changqingla/lumen/domestic-global-research-status
Claude Code and agent skill by changqingla/lumen
- community
Checking that the SKILL.md file is still in the repository.
Write a domestic-versus-international research status analysis. Use when the user asks for research status across domestic and international contexts, progress comparisons, or cross-region research differences. If documents have been uploaded, write from document evidence first and supplement with web search only when evidence is insufficient. Prefer direct KB reading tools and do not depend on local reader_kb copy paths.
Install
npx vskill@latest install changqingla/lumen/domestic-global-research-statusSKILL.md
Domestic-Global Research Status Skill
Execution Rules
- Use
kb_list_docsfirst to confirm the document scope. - Documents first, web second: extract evidence from documents first, and use
web_searchonly when document evidence is insufficient. - If there are 3 or more documents, preferably use
spawn_agentfirst to extract document evidence in parallel. - If there are fewer than 3 documents, the main agent may read directly.
- When supplementing with web search, search only for missing information and avoid redundant accumulation.
Subagent Document Extraction Requirements (3+ Documents)
Each subagent task_description should require extraction of at least:
- Research direction and problem definition
- Representative domestic work, institutions, and methods
- Representative international work, institutions, and methods
- Key results and evaluation metrics
- Development-stage judgment and limitations
- Quotable evidence, including document ID and line numbers
Use only the following allowed_tools:
kb_list_docskb_read_dockb_read_doc_lineskb_search_doc
Web Supplement Rules
- Call
web_searchonly in the following cases:
- Documents lack evidence for either the domestic or international side.
- Recent progress from the last two years is missing.
- Key institutions, benchmark data, or policy background are missing.
- List information gaps first, then run targeted search queries.
- If
web_searchis unavailable or disabled, clearly state that web evidence cannot be supplemented.
Output Structure (Required)
Quality Bar
- Both the domestic and international sections must contain substantive content. Neither side may be missing.
- Every key judgment must include evidence mapping, such as document paths or web sources.
- Provide at least 3 domestic-versus-international differences and explain their causes.
- Include research gaps and next-step directions. Do not stop at descriptive reporting.
- If web materials support conclusions, mark their timeliness with dates or years.
- Do not use document IDs in the final report. Use document names instead when references are needed.
Final Delivery Requirements
- Organize the final result as a complete Markdown document, preferably generated in the sandbox, for example by using
sandbox_write_fileto writedocuments/domestic-global-research-status-{topic}.md. - After generation, call
sandbox_publish_fileto publish the Markdown file so the frontend can display a downloadable artifact. Do not stop after only callingwrite_file. - If self-checking is needed, use
sandbox_read_file,sandbox_read_lines, orsandbox_list_directoryto inspect file content and paths. - The final response must include delivery information for the published Markdown document and clearly tell the user that the file is available for download. Do not only say that it has been generated, and do not only paste the body text.
- Do not expose internal MinIO paths in the final response. If describing the result, only state that the Markdown document has been generated and made available for download, along with its purpose.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingruntimes/skills/public/domestic-global-research-status/SKILL.md
Popularity
- Repository stars
- 44
- Repository forks
- 1
- 7-day trend score
- 19
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/changqingla/lumen/domestic-global-research-status)