@deepseek-ai/dsh-skill 0.1.3-alpha.2 → 0.1.5-alpha.2

package/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/skill/skill/README.md
-README.md: 004c5a1bf01d16fd03e54463fd06e6cde168811e
-README.zh.md: 3d964c4bb7c0f5610152413cfd1de576852aab13
+README.md: 5bddf8483547fc08aebeadf11c835c18482b9abe
+README.zh.md: 0bf87d9a8468b49d1cd1ed4da6e3d3ade23825f3

package/README.md

@@ -9,7 +9,7 @@ English | [中文](README.zh.md)
 
 ## Summary
 
-Agents and users can access reusable, task-specific instructions through one lookup no matter where the instructions come from: any provider can contribute skills from local directories, embedded plugin data, or a remote service, and every consumer receives one merged catalog with the winning skill for each name and can load any skill's full instructions on demand. Mount this plugin when skills should be loadable from more than one source or from a non-filesystem source, and skip it when a composition loads no skills. It ships no skill content of its own — pair it with at least one provider (the shipped `dsh-skill-filesystem`), and with `dsh-tool-skill` when agents should load skills.
+Use this package to give agents and users one catalog of reusable, task-specific instructions collected from local directories, embedded plugin data, or remote services. It resolves duplicate names predictably, validates entries, tolerates unavailable sources without discarding usable results, and loads the selected skill's full instructions on demand. Mount it when a composition needs skills from multiple or non-filesystem sources; pair it with `dsh-skill-filesystem` for local discovery and `dsh-tool-skill` for model access, because it includes no skill content itself.
 
 ## Table of Contents
 

package/README.zh.md

@@ -9,7 +9,7 @@ kind: "package-reference"
 
 ## 概述
 
-agent（智能体）和用户可以通过单一查找使用可复用的任务专项指令，无论指令来自何处：任意提供方都可以从本地目录、嵌入式插件数据或远程服务贡献 skill（技能），每个消费方都会收到一份合并目录——每个名称对应胜出的 skill——并能按需加载任一 skill 的完整指令。当组合需要从多个来源或非文件系统来源加载 skill 时，请挂载本插件；当组合完全不加载 skill 时，请跳过。它自身不携带任何 skill 内容——请至少搭配一个提供方（随附的 `dsh-skill-filesystem`）；需要 agent 加载 skill 时，再搭配 `dsh-tool-skill`。
+使用本包可让 agent（智能体）和用户通过一个目录访问从本地目录、嵌入式插件数据或远程服务收集的可复用任务专项指令。它会以可预测的方式裁决重名项、验证条目、在来源不可用时保留可用结果，并按需加载所选 skill（技能）的完整指令。当组合需要多个来源或非文件系统来源的 skill 时，请挂载本包；本包自身不含 skill 内容，因此本地发现需搭配 `dsh-skill-filesystem`，模型访问需搭配 `dsh-tool-skill`。
 
 ## 目录
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@deepseek-ai/dsh-skill",
   "description": "Agent skill provider registry for the DeepSeek Harness",
-  "version": "0.1.3-alpha.2",
+  "version": "0.1.5-alpha.2",
   "publishConfig": {
     "access": "public"
   },
@@ -27,17 +27,17 @@
   ],
   "license": "MIT",
   "peerDependencies": {
-    "@deepseek-ai/dsh-llm": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-scope": "^0.1.3-alpha.2",
-    "@deepseek-ai/cordis": "^4.0.2"
+    "@deepseek-ai/cordis": "^4.0.2",
+    "@deepseek-ai/dsh-llm": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-scope": "^0.1.5-alpha.2"
   },
   "dependencies": {
-    "@deepseek-ai/dsh-util-values": "^0.1.3-alpha.2",
-    "@deepseek-ai/schemastery": "^3.18.2"
+    "@deepseek-ai/schemastery": "^3.18.2",
+    "@deepseek-ai/dsh-util-values": "^0.1.5-alpha.2"
   },
   "devDependencies": {
     "@deepseek-ai/cordis": "^4.0.2",
-    "@deepseek-ai/dsh-llm": "^0.1.3-alpha.2",
-    "@deepseek-ai/dsh-scope": "^0.1.3-alpha.2"
+    "@deepseek-ai/dsh-llm": "^0.1.5-alpha.2",
+    "@deepseek-ai/dsh-scope": "^0.1.5-alpha.2"
   }
 }