quality-refinement-autoloop

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Quality Refinement Autoloop

质量精炼自动循环

Use this when the user says the result is wrong, ugly, not aligned, not textured, not animated, not exportable, or otherwise below expectation. The goal is not to keep tweaking blindly. The goal is to convert failure into a reusable, generic skill improvement before trying again.

当用户反馈结果有误、效果不佳、未对齐、无纹理、无动画、无法导出，或存在其他未达预期的问题时，使用本流程。其目标不是盲目反复调整，而是在重试之前，将失败转化为可复用的通用Skill改进。

Autoloop phases

自动循环阶段

0. Freeze and preserve

0. 冻结与保留

Stop making product changes immediately.
Preserve the last accepted baseline and the failed artifact.
Name the failed branch/version honestly; do not overwrite accepted outputs.

立即停止对产出的修改。
保留最后一个被接受的基线版本和失败的工件。
如实命名失败的分支/版本；不得覆盖已接受的产出。

1. Evidence capture

1. 证据采集

Collect the smallest evidence set that proves the failure:

user feedback quote or summary;
source/reference files used;
current output path/version;
relevant render/contact sheet/overlay/audit report;
scene/material/object inventory if the failure is inside Blender.

收集能够证明失败的最小证据集：

用户反馈原文或摘要；
使用过的源文件/参考文件；
当前产出路径/版本；
相关的渲染结果/联系表/叠加层/审核报告；
若失败发生在Blender内部，需提供场景/材质/对象清单。

2. Diagnose failure dimension

2. 诊断失败维度

Classify the primary gap:

geometry / silhouette / landmarks;
multiview/depth consistency;
UV / atlas / texture fit;
closed surface coverage (front/back/side);
look/material/lighting calibration;
animation/motion/export truth;
orchestration/handoff between skills;
missing validator or missing deterministic helper script.

对主要差距进行分类：

几何/轮廓/标志性结构；
多视图/深度一致性；
UV/图集/纹理适配；
封闭表面覆盖度（正面/背面/侧面）；
外观/材质/光照校准；
动画/运动/导出真实性；
Skill之间的编排/交接；
缺少验证器或确定性辅助脚本。

3. Skill-gap decision

3. Skill差距决策

Ask: does the current skill stack already contain a generic method for this failure?

If yes: run the existing skill and repair the artifact.
If no: add/refine a generic skill first, then repair.
If repeated failures come from skill interplay, update the harmonizer/handoff rule, not just a leaf skill.

自问：当前Skill栈是否已经包含应对此类失败的通用方法？

是：运行现有Skill并修复工件。
否：先添加/优化通用Skill，再进行修复。
若反复失败源于Skill之间的交互问题，需更新协调器/交接规则，而非仅修改单个叶子Skill。

4. Sanitize the lesson

4. 经验脱敏

Before writing a skill change:

remove project/client/asset names;
remove secrets, raw logs, private paths, personal data, and copyrighted source content;
keep only reusable method, gates, scripts, and failure patterns;
describe inputs/outputs generically;
prefer deterministic scripts for fragile audits.

在编写Skill变更之前：

移除项目/客户/资产名称；
移除密钥、原始日志、私有路径、个人数据以及受版权保护的源内容；
仅保留可复用的方法、校验规则、脚本和失败模式；
以通用方式描述输入/输出；
对于脆弱的审核环节，优先使用确定性脚本。

5. Patch skill stack

5. 补丁更新Skill栈

Apply the smallest publishable change:

one concise skill or one concise section in an existing skill;
optional helper script if the validation is repeatable;
harmonizer update if ordering/handoff changed;
manifest entry/version update.

应用最小可发布变更：

新增一个简洁的Skill，或在现有Skill中新增一个简洁的章节；
若验证可重复，可选添加辅助脚本；
若排序/交接逻辑变更，更新协调器；
更新清单条目/版本号。

6. Validate skill change

6. 验证Skill变更

Required checks:

scripts compile;
manifest paths exist;
skill graph audit passes with harmonizer present;
sanitizer scan passes for project-specific terms;
if applicable, run the new helper against the failed artifact and save a report.

必做检查：

脚本可编译；
清单路径存在；
包含协调器的Skill图审核通过；
脱敏扫描通过，未发现项目专属术语；
如适用，针对失败工件运行新的辅助脚本并保存报告。

7. Repair product only after skill gate

7. 仅在Skill校验通过后修复产出

Rebuild or repair from the correct baseline using the improved skill. Do not reuse rejected outputs unless explicitly marked as source evidence.

使用改进后的Skill从正确的基线重建或修复工件。不得复用被拒绝的产出，除非明确标记为源证据。

8. Release prep when requested

8. 按需准备发布

Only when the user asks to publish/commit/push:

fetch latest remote and confirm local branch is up to date;
resolve/harmonize conflicts before staging;
bump version using semver appropriate to scope;
update README / plugin README / CHANGELOG / VERSIONING when relevant;
run sanitizer and compile/audit checks;
stage, commit, and push using the configured remote.

仅当用户要求发布/提交/推送时执行：

获取最新远程仓库内容，确认本地分支为最新版本；
在暂存前解决/协调冲突；
根据变更范围使用semver提升版本号；
如相关，更新README / 插件README / CHANGELOG / VERSIONING；
运行脱敏检查和编译/审核检查；
使用配置的远程仓库执行stage、commit、push。

Hard rules

硬性规则

Do not bake task-specific examples into public skills.
Do not call overlay curves/planes “texture coverage” unless the real mesh surface also passes coverage gates.
Do not tune lighting/materials to hide geometry or UV failures.
Do not claim export support if the effect exists only in Blender Python or a render sequence.
Do not push without an explicit user request and an up-to-date remote check.

不得将任务专属的示例植入公共Skill中。
除非真实网格表面也通过覆盖度校验，否则不得将叠加曲线/平面称为“纹理覆盖”。
不得通过调整光照/材质来掩盖几何或UV问题。
如果效果仅存在于Blender Python或渲染序列中，不得声称支持导出。
未经用户明确请求且未完成远程仓库最新状态检查，不得执行push操作。

Recommended artifacts

Scripts

脚本

```
scripts/ralph_autoloop_plan.py
```
creates a generic failure-classification and loop plan from feedback/artifact hints.
```
scripts/sanitize_skill_contributions.py
```
scans skill files for project-specific or private terms before publication.
```
scripts/release_readiness_check.py
```
performs lightweight manifest/docs/version/path checks before commit/push.

```
scripts/ralph_autoloop_plan.py
```
：根据反馈/工件线索生成通用的失败分类和循环计划。
```
scripts/sanitize_skill_contributions.py
```
：在发布前扫描Skill文件，检查是否存在项目专属或私有术语。
```
scripts/release_readiness_check.py
```
：在commit/push前执行轻量级的清单/文档/版本/路径检查。