conductor, not autopilot — every checkpoint is real and the user can interrupt or switch paths anytime.

当用户说出“让我们用EvanFlow处理这个”、“使用EvanFlow”、“用EvanFlow处理这个想法”、“通过EvanFlow运行这个”或类似表述时，调用

evanflow-go

。它是整个循环（头脑风暴→规划→执行→TDD→迭代→停止）的编排器，会宣布每个步骤、遵守检查点（设计批准、规划批准），并在每个阶段切换到对应的子技能。用户无需记住何时使用哪个子技能，即可获得完整的EvanFlow工作流。

evanflow-go

是指挥者而非自动驾驶——每个检查点都是真实存在的，用户可随时中断或切换路径。

Shared Vocabulary

共享术语

Every

evanflow-*

skill speaks this. Cross-reference here, don't redefine.

Module — any unit with interface + implementation (function, class, package). Scale-agnostic.
Interface — complete caller knowledge: type signature, invariants, ordering constraints, error modes, performance characteristics.
Depth — large behavior behind a small interface = deep (good). Large interface, thin behavior = shallow (avoid).
Seam — where an interface lives; a place behavior can shift without editing in place.
Adapter — concrete implementation satisfying an interface at a seam.
Deletion test — does removing this module concentrate complexity across N callers, or does complexity vanish? The first is a real module; the second is bloat.
Vertical slice — one test → one impl → repeat. Never write all tests first then all code (horizontal slicing produces tests of imagined behavior).
Behavior through public interface — tests describe what, not how. They survive refactors. If a rename breaks a test but behavior didn't change, the test was wrong.
Grill — opt-in interview pattern, embedded as a labeled section inside planning skills. Stress-test before committing to a path. Not a separate skill invocation in EvanFlow.
Ubiquitous language — canonical domain terms in
```
CONTEXT.md
```
. New terms added as discovered.
Mockup quick-mode — when user just wants visual concepts, skip spec/plan ceremony. Produce mockups directly in whatever form the project uses (HTML files, Figma frames, ASCII layouts, etc.) — no full design loop required.

所有

evanflow-*

技能均使用这套术语。此处可交叉引用，无需重复定义。

Module（模块） — 任何包含接口+实现的单元（函数、类、包）。与规模无关。
Interface（接口） — 完整的调用方认知：类型签名、不变量、顺序约束、错误模式、性能特征。
Depth（深度） — 小接口背后承载大逻辑=深度模块（优质）。大接口仅对应单薄逻辑=浅层模块（需避免）。
Seam（衔接点） — 接口所在的位置；无需原地修改即可切换逻辑的地方。
Adapter（适配器） — 在衔接点处满足接口要求的具体实现。
Deletion test（删除测试） — 删除该模块后，复杂度会分散到N个调用方，还是随之消失？前者是有效模块；后者是冗余代码。
Vertical slice（垂直切片） — 编写一个测试→实现对应功能→重复该过程。绝不要先写完所有测试再写所有代码（水平切片会针对想象中的逻辑编写测试）。
Behavior through public interface（通过公共接口定义行为） — 测试描述做什么，而非怎么做。这类测试能在重构后依然有效。如果重命名操作破坏了测试但逻辑未变，说明测试本身存在问题。
Grill — 可选的访谈模式，嵌入在规划类技能的标记章节中。在确定方案前进行压力测试。不属于EvanFlow中的独立技能调用。
Ubiquitous language（通用语言） —
```
CONTEXT.md
```
中的标准领域术语。新术语会在发现后添加。
Mockup quick-mode（快速原型模式） — 当用户仅需视觉概念时，跳过规格/规划流程。直接以项目适用的形式生成原型（HTML文件、Figma框架、ASCII布局等）——无需完整设计循环。

Hard Rules (apply to every evanflow skill)

