Agent skill

Patent Disclosure Skill

by trsoliu in trsoliu/mini-wiki

中国专利:从项目文档挖掘专利点并生成可交付技术交底书(查新、脱敏成文、自检与迭代);或将已有专利解读为通俗笔记与 Obsidian 知识图谱(叙事故事线、公开线索辅助)。| China patents: draft technical disclosures from project docs, or read existing patents into plain-language…

MITAuto-check: notesLegal & Compliance

Install Patent Disclosure Skill

skills CLI
$ npx skills add trsoliu/mini-wiki --skill patent-disclosure-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install trsoliu/mini-wiki patent-disclosure-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/trsoliu/mini-wiki.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/patent-disclosure-skill .claude/skills/patent-disclosure-skill && rm -rf skills-src

Use ~/.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/

Facts

Skill name
patent-disclosure-skill
GitHub stars
116
Token cost
~1.7k tokens
SKILL.md length
395 words
Files
115 (incl. references, assets)
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

中国专利:从项目文档挖掘专利点并生成可交付技术交底书(查新、脱敏成文、自检与迭代);或将已有专利解读为通俗笔记与 Obsidian 知识图谱(叙事故事线、公开线索辅助)。| China patents: draft technical disclosures from project docs, or read existing patents into plain-language…

  • Works in 7 steps: Read intake.md → Step 1 → Read project_scan.md → Step 2 → Read patent_points_analyzer.md → Step 3–4 → …
  • Tasks that involve Intellectual property
  • SKILL.md covers 环境与约定, 触发条件, 工具与数据来源 and Prompt 文件映射, plus 4 more sections
  • Calls pip

What it does

Patent Disclosure Skill is an agent skill from trsoliu/mini-wiki. 中国专利:从项目文档挖掘专利点并生成可交付技术交底书(查新、脱敏成文、自检与迭代);或将已有专利解读为通俗笔记与 Obsidian 知识图谱(叙事故事线、公开线索辅助)。| China patents: draft technical disclosures from project docs, or read existing patents into plain-language notes and an Obsidian knowledge graph.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 117 other files, including reference files and assets (for example `INSTALL.md`, `README.md` and `assets/obsidian/_专利解读索引.template.md`).

It sits in Legal & Compliance, covering Intellectual property and Plain language and style rules. It works with Obsidian, Microsoft Word, Mermaid and Microsoft PowerPoint. The repository describes itself as: Open Source Skills Wiki: AI-Powered skills Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. The licence is MIT.

When your agent uses it

  • Tasks that involve Intellectual property
  • Tasks that involve Plain language and style rules

Example prompts

  • “/patent-disclosure-skill”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Read, Write, Edit, Grep, Glob, WebSearch, Bash

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Read intake.md → Step 1
  2. Read project_scan.md → Step 2
  3. Read patent_points_analyzer.md → Step 3–4
  4. Read prior_art_search.md → Step 5
  5. Read disclosure_preview.md → Step 6(可跳过)
  6. Read disclosure_builder.md + template_reference.md → Step 7(文件名 §7.3 第 5 点;对话附 §7.6 权利要求偏向点,不入正文)
  7. Read disclosure_self_check.md → Step 8 内部自检后交付

What it can do on your machine

Read from SKILL.md and the folder at commit 5fae5f2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Grep
    • Glob
    • WebSearch
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Patent Disclosure Skill loads about 1.7k tokens when it runs, and up to ~5.5k if it reads all its reference files. Until then it costs about 64 tokens; SKILL.md has 395 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.5k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Edit, Grep, Glob, WebSearch, Bash

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from trsoliu/mini-wiki at commit 5fae5f2, republished under its MIT licence (© trsoliu). 395 words, ~1,711 tokens.

