Paper to Chinese Patent Drafter
Yuan1z0825/nature-skills
Drafts Chinese invention patent applications and technical disclosures from research papers or inventor materials, tying each claim feature to source evidence.
通过 Analytics 检索式（如 TACD： 关键词）在智慧芽专利数据库中检索专利列表，返回专利ID、公开号及命中总数。当用户提到专利检索式检索、专利表达式搜索、Analytics检索式、TACD检索、专利关键词检索、检索式查专利、专利语义检索、patent expression search, patent query syntax, Analytics query, TACD…
Install Linkfox Zhihuiya Retrieval Patent Search
$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-retrieval-patent-search -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install linkfox-ai/linkfox-skills linkfox-zhihuiya-retrieval-patent-search --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/linkfox-zhihuiya-retrieval-patent-search .claude/skills/linkfox-zhihuiya-retrieval-patent-search && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "linkfox-zhihuiya-retrieval-patent-search" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-zhihuiya-retrieval-patent-search into .claude/skills/linkfox-zhihuiya-retrieval-patent-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-zhihuiya-retrieval-patent-search", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-zhihuiya-retrieval-patent-searchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-retrieval-patent-search -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install linkfox-ai/linkfox-skills linkfox-zhihuiya-retrieval-patent-search --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/linkfox-zhihuiya-retrieval-patent-search .agents/skills/linkfox-zhihuiya-retrieval-patent-search && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "linkfox-zhihuiya-retrieval-patent-search" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-zhihuiya-retrieval-patent-search into .agents/skills/linkfox-zhihuiya-retrieval-patent-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-zhihuiya-retrieval-patent-search", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-retrieval-patent-search -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install linkfox-ai/linkfox-skills linkfox-zhihuiya-retrieval-patent-search --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/linkfox-zhihuiya-retrieval-patent-search .cursor/skills/linkfox-zhihuiya-retrieval-patent-search && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "linkfox-zhihuiya-retrieval-patent-search" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-zhihuiya-retrieval-patent-search into .cursor/skills/linkfox-zhihuiya-retrieval-patent-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-zhihuiya-retrieval-patent-search", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/linkfox-ai/linkfox-skills.git --path skills/linkfox-zhihuiya-retrieval-patent-search--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-retrieval-patent-search -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install linkfox-ai/linkfox-skills linkfox-zhihuiya-retrieval-patent-search --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/linkfox-zhihuiya-retrieval-patent-search .gemini/skills/linkfox-zhihuiya-retrieval-patent-search && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "linkfox-zhihuiya-retrieval-patent-search" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-zhihuiya-retrieval-patent-search into .gemini/skills/linkfox-zhihuiya-retrieval-patent-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-zhihuiya-retrieval-patent-search", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install linkfox-ai/linkfox-skills linkfox-zhihuiya-retrieval-patent-searchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-retrieval-patent-search -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/linkfox-zhihuiya-retrieval-patent-search .github/skills/linkfox-zhihuiya-retrieval-patent-search && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "linkfox-zhihuiya-retrieval-patent-search" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-zhihuiya-retrieval-patent-search into .github/skills/linkfox-zhihuiya-retrieval-patent-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-zhihuiya-retrieval-patent-search", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-retrieval-patent-search -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install linkfox-ai/linkfox-skills linkfox-zhihuiya-retrieval-patent-search --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/linkfox-zhihuiya-retrieval-patent-search .opencode/skills/linkfox-zhihuiya-retrieval-patent-search && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "linkfox-zhihuiya-retrieval-patent-search" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-zhihuiya-retrieval-patent-search into .opencode/skills/linkfox-zhihuiya-retrieval-patent-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-zhihuiya-retrieval-patent-search", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
linkfox-zhihuiya-retrieval-patent-search- GitHub stars
- 107
- Token cost
- ~2.3k tokens
- SKILL.md length
- 949 words
- Files
- 5 (incl. scripts, references)
- Skills in repo
- 177
- Repo updated
- First seen
- Licence
- MIT
At a glance
通过 Analytics 检索式（如 TACD： 关键词）在智慧芽专利数据库中检索专利列表，返回专利ID、公开号及命中总数。当用户提到专利检索式检索、专利表达式搜索、Analytics检索式、TACD检索、专利关键词检索、检索式查专利、专利语义检索、patent expression search, patent query syntax, Analytics query, TACD…
- Works in 6 steps: Present results as a table: show pn,… → Show totals: always state… → Default sort: if the user does not… → …
- Tasks that involve Intellectual property
- SKILL.md covers Core Concepts, Data Fields, 调用方式 and 解决认证和算力问题, plus 6 more sections
- Runs Python scripts from its folder; calls python; needs LINKFOX_AGENT_API_KEY and LINKFOXAGENT_API_KEY
What it does
Linkfox Zhihuiya Retrieval Patent Search is an agent skill from linkfox-ai/linkfox-skills. 通过 Analytics 检索式（如 TACD： 关键词）在智慧芽专利数据库中检索专利列表，返回专利ID、公开号及命中总数。当用户提到专利检索式检索、专利表达式搜索、Analytics检索式、TACD检索、专利关键词检索、检索式查专利、专利语义检索、patent expression search, patent query syntax, Analytics query, TACD search, PatSnap, 智慧芽专利检索时触发此技能。即使用户未明确提及"检索式"或"智慧芽"，只要用户希望用检索式/表达式语法在专利库中检索专利列表，也应触发此技能。
Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/api.md`, `references/onboarding.md` and `scripts/onboarding.py`).