硬性规则（适用于所有EvanFlow技能）

Never auto-commit, never auto-stage, never auto-finish. Every git write op (
```
commit
```
,
```
push
```
,
```
merge
```
,
```
rebase
```
,
```
tag
```
,
```
branch -d/-D
```
) requires the user to explicitly ask for it in the current turn. Even
```
git add
```
should not happen on the agent's initiative — leave files unstaged until the user signals they're about to commit.
No "finish/integrate" workflow on the agent's initiative. After implementation + iterate, the agent reports what was done and stops. The user decides whether to commit, merge, open a PR, keep iterating, or change direction.
Never invent values you don't authoritatively have. This includes: file paths, env var values, API keys, secret values, IDs (UUIDs, foreign keys, third-party object IDs), URLs, port numbers, hostnames, version numbers, third-party service names, function names you haven't verified exist. If unsure, STOP and ask — don't guess. Action-hallucination (an agent confidently doing the wrong thing) is the most dangerous failure mode in agentic coding (industry research, 2026). The cost of asking is one round-trip; the cost of acting on a hallucinated value is potentially catastrophic.
Watch for context drift. If you find yourself re-asking established questions, contradicting earlier decisions, or losing track of constraints set earlier in the session, invoke
```
evanflow-compact
```
to preserve anchors and propose a
```
/clear
```
. ~65% of agent failures trace to context drift, not raw token exhaustion.
No skill tax. Ad-hoc questions don't require a skill invocation. Skills are tools, not a tollbooth.
No forced spec/plan paths. Specs and plans live wherever the user wants. Default to
```
docs/
```
only if no preference is stated.
No forced sub-skill chains. Each evanflow skill stands alone. Hand-offs are suggestions, not mandates.
Verify before claiming done. Run the project's quality checks (typecheck, lint, test) and confirm output before reporting completion.

绝不自动提交、绝不自动暂存、绝不自动完成。 所有Git写入操作（
```
commit
```
、
```
push
```
、
```
merge
```
、
```
rebase
```
、
```
tag
```
、
```
branch -d/-D
```
）都需要用户在当前对话轮次中明确要求。即使是
```
git add
```
也不应由Agent主动执行——保持文件未暂存状态，直到用户示意准备提交。
Agent不得主动启动“完成/集成”工作流。 实现+迭代完成后，Agent仅汇报已完成的工作并停止。由用户决定是否提交、合并、发起PR、继续迭代或改变方向。
绝不要编造非权威来源的信息。 包括：文件路径、环境变量值、API密钥、保密值、ID（UUID、外键、第三方对象ID）、URL、端口号、主机名、版本号、第三方服务名称、未确认存在的函数名。若不确定，停止操作并询问——不要猜测。动作幻觉（Agent自信地执行错误操作）是智能体编码中最危险的故障模式（2026年行业研究）。询问仅需一次交互往返；基于幻觉信息操作的代价可能是灾难性的。
警惕上下文漂移。 如果发现自己重复询问已确认的问题、与之前的决定矛盾、或忘记会话早期设定的约束，调用
```
evanflow-compact
```
来保留关键信息并建议执行
```
/clear
```
。约65%的智能体故障源于上下文漂移，而非原始令牌耗尽。
无技能使用门槛。 临时问题无需调用技能。技能是工具，而非关卡。
无强制规格/规划路径。 规格和规划可存储在用户指定的任意位置。仅当用户无偏好时默认使用
```
docs/
```
目录。
无强制子技能调用链。 每个EvanFlow技能均可独立使用。技能切换是建议而非强制要求。
完成前先验证。 运行项目的质量检查（类型检查、代码 lint、测试）并确认输出后，再汇报完成状态。

The Default Loop

默认循环

1. (optional)  evanflow-brainstorming   — clarify intent, propose 2-3 approaches, embedded grill.
                                          Mockup-only requests use mockup quick-mode.
                                          (Hands off to evanflow-prd for substantial features.)
2. (if non-trivial) evanflow-writing-plans — file structure, bite-sized tasks, embedded grill.
                                          Step 2.5: parallelization check — offers
                                          coder-overseer if 3+ independent units exist.
3. EXECUTE     evanflow-executing-plans  — task harness: critical review, TaskCreate, inline
                                          verification, blockers, quality checks. Step 0:
                                          parallelization check (offers coder-overseer).
        OR     evanflow-coder-overseer   — same harness role, parallel: contract → RED checkpoint →
                                          coders → per-coder overseers → integration overseer.

   ↳ INSIDE every code-writing task in EXECUTE:
       evanflow-tdd                      — vertical-slice RED → GREEN → REFACTOR per cycle.
                                          NOT a separate phase. The discipline that runs
                                          inside the task harness for any production code.