Download SKILL.mdSave it as .claude/skills/patent-disclosure-skill/SKILL.md (or your agent's skills folder). This skill also uses 114 other files; get the full folder from GitHub.
name
patent-disclosure-skill
description
中国专利:从项目文档挖掘专利点并生成可交付技术交底书(查新、脱敏成文、自检与迭代);或将已有专利解读为通俗笔记与 Obsidian 知识图谱(叙事故事线、公开线索辅助)。| China patents: draft technical disclosures from project docs, or read existing patents into plain-language notes and an Obsidian knowledge graph.
allowed-tools
Read, Write, Edit, Grep, Glob, WebSearch, Bash
version
2.0.0
user-invocable
true
argument-hint
[可选:项目路径 / 技术主题 / 专利号或 PDF 路径]

中国专利 · 交底书编写与通俗解读

本技能支持两种用法;分步指令在 prompts/,执行前须 Read 对应文件。

模式何时用主入口
A · 交底书编写从项目材料挖专利点 → 查新 → 成稿 .md/.docx → 迭代下文「交底书主流程」
B · 专利通俗解读已有公开号 / PDF / 全文,原文抽象难读,要通俗叙事 + 图谱下文「专利通俗解读」+ patent_plain_reader.md

提供专利号或专利全文/PDF且意图为「读懂」时 → 优先模式 B,不默认跑交底书 Step 1–8。

环境与约定

  • 语言:默认与用户语种一致;专利与法律术语用行业常用表述。
  • 交底书图示(Step 7):3.2/3.4 用 fenced mermaid;见工具表与 tools/README.md。
  • 解读 + Obsidian:强烈推荐配置库(PATENT_READER_OBSIDIAN_VAULT),以完整体验索引、Canvas 知识图谱、术语网、关系图配色与公开线索旁注;无库可降级 outputs/patent_reader/。入库时自动 bootstrap(CSS / Bases / 关系图),勿再引导用户手动装 CSS。用户侧 Obsidian 安装与可选社区插件见 docs/obsidian-setup-guide.md。

触发条件

  • 交底书:专利挖掘、专利点、技术交底书、交底书、查新、现有技术对比;/patent-disclosure-skill、/交底书 等。
  • 通俗解读:专利解读、读专利、看懂专利、反向专利、专利翻译成通俗;/patent-read、/读专利;或用户给出公开号 / 专利 PDF / 全文且目标为理解而非写交底书。
  • 交底书迭代(意图识别):在已有交底书上补材料、改章节、纠错等——无需固定「迭代」一词,也不必先问是否迭代。Read iteration_context.md,再 merger.md(扩合并)或 correction_handler.md(纠错);另存 {案件名}_{YYYYMMDDHHmmss}.md/.docx,不覆盖旧稿(除非用户明确要求)。禁止迭代意图成立时默认回到 Step 3–4 重挖专利点。对话中已有交底书路径/附件时优先按迭代处理。

工具与数据来源

按任务选用;工具名以当前 Agent 环境为准。扫描含 .docx/.pptx 时,Step 2 阅读前须先 docx_to_md.py / pptx_to_md.py(pip install -r requirements.txt)。

常见任务与建议方式
任务建议方式
加载分步指令Read → ${CLAUDE_SKILL_DIR}/prompts/*.md
读代码、设计文档、PDF、图片文件读取;大仓库先检索再精读
Word / PPT → Markdowndocx_to_md.py / pptx_to_md.py(见上)
联网查新(交底书 Step 5)Read prior_art_search.md。优先 cnipa_epub_search.py:先归纳 2~8 语义块,每次工具调用仅一词,自行按 pub_number 合并 EPUB_HITS_JSON;需 tools/requirements-cnipa.txt + Playwright Chromium。abstract 必用。异常或无果再 WebSearch
交底书定稿(.md + .docx)3.2/3.4 用 mermaid;mermaid_render.py → PNG 并默认出 docx。见 tools/README.md
交底书落盘建议 ./outputs/{案件标识}/;文件名 {案件名}_{YYYYMMDDHHmmss}(§7.3 第 5 点,含首次与迭代)
迭代对话留档案件目录追加 交底书修订对话记录.md(iteration_dialog_log.py)
专利通俗解读Read patent_plain_reader.md。先 check_obsidian_env.py(强烈推荐有库;未检测到则询问并用 --set;用户明确不要库才跳过)。仅公开号时用 fetch_patent_pdf.py(源表 references/patent_pdf_sources.yaml;禁止会话内现写下载脚本)→ extract → 叙事/权要可视化 → 公开线索由 Agent 读 URL 写 summary → write_patent_obsidian_note(入库自动 bootstrap;线索脚本抓取仅 --fetch-clues-fallback)。交付后可选社区插件引导;库内 ≥2 篇须反问关联,同意后 link_patent_notes.py