It sits in Legal & Compliance, covering Intellectual property. The licence is MIT.
When your agent uses it
- Tasks that involve Intellectual property
Example prompts
- “/linkfox-zhihuiya-retrieval-patent-search”
Requirements
- Python 3
- A credential in LINKFOX_AGENT_API_KEY
- A credential in LINKFOXAGENT_API_KEY
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Present results as a table: show pn, title, apdt/pbdt (format as dates), inventor, currentAssignee, authority per item.
- Show totals: always state allRecordsCount (total hits) and the current page range (offset–offset+limit).
- Default sort: if the user does not specify a sort, actively inject {"field": "SCORE", "order": "DESC"} so results are relevance-ordered…
- Large result sets: present a summary table first, note the total, and offer to expand specific patents.
- Expand via sibling skills: to get full metadata for a patent, direct the user to linkfox-zhihuiya-bibliography /…
- No fabrication: only display fields actually present in the response; never invent titles, dates, or assignees not returned.
What it can do on your machine
Read from SKILL.md and the folder at commit 38fef04. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
skill.linkfox.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
LINKFOX_AGENT_API_KEYLINKFOXAGENT_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Linkfox Zhihuiya Retrieval Patent Search loads about 2.3k tokens when it runs, and up to ~4.5k if it reads all its reference files. Until then it costs about 81 tokens; SKILL.md has 949 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from linkfox-ai/linkfox-skills at commit 38fef04, republished under its MIT licence (© linkfox-ai). 949 words, ~2,302 tokens.
Download SKILL.mdSave it as
.claude/skills/linkfox-zhihuiya-retrieval-patent-search/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- linkfox-zhihuiya-retrieval-patent-search
- description
- 通过 Analytics 检索式（如 TACD： 关键词）在智慧芽专利数据库中检索专利列表，返回专利ID、公开号及命中总数。当用户提到专利检索式检索、专利表达式搜索、Analytics检索式、TACD检索、专利关键词检索、检索式查专利、专利语义检索、patent expression search, patent query syntax, Analytics query, TACD search, PatSnap, 智慧芽专利检索时触发此技能。即使用户未明确提及"检索式"或"智慧芽"，只要用户希望用检索式/表达式语法在专利库中检索专利列表，也应触发此技能。
Zhihuiya Patent Expression Search
This skill searches the Zhihuiya (PatSnap) patent database using an Analytics query expression (e.g. TACD: virtual reality), returning a list of matching patents with their patent IDs and publication numbers, plus the total hit count.
Core Concepts
Expression-based patent search uses Zhihuiya's Analytics query syntax to retrieve patents matching a field-scoped boolean expression. Unlike image-based search, this is a text query against the full patent corpus.
Query expression (queryText) holds an Analytics expression. Common field-scoped syntax:
| Syntax | Scope |
|---|---|
TACD: <term> | Title + Abstract + Claims + Description |
TAC: <term> | Title + Abstract + Claims |
TA: <term> | Title + Abstract |
AND / OR / NOT | Boolean operators (combine terms/fields) |
This skill returns a list of patents (
patentId+pn). To retrieve detailed bibliographic data, full text, legal status, family, or images for a specific patent, feed the returnedpatentId/pninto the correspondinglinkfox-zhihuiya-bibliography/linkfox-zhihuiya-simple-bibliography/linkfox-zhihuiya-legal-status/linkfox-zhihuiya-patent-familyskills.