4.             evanflow-iterate          — self-review loop AFTER all tasks are done:
                                          re-read diff, fix issues, re-run checks,
                                          (UI) view the page. Repeat until clean.
5.             STOP. Report what was done. Await user direction.

The loop is interlinked end-to-end. Each step actively offers the right next-step skill when conditions match — including offering

evanflow-coder-overseer

at both planning time (step 2) and execution time (step 3) when the plan is parallelizable.

Cross-cutting:

evanflow-compact

runs alongside the loop whenever context drift symptoms appear or at clean phase boundaries. Don't wait for token-limit warnings — proactive compaction at boundaries is far higher quality than reactive mid-flow compaction.

There is no auto-commit, no auto-finish, no auto-integration step. The user controls when to commit, when to merge, when to push, when to open a PR. After step 5, the agent reports and waits.

Ad-hoc questions, quick mockups, exploratory reads: no skill invoked. Just answer.

1. (可选)  evanflow-brainstorming   — 明确意图，提出2-3种实现方案，内置Grill环节。
                                          仅需原型的请求使用快速原型模式。
                                          （针对复杂功能，会切换到evanflow-prd。）
2. (若任务非 trivial) evanflow-writing-plans — 文件结构规划、拆分小任务，内置Grill环节。
                                          步骤2.5：并行化检查——若存在3个及以上独立单元，
                                          提供coder-overseer模式。
3. 执行阶段     evanflow-executing-plans  — 任务管理：严格审核、TaskCreate、内联
                                          验证、障碍处理、质量检查。步骤0：
                                          并行化检查（提供coder-overseer模式）。
        或     evanflow-coder-overseer   — 同样的任务管理角色，采用并行模式：契约→RED检查点→
                                          编码人员→对应监督者→集成监督者。

   ↳ 在执行阶段的所有代码编写任务中：
       evanflow-tdd                      — 每个循环遵循垂直切片RED → GREEN → REFACTOR流程。
                                          这不是独立阶段，而是任何生产代码编写任务中需遵循的规范。

4.             evanflow-iterate          — 所有任务完成后的自我审查循环：
                                          重新查看代码差异、修复问题、重新运行检查、
                                          （UI场景）查看页面。重复操作直到无问题。
5.             停止。汇报已完成的工作。等待用户指令。

循环全程相互关联。 每个步骤会在条件匹配时主动推荐合适的下一步技能——包括在规划阶段（步骤2）和执行阶段（步骤3），当方案可并行时推荐

evanflow-coder-overseer

。

跨环节支持： 当出现上下文漂移症状或进入清晰的阶段边界时，

evanflow-compact

会伴随循环运行。不要等到令牌限制警告才处理——在阶段边界主动压缩上下文的质量远高于在流程中被动处理。

无自动提交、无自动完成、无自动集成步骤。 用户掌控提交、合并、推送、发起PR的时机。步骤5完成后，Agent仅汇报工作并等待指令。

临时问题、快速原型、探索性阅读：无需调用技能，直接回答即可。

When to Invoke Each Skill

各技能调用时机

Trigger	Skill
"Let's evanflow this" / "use evanflow" / "evanflow this idea" / any "run this through evanflow"	`evanflow-go` (entry point — walks the whole loop)
"Help me think through X" / "I want to build Y" / new feature scoping (without saying "evanflow")	`evanflow-brainstorming` (or invoke `evanflow-go` if user wants the full loop)
"Plan out Z" / spec exists, ready to break into tasks	`evanflow-writing-plans`
"Execute the plan" / picking up an existing plan doc	`evanflow-executing-plans`
Any production code change	`evanflow-tdd`
"Polish this" / "review this" / "make sure it's clean" / after implementation	`evanflow-iterate`
Plan has 3+ truly independent parallel tasks with a shared contract	`evanflow-coder-overseer` (instead of `evanflow-executing-plans` )
Long session, drift symptoms, major phase boundary, or session feels heavy	`evanflow-compact`
"Commit this" / "push" / "merge" / "open a PR" — user-initiated only	(no skill — just do it directly when explicitly asked)
"Write a PRD for X" / new feature in PRD shape	`evanflow-prd`
"Refactor X" / "this file is too big" / architecture concerns	`evanflow-improve-architecture`
"Design the API for X" / interface design	`evanflow-design-interface`
"Update CONTEXT.md" / new domain term emerged	`evanflow-glossary`
"Debug Y" / unexpected behavior, root-cause needed	`evanflow-debug`
Code review (giving or receiving)	`evanflow-review`
"File a bug for X" / QA session	`evanflow-qa`
Token-heavy session, want compression	`caveman` (upstream, kept as-is)

