SciAtlas Trend Report
Use this skill to build a trend report from search-papers evidence only.
Operating Contract
- Do not call any SciAtlas downstream command. The only SciAtlas retrieval command allowed is
search-papers.
- Own the end-to-end novice flow: install or locate the CLI, guide registration, configure environment variables, run retrieval, inspect artifacts, and write the trend report.
- Ask the user only for email, verification code, token, or the desired time range if it is essential.
- Do not ask the user to run shell commands when tool access is available.
- Do not reveal the full token.
Zero-Start Bootstrap
- Check whether the
sciatlas executable exists without invoking a SciAtlas command: use Get-Command sciatlas -ErrorAction SilentlyContinue on Windows PowerShell or command -v sciatlas on macOS/Linux. Install if needed with python -m pip install -e ./sciatlas or python -m pip install "git+https://github.com/zjunlp/SciAtlas.git#subdirectory=sciatlas".
- If there is no
SCIATLAS_API_KEY, guide registration at http://sciatlas.openkg.cn/register, asking for email/code/token only when needed.
- Configure:
$env:SCIATLAS_API_BASE_URL = "http://sciatlas.openkg.cn"
$env:SCIATLAS_API_KEY = "<token>"
setx SCIATLAS_API_BASE_URL "http://sciatlas.openkg.cn"
setx SCIATLAS_API_KEY "<token>"
export SCIATLAS_API_BASE_URL="http://sciatlas.openkg.cn"
export SCIATLAS_API_KEY="<token>"
- Use
search-papers --top-k 1 as the only token smoke test if needed.
Search Plan
Run only search-papers. Use a time range whenever possible:
sciatlas search-papers --retrieval-mode hybrid --query "<topic>" --time-range "<start-end>" --keyword "high:<core topic>" --top-k 12 --top-keywords 0 --max-titles 0 --max-refs 0 --bias-citation high --bias-exploration middle --ranking-profile impact --report-max-items 12
If the user asks for "recent trends", default to the last five complete years unless the current year matters.
If the field has older foundations, run one foundation search without the recent time range:
sciatlas search-papers --retrieval-mode hybrid --query "<topic> foundational work" --keyword "high:<core topic>" --top-k 6 --top-keywords 0 --max-titles 0 --max-refs 0 --bias-citation high --ranking-profile impact --report-max-items 6
Reading Artifacts
Read report.md and response.json. Build a timeline ledger:
- Paper title.
- Year.
- Main contribution.
- Theme.
- Whether it is foundation, transition, consolidation, or emerging direction.
- Evidence phrase.
Trend Analysis Method
- Sort papers by year.
- Bucket years into phases. Use natural breaks in the result set, not arbitrary equal chunks.
- For each phase, identify the dominant problem, method, and evaluation pattern.
- Track what changed: data scale, model architecture, retrieval strategy, benchmark, deployment setting, or theoretical framing.
- Identify representative papers for each phase and explain why they represent that phase.
- Separate "well-supported trend" from "possible emerging signal." Emerging signals need at least 2 papers or a clear recent change in framing.
- End with open questions and next searches.
Deliverable
Return:
- Search command(s), with token omitted.
- Timeline table.
- 3-5 trend phases.
- Representative papers per phase.
- Emerging directions and weak signals.
- Next
search-papers queries.
1---2name: sciatlas-trend-report3description: Use only SciAtlas search-papers to take a novice user from zero setup to a final timeline-oriented research trend report, including setup, registration guidance, configuration, retrieval, artifact reading, and synthesis. Trigger when the user asks for topic history, field evolution, recent trends, representative papers over time, or emerging directions.4---56# SciAtlas Trend Report78Use this skill to build a trend report from `search-papers` evidence only.910## Operating Contract1112- Do not call any SciAtlas downstream command. The only SciAtlas retrieval command allowed is `search-papers`.13- Own the end-to-end novice flow: install or locate the CLI, guide registration, configure environment variables, run retrieval, inspect artifacts, and write the trend report.14- Ask the user only for email, verification code, token, or the desired time range if it is essential.15- Do not ask the user to run shell commands when tool access is available.16- Do not reveal the full token.1718## Zero-Start Bootstrap19201. Check whether the `sciatlas` executable exists without invoking a SciAtlas command: use `Get-Command sciatlas -ErrorAction SilentlyContinue` on Windows PowerShell or `command -v sciatlas` on macOS/Linux. Install if needed with `python -m pip install -e ./sciatlas` or `python -m pip install "git+https://github.com/zjunlp/SciAtlas.git#subdirectory=sciatlas"`.212. If there is no `SCIATLAS_API_KEY`, guide registration at `http://sciatlas.openkg.cn/register`, asking for email/code/token only when needed.223. Configure:2324```powershell25$env:SCIATLAS_API_BASE_URL = "http://sciatlas.openkg.cn"26$env:SCIATLAS_API_KEY = "<token>"27setx SCIATLAS_API_BASE_URL "http://sciatlas.openkg.cn"28setx SCIATLAS_API_KEY "<token>"29```3031```bash32export SCIATLAS_API_BASE_URL="http://sciatlas.openkg.cn"33export SCIATLAS_API_KEY="<token>"34```35364. Use `search-papers --top-k 1` as the only token smoke test if needed.3738## Search Plan3940Run only `search-papers`. Use a time range whenever possible:4142```bash43sciatlas search-papers --retrieval-mode hybrid --query "<topic>" --time-range "<start-end>" --keyword "high:<core topic>" --top-k 12 --top-keywords 0 --max-titles 0 --max-refs 0 --bias-citation high --bias-exploration middle --ranking-profile impact --report-max-items 1244```4546If the user asks for "recent trends", default to the last five complete years unless the current year matters.4748If the field has older foundations, run one foundation search without the recent time range:4950```bash51sciatlas search-papers --retrieval-mode hybrid --query "<topic> foundational work" --keyword "high:<core topic>" --top-k 6 --top-keywords 0 --max-titles 0 --max-refs 0 --bias-citation high --ranking-profile impact --report-max-items 652```5354## Reading Artifacts5556Read `report.md` and `response.json`. Build a timeline ledger:5758- Paper title.59- Year.60- Main contribution.61- Theme.62- Whether it is foundation, transition, consolidation, or emerging direction.63- Evidence phrase.6465## Trend Analysis Method66671. Sort papers by year.682. Bucket years into phases. Use natural breaks in the result set, not arbitrary equal chunks.693. For each phase, identify the dominant problem, method, and evaluation pattern.704. Track what changed: data scale, model architecture, retrieval strategy, benchmark, deployment setting, or theoretical framing.715. Identify representative papers for each phase and explain why they represent that phase.726. Separate "well-supported trend" from "possible emerging signal." Emerging signals need at least 2 papers or a clear recent change in framing.737. End with open questions and next searches.7475## Deliverable7677Return:7879- Search command(s), with token omitted.80- Timeline table.81- 3-5 trend phases.82- Representative papers per phase.83- Emerging directions and weak signals.84- Next `search-papers` queries.