Prompt 文件映射

交底书编写
步骤文件用途
Step 1prompts/intake.md边界与输入
Step 2prompts/project_scan.md项目扫描;Office 须先转换
Step 3–4prompts/patent_points_analyzer.md专利点融合与选定
Step 5prompts/prior_art_search.md查新
Step 6prompts/disclosure_preview.md摘要预览
Step 7prompts/disclosure_builder.md + template_reference.md成文、脱敏、符号/公式体例、mermaid
Step 8prompts/disclosure_self_check.md内部自检(不入正文)
迭代iteration_context.md / merger.md / correction_handler.md扩合并 / 纠错另存
专利通俗解读
步骤文件用途
门禁check_obsidian_env.py(见 patent_plain_reader.md 第 0 步)探测/写入库路径;强烈推荐有库
仅公开号取 PDFtools/patent_reader/fetch_patent_pdf.py + references/patent_pdf_sources.yaml固化下载(第 1 步前);禁止会话内现写脚本
主流程prompts/patent_plain_reader.mdextract / 附图 / 权树校对 / 线索 / 写笔记 / 入库(须先 Read)
写笔记时prompts/obsidian_ofm_companion.md + references/patent_obsidian_format.md + assets/patent_note_template.mdCallout / 结构 / 模板
写笔记时(按需)references/ipc_application_hints.yamlIPC 应用场景坐标
自检prompts/patent_reader_self_check.md交付前内部自检(不入笔记)
交付时(对话)prompts/obsidian_plugin_guide.md可选社区插件引导(不入笔记)
用户文档docs/obsidian-setup-guide.md装 Obsidian / 社区插件(给人看,勿当主链全文 Read)
按需tools/patent_reader/README.md解读工具链说明

顺序摘要:门禁 →(仅公开号)fetch_patent_pdf → 主流程(extract / 附图 / 线索 / 入库)→ 写笔记时读 ofm/format/模板 → lint 后自检 → 已入库则交付引导;用户已给 PDF/全文则跳过下载;obsidian-setup-guide 与工具 README 仅按需查阅。


Show full SKILL.md (139 more words)Show less

模式 A · 交底书主流程

  1. Read intake.md → Step 1
  2. Read project_scan.md → Step 2
  3. Read patent_points_analyzer.md → Step 3–4
  4. Read prior_art_search.md → Step 5
  5. Read disclosure_preview.md → Step 6(可跳过)
  6. Read disclosure_builder.md + template_reference.md → Step 7(文件名 §7.3 第 5 点;对话附 §7.6 权利要求偏向点,不入正文)
  7. Read disclosure_self_check.md → Step 8 内部自检后交付

禁止:交底书正文出现「自检清单」章节。


模式 B · 专利通俗解读

启用:读懂已有专利(见触发条件),且非交底书迭代。

目标能力(交付物应体现):

  • 取证解读:权要树、术语、特征—说明书—附图对照
  • 叙述故事线:一句话 + 问题/思路/怎么做/效果/差别等连贯叙事
  • 知识图谱:*_图谱.canvas、术语双链、关系图配色;多篇可 _专利关联.canvas
  • 公开线索辅助:≤3 条公开材料,L1–L4 旁注与 clues/(推测语境,非权要/说明书证据)

步骤:

