docs(meta): 修 "6 中国原创" 文案漂移,准确反映 14+4+2 拆分#27
Open
jnMetaCode wants to merge 2 commits into
Open
Conversation
5 处描述把 skill 数量写成 "14 翻译 + 6 中国原创",但实际只有 4 个 chinese-* (chinese-code-review / chinese-commit-conventions / chinese-documentation / chinese-git-workflow)是中国原创;另外 2 个(mcp-builder / workflow-runner) 是上游 v5.0+ 已删除但本 fork 保留的 skill,不是中国原创。 - 结构化描述(3 个 plugin/marketplace JSON):拆为 "14 翻译 + 4 中国原创 + 2 上游历史保留" - 散文(README + package.json):改 "完整汉化 + 4 个中国原创 skills" (mcp-builder/workflow-runner 实质上是汉化版,归入"完整汉化"语义) 数学:14 + 4 + 2 = 20,与 .codex-plugin/plugin.json 已有的 "4 个中文 skills 沉淀" 对齐。
跟前一 commit 同性质——"国产原创" 语义明确指 chinese-original, mcp-builder/workflow-runner 是上游翻译版不是国产原创。 剩余 L44/46/L122/L133/L134 用的是 "中国特色"(china-specific) 框架,可以包含 fork-specific 历史保留,留给跟进 PR 单独处理。
This was referenced May 11, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
你要解决什么问题?
5 处对外描述把 skill 数量写成 "14 翻译 + 6 中国原创",但实际只有 4 个
chinese-*skill 是中国原创:chinese-code-reviewchinese-commit-conventionschinese-documentationchinese-git-workflow另外 2 个被算进 "6 中国原创" 的(
mcp-builder/workflow-runner)是上游 v5.0+ 已经删除、但本 fork 选择保留的历史 skill(issue #19 明确说明留到 v2.0 一起处理),它们是上游 skill 的汉化版,不是中国原创。用户感知:
skills/目录 → 找不到 6 个chinese-*目录,只有 4 个,会困惑.codex-plugin/plugin.json早就写 "4 个中文 skills 沉淀"(正确),跟另外 5 处描述互相矛盾这个 PR 做了什么改变?
5 个文件各改 1 行描述:
.claude-plugin/plugin.json+.claude-plugin/marketplace.json+.cursor-plugin/plugin.json):14 翻译 + 6 中国原创→14 翻译 + 4 中国原创 + 2 上游历史保留README.md+package.json):完整汉化 + 6 个中国原创 skills→完整汉化 + 4 个中国原创 skills(mcp-builder/workflow-runner 是汉化版本,归入"完整汉化"语义)不动 skill 内容、不动 installer 逻辑、不动
.codex-plugin/plugin.json(它已经写对)。这个改变适合放在核心库中吗?
适合。是本 fork 自己元数据的准确性修复,不涉及任何 skill 行为,对所有用户和所有下游(plugin marketplace / npm / Cursor plugin / Claude plugin)都生效。
你考虑了哪些替代方案?
using-superpowersskill 引用、破坏现有用户磁盘上已安装的 skill 路径,不能动。这个 PR 是否包含多个不相关的改变?
否。只动"描述"字段,5 个文件、5 行替换。
已有的 PR
最近相关历史:
测试环境
测试方式:本地
git diff --stat确认 5 文件各改 1 行;grep -rn \"6 中国原创\\|6 个中国\" --include=\"*.json\" --include=\"*.md\"确认无残留(README:268/281 提到的 "46 中国原创" 是另一个项目 agency-agents-zh 的,无关,不动)。评估
不适用 —— 纯文案改动,不影响 AI 行为。无 skill 内容修改、无 prompt 调优、无红旗表格变更。
严格性
人工审核
补漏(后续 commit a11d735)
Review 时发现 README L61 还有同性质漂移:
"国产原创"(domestic-original)和已修的 5 处 "中国原创" 同语义,已补到本 PR(同一性质,scope 内)。
README 还剩 4 处用 "中国特色 Skills(6 个)" 框架的描述(L44/46、L122、表格"上游有吗"列),不属于"中国原创/国产原创"漂移——"中国特色"语义可扩到 fork-specific 历史保留。这部分留作跟进 PR 统一处理,不塞本 PR,保持 scope 干净。