Data Fields
Each data[] item (one matching patent):
| Field | Description |
|---|---|
| patentId | Zhihuiya internal patent ID |
| pn | Publication (announcement) number |
| title | Patent title |
| apdt | Application date (integer, YYYYMMDD) |
| pbdt | Publication date (integer, YYYYMMDD) |
| apno | Application number |
| authority | Patent office / authority (e.g. US) |
| inventor | Inventor(s), pipe-separated |
| originalAssignee | Original applicant(s), pipe-separated |
| currentAssignee | Current assignee(s), pipe-separated |
Top-level fields:
| Field | Description |
|---|---|
| data | 专利列表（每项含上表 10 个字段） |
| total | Number of records returned in this response |
| allRecordsCount | Total hits matching the query expression |
| costToken | Token cost for this query |
| columns | Render metadata (display hints, not data records) |
| type | Render style (e.g. tableListWorkbenches) |
| errcode | 200 on success |
| errmsg | ok on success |
The top-level
columnsarray is render metadata and may be longer than the realdatalist — do not treat it as data.
调用方式
- API 端点：
POST /zhihuiya/querySearchPatent（完整参数/响应/错误码见references/api.md） - Python 脚本：
python scripts/zhihuiya_query_search_patent.py '<JSON 参数>' [--inline] - 成本约束：本工具会消耗算力；同一会话同一参数组合默认只调用一次，脚本带 24h 本地缓存。失败/空结果不得自动换关键词、翻页或改检索式连续试探；需要继续检索或翻页时先向用户说明会产生额外消耗。
输出策略（脚本默认行为）：
- 始终将完整响应写入
<cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-zhihuiya-retrieval-patent-search-<timestamp>.json（<cwd>为脚本执行时的工作目录，在 Claude Code 里即当前项目目录；<session>取自环境变量SESSION_ID，按用户任务自动聚合；禁止写入 /tmp，当前目录不可写则报错） - 响应体 ≤ 8 KB：落盘后把完整 JSON 打印到 stdout
- 响应体 > 8 KB：落盘后 stdout 只输出摘要（顶层字段、常见计数如
total/costToken、最大列表字段的长度 + 前 3 条样本） - 加
--inline强制全量打印到 stdout（同样落盘）
读数据建议：先看摘要判断是否足够；需要具体字段时优先用 jq或ConvertFrom-Json 从保存的 json 文件按需抽取，避免整份 JSON 进入上下文。
解决认证和算力问题
发生以下异常情况时，采用 references/onboarding.md 引导解决问题：
异常情况
- 未配置API Key：环境变量未配置
LINKFOX_AGENT_API_KEY，也未配置LINKFOXAGENT_API_KEY。 - 响应401或402状态码
- 响应提示算力或权限不足：消息含"算力余额不足/计费不足/余额不足/quota exceeded/insufficient balance/No permission/API package quota/套餐到期/需充值/请充值"，或类似含义的内容。
Parameter Guide
| Parameter | Required | Default | Description |
|---|---|---|---|
| queryText | Yes | - | Analytics 检索式，最大 12000 字符 |
| limit | No | 10 | 返回专利个数，1–1000 |
| offset | No | 0 | 偏移量，0–19999；limit + offset ≤ 20000 |
| sort | No | - | 排序数组，元素 {field, order} |
| stemming | No | 0 | 截词检索：1 开启 / 0 关闭，默认关闭 |
| collapseType | No | ALL | 去重方式：ALL / APNO / DOCDB / INPADOC / EXTEND |
| collapseBy | No | - | 去重排序字段：APD / PBD / AUTHORITY / SCORE |
| collapseOrder | No | - | 去重排序顺序：OLDEST / LATEST |
| collapseOrderAuthority | No | - | 受理局优先级数组（仅 collapseBy=AUTHORITY 时有效），按输入顺序保留对应专利 |
Sort object
field | Meaning |
|---|---|
| PBDT_YEARMONTHDAY | Publication date |
| APD_YEARMONTHDAY | Application date |
| ISD | Issue / grant date |
| SCORE | Query relevance |
order: DESC or ASC. Example: [{"field":"SCORE","order":"DESC"}].
