deepxiv-baseline-table
Build a markdown baseline table for a research topic using deepxiv search, brief, head, and experiment-section reads, extracting…
Look up Chinese national standards (GB, GB/T, GB/Z): code, title, status, dates, ICS class. Metadata only, no full text. Use when a task needs which Chinese standard applies or whether it is in force.
$ npx -y skills add deepxiv/deepxiv_sdk --skill deepxiv-fa-standards --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/deepxiv-fa-standardsContext preview
The summary Claude sees to decide when to auto-load this skill.
Look up Chinese national standards (GB, GB/T, GB/Z): code, title, status, dates, ICS class. Metadata only, no full text. Use when a task needs which Chinese standard applies or whether it is in force.
name: deepxiv-fa-standards description: Look up Chinese national standards (GB, GB/T, GB/Z): code, title, status, dates, ICS class. Metadata only, no full text. Use when a task needs which Chinese standard applies or whether it is in force.
Catalogue of 79,311 Chinese national standards (openstd: mandatory GB / recommended GB/T / guiding GB/Z). **Metadata only, no full text**: code, Chinese and English title, status, issue and effective dates, ICS class, tags.
Corpus: 79,787 documents, updated 2026-10.
pip install -U deepxiv-sdk # deepxiv registers a token on first use
With a registered key (https://data.rag.ac.cn/register), `search` and `read` are fair use: 60/min, 5 at once, 5,000/day; on the auto-registered token they spend the deepxiv daily limit at the credits listed below. `ask` draws on the daily ask allowance (resets 00:00 UTC; a site-wide daily total can run out early at peak times), or 3 lifetime trial asks on the auto-registered token. On 429, back off for `Retry-After` seconds. Data goes to stdout; cost, quota and sources go to stderr. Exit 0 ok, 1 API error, 2 usage error. The general CLI guide is the `deepxiv-cli` skill.
deepxiv fa search standards "锂离子电池安全" -F state=现行 -k 5 deepxiv fa read standards "GB/T 42729-2023" -l brief deepxiv fa ask "电动自行车用锂离子电池有哪些强制性国家标准?" -d standards
Free samples: ids `GB/T 42729-2023`; queries `锂离子电池 安全`.
deepxiv fa search standards "query" [-F FILTER]... [-k N] [--offset N] [--mode M] [--head] [--json]
Modes: hybrid, dense, bm25. Up to 100 hits. Cost 2 (with `--head`: 3). An empty query is rejected; use `"*"` to list by filters only. Filters combine with AND; an undeclared field exits 2.
| filter | type | `-F` syntax | meaning | |---|---|---|---| | `nature` | keyword | `k=v`, `k=a,b` | Nature: mandatory / recommended / guiding Values: `强制性`, `推荐性`, `指导性技术文件`. | | `state` | keyword | `k=v`, `k=a,b` | Status: in force / coming into force / withdrawn / suspended Values: `现行`, `即将实施`, `废止`, `暂不实施`. | | `std_prefix` | keyword | `k=v`, `k=a,b` | Code prefix Values: `GB`, `GB/T`, `GB/Z`. | | `ics` | keyword | `k=v`, `k=a,b` | ICS top-level class (see facets) | | `is_mandatory` | bool | `k=v` | Mandatory | | `issue_year` | integer | `k=v`, `k>=n`, `k=n..m` | Issue year, range | | `act_year` | integer | `k=v`, `k>=n`, `k=n..m` | Effective year, range |
Advanced filters (see `deepxiv fa spec standards`): `tags`.
deepxiv fa read standards ID [ID...] [-l brief|detail|full] [-e EXTRA] [-p k=v]... [-f json|md|html]
| level | credits | returns | |---|---|---| | `brief` | 1 | Card: the fields needed to triage, same as in search hits | | `detail` (default) | 2 | Every structured field (rule-derived plus model-generated; model fields are listed in _enrich.fields) | | `full` | 5 | Full text (not available yet: the standard text is not in this corpus — see openstd.samr.gov.cn) |
At `-l full`, `-p section=NAME` reads one section and `-p characters=N` the first N characters.
`deepxiv fa facets standards FIELD` lists the legal values and counts, free. Use it instead of guessing a spelling. Fields: `nature`, `state`, `std_prefix`, `ics`.
deepxiv fa ask "question" -d standards [-e low|medium|high] [-p k=v]... [--no-stream] [--json]
Agentic Q&A, with one boundary up front: this domain holds catalogue metadata only, no clause text. It can answer which standards exist, how they are classified, whether they are in force and when they take effect; it cannot answer what a clause says — it will say so and point at openstd. Citations are [standards:<std_code> <title>]
Always pass `-d standards`: automatic domain picking is still early.
Cite records as `[GB/T 42729-2023]`. Say plainly when the corpus has nothing.
---
Generated by `scripts/gen_fa_skills.py` from `deepxiv fa spec standards --json` on 2026-10-19. Field names and prices can change; `deepxiv fa spec standards` is the live source.
Talk to research papers like talking to authors - Python package with AI agent for arXiv papers
Build a markdown baseline table for a research topic using deepxiv search, brief, head, and experiment-section reads, extracting…
Use the deepxiv CLI to search and read academic papers (arXiv, PMC, bioRxiv, medRxiv) section by section, get cited answers from…
Find which academicians and society fellows (CAS, CAE, NAS, NAE, Royal Society, ACM, IEEE, AAAI …) cited a paper and what they…
Search Chinese and US court judgments (17M+ Chinese, 3.4M US) and read their extracted fields: claims, facts, reasoning, outcome,…
Search ~390k public vulnerabilities (NVD) with CISA KEV exploited-in-the-wild flags and EPSS exploitation probability. Use when a…
Search ~257k US drug labels (openFDA SPL): indications, contraindications, interactions, boxed warnings, pharmacologic class. Use…