  1. Read patent_plain_reader.md → 先跑 check_obsidian_env.py(强烈推荐有库;无库则询问路径/--set,或确认仅 outputs)→ 仅公开号、无本地全文时跑 fetch_patent_pdf.py(源表 patent_pdf_sources.yaml;失败可 cnipa_epub_search 核验元数据,勿现写下载脚本)→ extract_patent_text(及附图)→ 校对 claim_tree / 写 claim_deltas → 叙事与可视化 → Agent 读线索 URL 写 summary → 写笔记 → lint → write_patent_obsidian_note(有库时入库并自动 bootstrap)
  2. Read obsidian_ofm_companion.md + patent_obsidian_format.md + 模板
  3. Read patent_reader_self_check.md → lint 通过后复核
  4. 已入库:对话末尾 Read obsidian_plugin_guide.md(仅可选社区插件;勿要求用户再装 CSS)
  5. 库内 ≥2 篇解读时须反问是否关联;同意后 link_patent_notes.py

与模式 A 互斥:解读不跑交底书 Step 1–8。若用户要「先解读再写交底书」,先完成模式 B 交付,再询问是否进入 intake。


迭代模式(交底书 · 摘要)

按自然语言意图启用(见触发条件),不为「是否迭代」打断用户。

  • 补材料 / 扩展 / §7.6 侧重点已声明:iteration_context.md → merger.md → 另存时间戳稿 + 追加修订对话记录 + 输出合并摘要
  • 纠错 / 与事实不符:iteration_context.md → correction_handler.md → 另存 + 记录 + 纠正摘要;定稿仍附 §7.6 引导

新稿定稿路径上仍内部执行 disclosure_self_check.md。


Agent 自用工作流检查清单

□ 已区分模式 A(交底书)/ B(解读)/ 交底书迭代,未混跑
□ 已按步骤 Read 对应 prompts;Step 2 若含 Office,已 docx_to_md / pptx_to_md 并读产出 `.md`
□ 「在已有交底书上改」类意图:已 Read iteration_context 并走 merger/correction;交付为新时间戳文件,未无故覆盖旧稿;已追加交底书修订对话记录.md 并输出留档摘要
□ 查新:优先 cnipa_epub_search(分次一词并合并 EPUB_HITS_JSON);abstract 必用;异常再 WebSearch;1.1 与区别论述已写
□ 除用户跳过外已做摘要预览;脱敏/mermaid/§7.7/3.4.1 与 .md+.docx 时间戳文件名符合要求;正文无技能仓库类脚注
□ 定稿对话含 §7.6 权利要求偏向点(不入正文、不捏造);自检仅后台,正文无自检清单
□ 【模式 B】已 check_obsidian_env;仅公开号已用 fetch_patent_pdf(未现写下载脚本);强烈推荐有库(无库已确认降级 outputs);叙事/线索/图谱要点已覆盖;入库自动 bootstrap,未误导用户手装 CSS;≥2 篇已反问关联并按需 link_patent_notes

© trsoliu, 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 114 other files (references, assets) in .agents/skills/patent-disclosure-skill of trsoliu/mini-wiki.

  • SKILL.md
  • .gitignore
  • INSTALL.md
  • LICENSE
  • README.md
  • assets/obsidian/_专利解读索引.template.md
  • assets/obsidian/glossary.base
  • assets/obsidian/graph_color_groups.json
  • assets/obsidian/patent-reader.css
  • assets/obsidian/patents.base
  • assets/patent_note_template.md
  • docs/obsidian-setup-guide.md
  • docs/thanks.jpg
  • docs/效果例-obs图谱.jpg
  • docs/效果例-初版生成.jpg
  • docs/效果例-解读.jpg
  • docs/效果例-迭代更新.jpg
  • examples
  • … and 97 more

Open the folder on GitHubat commit 5fae5f2

Compare with similar skills

Patent Disclosure Skill 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.