Collapse (deduplication)
collapseType | Description |
|---|---|
| ALL | No dedup |
| APNO | By application number |
| DOCDB | By simple family |
| INPADOC | By INPADOC family |
| EXTEND | By PatSnap extended family |
collapseBy selects which representative record to keep (APD/PBD/AUTHORITY/SCORE); collapseOrder picks OLDEST or LATEST.
Usage Examples
1. Basic expression search
检索 TACD: virtual reality 的专利，返回 10 条Action: {"queryText": "TACD: virtual reality", "limit": 10}
2. Sort by relevance
用检索式 TACD: drone AND camera 查专利，按相关性排序Action: {"queryText": "TACD: drone AND camera", "sort": [{"field": "SCORE", "order": "DESC"}]}
3. Paginate
翻到第 2 页，每页 10 条Action: {"queryText": "TACD: virtual reality", "offset": 10, "limit": 10}
4. Dedup by DOCDB family
检索 TACD: virtual reality，按简单同族去重，保留最新Action: {"queryText": "TACD: virtual reality", "collapseType": "DOCDB", "collapseBy": "APD", "collapseOrder": "LATEST"}
Display Rules
- Present results as a table: show
pn,title,apdt/pbdt(format as dates),inventor,currentAssignee,authorityper item. - Show totals: always state
allRecordsCount(total hits) and the current page range (offset–offset+limit). - Default sort: if the user does not specify a sort, actively inject
{"field": "SCORE", "order": "DESC"}so results are relevance-ordered; respect any sort the user explicitly requests. - Large result sets: present a summary table first, note the total, and offer to expand specific patents.
- Expand via sibling skills: to get full metadata for a patent, direct the user to
linkfox-zhihuiya-bibliography/linkfox-zhihuiya-simple-bibliography; do not re-query this search skill for details. - No fabrication: only display fields actually present in the response; never invent titles, dates, or assignees not returned.
Show full SKILL.md (321 more words)Show less
Important Limitations
queryTextis required and must be a valid Analytics expression. Missing it returnserrcode 400.- Paging ceiling:
limit + offsetmust be ≤ 20000;limitmax 1000;offsetmax 19999. - List-only output: this skill returns
patentId+pn(and basic fields). Full bibliographic/full-text/legal data must be fetched via dedicatedlinkfox-zhihuiya-*skills. - No auto-retry on empty/error: if the query returns no hits or an error, do not automatically swap keywords or rewrite the expression; confirm with the user first (each call costs credits).
- Permission/quota: a
501 "No permission or API package quota"response means the current key lacks the query-search permission/quota. This is a permission/package issue (not merely low balance) and cannot be resolved by recharging alone — do not retry; surface it to the user to open/enable the query-search API package.
User Expression & Scenario Quick Reference
Applicable — Find patents by query expression:
| User Says | Scenario |
|---|---|
| "检索 TACD: virtual reality 的专利" | Basic expression search |
| "用检索式查虚拟现实相关专利" | Expression search |
| "检索式：TAC AND camera" | Boolean expression |
| "按公开日排序检索" | Sorted search |
| "按简单同族去重" | Deduplicated search |
| "翻到第 2 页" | Pagination |
Not applicable — Needs beyond expression search:
- Bibliographic detail of a known patent ID/number (use
linkfox-zhihuiya-bibliography) - Image-based patent search (use
linkfox-zhihuiya-patent-image-search) - Legal status / family / full-text / PDF (use dedicated
linkfox-zhihuiya-*skills)
Boundary judgment: When the user already has a patent ID or publication number and wants its metadata → use the bibliography skill. When the user wants to discover patents matching a query expression → this skill.
算力消耗规则
按动态规则计费：消耗算力 = 3 × 返回data条数。每条为 1 条检索式检索专利结果
重要：本技能的服务按倍数动态计算，返回条数越多消耗越大，必须提醒用户，由用户决定是否继续。优先用较小的
limit验证检索式命中，确认后再决定是否扩大范围或翻页。
Feedback:
Auto-detect and report feedback via the Feedback API when any of the following apply:
- The functionality or purpose described in this skill does not match actual behavior
- The skill's results do not match the user's intent
- The user expresses dissatisfaction or praise about this skill
- Anything you believe could be improved
Call the feedback API as specified in references/api.md. Do not interrupt the user's flow.
