Rename stevenjj33/web-research to stevenjj33/web-search

plugins/stevenjj33/web-research/README.md → plugins/stevenjj33/web-search/README.md

@@ -1,10 +1,10 @@
-# web-research
+# web-search
 
-End-to-end web research for MiniMax Code: search the web via Tavily (keyless, no API key required) and fetch each URL with a free-first cascade — **defuddle → Tavily `/extract` → mcode in-app browser**. One Skill, one Python entry point, no bash required.
+End-to-end web search and research for MiniMax Code: search the web via Tavily (keyless, no API key required) and fetch each URL with a free-first cascade — **defuddle → Tavily `/extract` → mcode in-app browser**. One Skill, one Python entry point, no bash required.
 
 ## The problem it solves
 
-Research inside an agent usually means three separate tool calls, three failure modes, and a manual paste-into-context step. This plugin collapses the whole flow into a single Skill invocation that the agent runs end-to-end and then summarises.
+Web research inside an agent usually means three separate tool calls, three failure modes, and a manual paste-into-context step. This plugin collapses the whole flow into a single Skill invocation that the agent runs end-to-end and then summarises.
 
 ## Try it
 
@@ -15,7 +15,7 @@ After installing the plugin, ask the agent:
 **Expected result**: a directory `./research-output/` containing `01-…md` through `05-…md`, each with a one-line tag (`[defuddle]` / `[tavily extract]` / `[browser required]`) on stderr. The agent then summarises the files in chat. Direct invocation:
 
 ```bash
-python3 skills/web-research/scripts/research.py "向量数据库 最新进展" 5 ./research-output
+python3 skills/web-search/scripts/research.py "向量数据库 最新进展" 5 ./research-output
 ```
 
 Single-URL form:
@@ -61,12 +61,12 @@ This plugin talks to three network destinations, in order:
 ## Files
 
 ```text
-plugins/<owner>/web-research/
+plugins/<owner>/web-search/
 ├── plugin.json
 ├── README.md
 ├── LICENSE
 └── skills/
-    └── web-research/
+    └── web-search/
         ├── SKILL.md
         └── scripts/
             ├── research.py

plugins/stevenjj33/web-research/plugin.json → plugins/stevenjj33/web-search/plugin.json

@@ -1,8 +1,8 @@
 {
   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
-  "name": "web-research",
+  "name": "web-search",
   "version": "0.1.0",
-  "description": "End-to-end web research: search the web via Tavily keyless, then fetch each URL with a free-first cascade (defuddle → Tavily extract → mcode browser fallback). One Skill, one Python entry point.",
+  "description": "End-to-end web search and research: search the web via Tavily keyless, then fetch each URL with a free-first cascade (defuddle → Tavily extract → mcode browser fallback). One Skill, one Python entry point.",
   "author": {
     "name": "stevenjj33",
     "url": "https://github.com/stevenjj33"

plugins/stevenjj33/web-research/skills/web-research/SKILL.md → plugins/stevenjj33/web-search/skills/web-search/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: web-research
+name: web-search
 description: Use when the user asks to research a topic on the web, gather information from multiple sources, do a literature scan, summarize recent developments on a subject, or look up articles. Triggers on requests like "调研 X", "找几篇关于 Y 的文章", "research Z", "汇总 Q 的资料", "look up the latest on W". Do NOT use for single-URL fetches with no research framing (use the defuddle skill directly), local file operations, code edits, or tasks that do not need web data.
 license: Apache-2.0
 compatibility: Requires Python 3.8+. Defuddle CLI is optional but strongly recommended. Network access to https://api.tavily.com required.
@@ -8,7 +8,7 @@ metadata:
   version: "0.1.0"
 ---
 
-# web-research
+# web-search
 
 End-to-end web research pipeline: search → fetch with a free-first cascade → summarise.