reflect

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Reflect

Adapted from Poteto's brainmaxxing

reflect

(MIT, see THIRD_PARTY.md). This repository has no separate memory vault: what the next agent must know lives in the repository itself, where it is reviewed like code.

改编自 Poteto 的 brainmaxxing

reflect

（MIT，见 THIRD_PARTY.md）。本仓库没有单独的 memory vault：下一位 Agent 必须了解的信息都保存在仓库本身，并像代码一样接受审查。

Process

流程

Scan the session for:
- mistakes made and corrections received;
- the product owner's preferences (how they want the app to behave or read);
- codebase knowledge gained (gotchas, why something is the way it is);
- library or tool quirks (
```
vendor/boring/
```
  , Flue, the model provider);
- friction in a skill (verify-app, new-agent) or in the verify CLI;
- repeated manual steps.
Skip anything trivial or already written down (grep AGENTS.md, docs/, the skills).
Route each learning (below), smallest durable form first.
Put the changes in the current branch, or a new one, and say what you changed.

扫描本次会话，查找：
- 犯过的错误及收到的纠正；
- 产品负责人的偏好（希望应用如何运行或呈现文案）；
- 获得的代码库知识（容易踩的坑、某项设计为何如此）；
- 库或工具的特殊行为（
```
vendor/boring/
```
  、Flue、模型提供商）；
- skill（verify-app、new-agent）或 verify CLI 中遇到的阻碍；
- 反复执行的手动步骤。
跳过琐碎内容或已经记录过的内容（grep AGENTS.md、docs/、skills）。
按照下述方式路由每条经验，优先采用最小且最持久的载体。
将修改放入当前分支或新建分支，并说明改动内容。

Routing, in this order

路由（按以下顺序）

Structure (principle-encode-lessons-in-structure): can it be a lint rule (
```
.oxlintrc.json
```
), an architecture rule (
```
scripts/verify/ARCHITECTURE.json
```
), a unit test, a
```
verify check
```
step, a validator in an agent's
```
index.mjs
```
, a law with its evidence (
```
docs/INVARIANTS.md
```
+
```
scripts/verify/VERIFY.json
```
) or a model (
```
formal/
```
)? Then encode it there and write no prose. A mistake an agent repeats becomes a rule in
scripts/verify/ARCHITECTURE.json
, with the law or decision it enforces, a fix hint, and a fixture in
```
test/unit/architecture.test.mjs
```
proving it fires; better still, make the mistake impossible (a type, a single helper, a constraint) so no rule is needed.
A skill (a pull request on hachej/boring-stack,
```
skills/<skill>/SKILL.md
```
): the learning is about how a skill's procedure works: fix the procedure.
The feature map (
```
docs/verify/<area>.md
```
): a gotcha about driving a feature.
docs/DECISIONS.md: a decision and its reason ("we do X because Y; not Z because W").
AGENTS.md: a rule every agent needs on every task. Keep it short: move detail to a skill.
Upstream: a gap in
```
@boring/agent
```
,
```
@boring/files
```
or
```
@boring/chat
```
goes to hachej/boring-ui-v3 as an issue or a pull request, never as an edit of
```
vendor/
```
.
The template (hachej/boring-app): a lesson every new app needs. Say so, so it lands in the template; existing apps take it by a normal pull request.

结构（principle-encode-lessons-in-structure）：如果可以将经验实现为 lint 规则（
```
.oxlintrc.json
```
）、架构规则（
```
scripts/verify/ARCHITECTURE.json
```
）、单元测试、
```
verify check
```
步骤、Agent 的
```
index.mjs
```
中的验证器、一条附有证据的法则（
```
docs/INVARIANTS.md
```
+
```
scripts/verify/VERIFY.json
```
）或一个模型（
```
formal/
```
），就将其编码到对应位置，并且不写说明性文字。Agent 重复犯下的错误应成为
scripts/verify/ARCHITECTURE.json
中的一条规则，并附上它所执行的原则或决策、修复提示，以及
```
test/unit/architecture.test.mjs
```
中一个证明规则会触发的 fixture；更好的做法是让错误不可能发生（通过一个类型、一个单一辅助函数或一项约束），从而不需要规则。
Skill（在 hachej/boring-stack 上提交 pull request，路径为
```
skills/<skill>/SKILL.md
```
）：如果经验与某个 skill 的工作流程有关，就修复该流程。
功能地图（
```
docs/verify/<area>.md
```
）：记录操作某项功能时遇到的坑。
docs/DECISIONS.md：记录一项决策及其原因（“我们采用 X，因为 Y；不采用 Z，因为 W”）。
AGENTS.md：记录每位 Agent 在每项任务中都需要遵循的规则。内容应保持简短，将详细信息移至 skill。
上游：
```
@boring/agent
```
、
```
@boring/files
```
或
```
@boring/chat
```
中存在的缺口，应在 hachej/boring-ui-v3 上提交 issue 或 pull request，绝不能直接编辑
```
vendor/
```
。
模板（hachej/boring-app）：记录每个新应用都需要的经验。明确说明这一点，使其进入模板；现有应用则通过普通 pull request 获取该经验。

Summary

摘要

undefined

undefined

Reflect summary

Structural: [rules, tests, checks added]
Skills: [skill files changed, one line each]
Docs: [DECISIONS / AGENTS / feature map entries]
Upstream or template: [issues or PRs to open]

undefined

Structural: [rules, tests, checks added]
Skills: [skill files changed, one line each]
Docs: [DECISIONS / AGENTS / feature map entries]
Upstream or template: [issues or PRs to open]

undefined