For more high-quality, professional cross-border e-commerce skills, visit LinkFox Skills.
© linkfox-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (scripts, references) in skills/linkfox-zhihuiya-retrieval-patent-search of linkfox-ai/linkfox-skills.
- SKILL.md
- references/api.md
- references/onboarding.md
- scripts/onboarding.py
- scripts/zhihuiya_query_search_patent.py
Open the folder on GitHubat commit 38fef04
Compare with similar skills
Linkfox Zhihuiya Retrieval Patent Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Linkfox Zhihuiya Retrieval Patent Search this skilllinkfox-ai/linkfox-skills | 107 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Paper to Chinese Patent DrafterYuan1z0825/nature-skills | 47k | 1 repos | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Paper To Cn Patentsnipp-zha/Paper-to-patent-Skill | 107 | 1 repos | ~959 | Automated safety check: Pass | None | |
| Patent Examinegfodor/legal-skills | 393 | — | ~4.8k | Automated safety check: Pass | GPL-3.0 | |
| Patent Auditgfodor/legal-skills | 393 | — | ~2.9k | Automated safety check: Pass | GPL-3.0 | |
| Replica BrandJakeschincariol/replica-skill | 1.4k | — | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
Paper To Cn Patent
snipp-zha/Paper-to-patent-Skill
Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts.
Patent Examine
gfodor/legal-skills
Iteratively examine and revise a draft U.S. An agent skill from gfodor/legal-skills.
Patent Audit
gfodor/legal-skills
Audit a draft U.S. An agent skill from gfodor/legal-skills.
Replica Brand
Jakeschincariol/replica-skill
Names and rebrands an app clone so it is the user's own: name candidates with the trademark, domain, store and handle checks to run, a new palette checked for contrast, a logo brief, a voice guide…
Patent Workaround
gfodor/legal-skills
Adversarially pressure-test a draft or pending U.S. An agent skill from gfodor/legal-skills.
More from linkfox-ai/linkfox-skills
All 177 skills in this repoLinkfox 1688 Search By Image
linkfox-ai/linkfox-skills
1688平台以图搜图，通过商品图片精准检索外观相似或同款的1688货源，返回标题、价格、起批量、月销量、复购率、交易评分等核心数据。当用户提到1688以图搜图、1688找货源、以图找同款、跨境找工厂、1688识图、图片找货源、找相似货源、image search 1688、find supplier by…
Linkfox Aba Intelligent Query
linkfox-ai/linkfox-skills
亚马逊ABA（品牌分析）搜索词数据的查询与分析，涵盖15个站点近3年的周维度数据。当用户提到ABA数据、亚马逊搜索词分析、关键词挖掘、搜索排名趋势、市场机会分析、季节性关键词、高点击低转化分析、蓝海词发现、竞品关键词分析、ABA data, search term report, keyword mining, search ranking trends, blue ocean…
Linkfox Amazon Alexa Search
linkfox-ai/linkfox-skills
通过亚马逊前台的 Alexa 购物助手发起自然语言问答，获取与问题相关的导购回答、推荐商品分组、ASIN 列表，以及可继续追问的问题。每次调用仅支持 1 条 prompt，如需追问须由 agent 总结上下文后拼接新问题发起新请求。可用 url 补充亚马逊页面上下文。当用户提到亚马逊 Alexa、Alexa 购物助手、亚马逊智能助手、AI…
Linkfox Amazon Opportunity Search By Metrics
linkfox-ai/linkfox-skills
亚马逊反向选品：基于历史商业洞察报告沉淀的指标数据池，按 30+ 项商业维度（市场规模与增长、价格区间与档位份额、竞争密度与头部集中度、人群画像如年龄/性别/收入、评论卖点与痛点等）反向筛选亚马逊赛道与关键词。当用户提到反向选品、指标筛选、细分市场反查、蓝海赛道挖掘、低竞争赛道、新人友好赛道、品牌分散市场、痛点切入、卖点反查、定价档位机会、人群画像选品、Amazon niche reverse…
Linkfox Amazon Product Detail
linkfox-ai/linkfox-skills
通过ASIN获取亚马逊商品详细信息，包括标题、图片、五点描述、规格参数、A+页面、价格、评分评论、变体等；可在取得原始HTML时尝试提取Item Highlights（商品亮点）。当用户提到亚马逊商品详情、ASIN查询、商品页面数据、Listing分析、五点描述提取、Item…
Linkfox Amazon Reviews List
linkfox-ai/linkfox-skills
按ASIN获取并分析亚马逊商品评论，支持15个站点(含美国站)，按星级筛选评论。当用户提到亚马逊评论、美国站评论、商品评价、买家投诉、差评、好评、星级评分、评论分析、评论情感、产品改良建议、Vine评论、已验证购买评论、竞品评论研究、Amazon reviews, US reviews, Amazon.com reviews, product feedback, negative review…
Related
Categories
Questions about Linkfox Zhihuiya Retrieval Patent Search
What does Linkfox Zhihuiya Retrieval Patent Search do?