触发语	技能
“让我们用EvanFlow处理这个” / “使用EvanFlow” / “用EvanFlow处理这个想法” / 任何类似“通过EvanFlow运行这个”的表述	`evanflow-go` （入口点——执行完整循环）
“帮我梳理X的思路” / “我想开发Y” / 新功能范围界定（未提及“evanflow”）	`evanflow-brainstorming` （若用户需要完整循环，可调用 `evanflow-go` ）
“规划Z的实现” / 已有规格，准备拆分为任务	`evanflow-writing-plans`
“执行规划” / 基于现有规划文档开展工作	`evanflow-executing-plans`
任何生产代码变更	`evanflow-tdd`
“优化这个” / “审查这个” / “确保代码整洁” / 实现完成后	`evanflow-iterate`
规划包含3个及以上真正独立的并行任务且有共享契约	`evanflow-coder-overseer` （替代 `evanflow-executing-plans` ）
会话时长较长、出现漂移症状、进入主要阶段边界或会话负载过重	`evanflow-compact`
“提交这个” / “推送” / “合并” / “发起PR” — 仅用户主动发起时	（无对应技能——仅在明确要求时直接执行）
“为X编写PRD” / 以PRD形式呈现新功能	`evanflow-prd`
“重构X” / “这个文件太大了” / 架构相关问题	`evanflow-improve-architecture`
“设计X的API” / 接口设计	`evanflow-design-interface`
“更新CONTEXT.md” / 出现新的领域术语	`evanflow-glossary`
“调试Y” / 出现意外行为，需排查根本原因	`evanflow-debug`
代码审查（发起或接收）	`evanflow-review`
“为X提交Bug” / QA环节	`evanflow-qa`
会话令牌占用过高，需要压缩	`caveman` （上游技能，保持原样）

Compatible Tooling

兼容工具

EvanFlow is self-contained — none of these are required. But some standalone utilities from other Claude Code skill sets compose well alongside if you happen to have them installed:

A git worktrees skill, for isolating big refactors
A verification-before-completion rule (already baked into
```
evanflow-executing-plans
```
and
```
evanflow-iterate
```
)
A parallel-agents dispatch pattern (already used inside
```
evanflow-design-interface
```
and
```
evanflow-coder-overseer
```
)
A token-compression mode for very long sessions (complements
```
evanflow-compact
```
)

For the historical record of which existing-ecosystem skills inspired which EvanFlow skills, and which were deliberately not adopted, see

docs/skills-audit.md

EvanFlow是独立系统——以下工具均非必需。但如果已安装其他Claude Code技能集中的独立工具，部分工具可与EvanFlow良好配合：

Git工作区技能，用于隔离大型重构
完成前验证规则（已内置到
```
evanflow-executing-plans
```
和
```
evanflow-iterate
```
中）
并行智能体调度模式（已在
```
evanflow-design-interface
```
和
```
evanflow-coder-overseer
```
中使用）
令牌压缩模式，适用于超长会话（补充
```
evanflow-compact
```
功能）

关于现有生态系统中的哪些技能启发了EvanFlow的技能设计，以及哪些技能被刻意未采用的历史记录，请查看

docs/skills-audit.md

。

evanflow

Original

Translation

EvanFlow

EvanFlow

Single Entry Point:
`evanflow-go`

单一入口：
`evanflow-go`

Shared Vocabulary

共享术语

Hard Rules (apply to every evanflow skill)

硬性规则（适用于所有EvanFlow技能）

The Default Loop

默认循环

When to Invoke Each Skill

各技能调用时机

Compatible Tooling

兼容工具

evanflow

Original

Translation

EvanFlow

EvanFlow

Single Entry Point: evanflow-go

单一入口：evanflow-go

Shared Vocabulary

共享术语

Hard Rules (apply to every evanflow skill)

硬性规则（适用于所有EvanFlow技能）

The Default Loop

默认循环

When to Invoke Each Skill

各技能调用时机

Compatible Tooling

兼容工具

Single Entry Point:
`evanflow-go`

单一入口：
`evanflow-go`