通过 Analytics 检索式（如 TACD： 关键词）在智慧芽专利数据库中检索专利列表，返回专利ID、公开号及命中总数。当用户提到专利检索式检索、专利表达式搜索、Analytics检索式、TACD检索、专利关键词检索、检索式查专利、专利语义检索、patent expression search, patent query syntax, Analytics query, TACD…. Linkfox Zhihuiya Retrieval Patent Search is an agent skill from linkfox-ai/linkfox-skills.
When should I use Linkfox Zhihuiya Retrieval Patent Search?
Linkfox Zhihuiya Retrieval Patent Search fits situations like: tasks that involve Intellectual property.
How do I install Linkfox Zhihuiya Retrieval Patent Search in Claude Code?
Run `npx skills add linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-retrieval-patent-search -a claude-code`. Or copy the skill folder (skills/linkfox-zhihuiya-retrieval-patent-search in linkfox-ai/linkfox-skills) into .claude/skills/linkfox-zhihuiya-retrieval-patent-search in your project. Claude Code loads it when a task matches its description.
How do I install Linkfox Zhihuiya Retrieval Patent Search in Codex?
Run `npx skills add linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-retrieval-patent-search -a codex`. Or copy the skill folder (skills/linkfox-zhihuiya-retrieval-patent-search in linkfox-ai/linkfox-skills) into .agents/skills/linkfox-zhihuiya-retrieval-patent-search in your project. Codex loads it when a task matches its description.
Can I use Linkfox Zhihuiya Retrieval Patent Search in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add linkfox-ai/linkfox-skills --skill linkfox-zhihuiya-retrieval-patent-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/linkfox-zhihuiya-retrieval-patent-search, .gemini/skills/linkfox-zhihuiya-retrieval-patent-search, .github/skills/linkfox-zhihuiya-retrieval-patent-search and .opencode/skills/linkfox-zhihuiya-retrieval-patent-search in your project.
What does Linkfox Zhihuiya Retrieval Patent Search need to run?
Going by SKILL.md and its folder, Linkfox Zhihuiya Retrieval Patent Search needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named LINKFOX_AGENT_API_KEY and LINKFOXAGENT_API_KEY. Our summary lists: Python 3; A credential in LINKFOX_AGENT_API_KEY; A credential in LINKFOXAGENT_API_KEY.
Does Linkfox Zhihuiya Retrieval Patent Search access the network?
SKILL.md names 1 domain. As links in the text: skill.linkfox.com. This is read from the text; nothing was executed.
Is Linkfox Zhihuiya Retrieval Patent Search safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Linkfox Zhihuiya Retrieval Patent Search use?
Linkfox Zhihuiya Retrieval Patent Search is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Linkfox Zhihuiya Retrieval Patent Search use?
About 2.3k tokens (SKILL.md is roughly 9.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.2k tokens, read only when the agent opens those files.
What are the alternatives to Linkfox Zhihuiya Retrieval Patent Search?
Skills that share tags, products or a category with Linkfox Zhihuiya Retrieval Patent Search: Paper to Chinese Patent Drafter (Yuan1z0825/nature-skills, 47k stars), Paper To Cn Patent (snipp-zha/Paper-to-patent-Skill, 107 stars), Patent Examine (gfodor/legal-skills, 393 stars) and Patent Audit (gfodor/legal-skills, 393 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Linkfox Zhihuiya Retrieval Patent Search?
linkfox-ai (a GitHub user) maintains it in linkfox-ai/linkfox-skills, which has 107 GitHub stars. The repository holds 177 skills in this directory. The repository was last updated on September 14, 2026.
Source: linkfox-ai/linkfox-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.