Patent Disclosure Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Patent Disclosure Skill this skilltrsoliu/mini-wiki116—~1.7kAutomated safety check: NotesMIT
Patent Disclosure Skillqzzqzzb/OpenClaudeScience106—~1.6kAutomated safety check: NotesMIT
Paper to Chinese Patent DrafterYuan1z0825/nature-skills47k1 repos~1.1kAutomated safety check: PassApache-2.0
Paper To Cn Patentsnipp-zha/Paper-to-patent-Skill1071 repos~959Automated safety check: PassNone
File Intelearlyaidopters/second-brain194—~481Automated safety check: PassNone
Contract Reviewzh-xx/legal-assistant-skills174—~1.6kAutomated safety check: PassApache-2.0

Similar skills

  • Patent Disclosure Skill

    qzzqzzb/OpenClaudeScience

    通用中国专利挖掘发现与交底书生成全流程:扫描项目文档挖掘专利点、讨论融合、基于脱敏模版生成技术交底书、联网查新、生成后自检含逻辑闭环与公式参数一致性。| Patent mining, disclosure drafting, prior-art search, and consistency self-check.

    106 GitHub stars~1.6k tokensUpdated 3 mo ago
    Legal & ComplianceAuto-check: notes
  • 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.

    47k GitHub starsUsed in 1 repo~1.1k tokens
    Legal & ComplianceAuto-check passed
  • 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.

    107 GitHub starsUsed in 1 repo~959 tokens
    Legal & ComplianceAuto-check passed
  • File Intel

    earlyaidopters/second-brain

    Run the Gemini file processor on any folder — extracts content from PDF, PPTX, XLSX, DOCX, CSV, JSON, and any text format, then generates Obsidian-ready summaries.

    194 GitHub stars~481 tokensUpdated 6 mo ago
    Documents & OfficeAuto-check passed
  • Contract Review

    zh-xx/legal-assistant-skills

    Contract review skill that adds comment-based issue annotations without changing original text.

    174 GitHub stars~1.6k tokensUpdated 5 mo ago
    Legal & ComplianceAuto-check passed
  • Doc Importer

    wpsnote/wpsnote-skills

    将本地文档批量导入到 WPS 笔记。支持扫描 Obsidian Vault、思源笔记、微信公众号存档、 下载目录或任意用户指定目录,自动识别 HTML、Markdown、PDF、DOCX、PPTX、XLSX 等格式, 转换为 WPS 笔记可读内容并保留图片和富文本格式。

    179 GitHub stars~2.7k tokensUpdated 4 mo ago
    Documents & OfficeAuto-check passed

More from trsoliu/mini-wiki

  • Mini Wiki

    trsoliu/mini-wiki

    Build and maintain a professional, source-traceable project knowledge network.

    116 GitHub stars~3.1k tokensUpdated 6 days ago
    Auto-check passed

Questions about Patent Disclosure Skill

What does Patent Disclosure Skill do?

中国专利:从项目文档挖掘专利点并生成可交付技术交底书(查新、脱敏成文、自检与迭代);或将已有专利解读为通俗笔记与 Obsidian 知识图谱(叙事故事线、公开线索辅助)。| China patents: draft technical disclosures from project docs, or read existing patents into plain-language…. Patent Disclosure Skill is an agent skill from trsoliu/mini-wiki. 中国专利:从项目文档挖掘专利点并生成可交付技术交底书(查新、脱敏成文、自检与迭代);或将已有专利解读为通俗笔记与 Obsidian 知识图谱(叙事故事线、公开线索辅助)。| China patents: draft technical disclosures from project docs, or read existing patents into plain-language notes and an Obsidian knowledge graph.

When should I use Patent Disclosure Skill?

Patent Disclosure Skill fits situations like: tasks that involve Intellectual property; tasks that involve Plain language and style rules.

How do I install Patent Disclosure Skill in Claude Code?

Run `npx skills add trsoliu/mini-wiki --skill patent-disclosure-skill -a claude-code`. Or copy the skill folder (.agents/skills/patent-disclosure-skill in trsoliu/mini-wiki) into .claude/skills/patent-disclosure-skill in your project. Claude Code loads it when a task matches its description.

How do I install Patent Disclosure Skill in Codex?

Run `npx skills add trsoliu/mini-wiki --skill patent-disclosure-skill -a codex`. Or copy the skill folder (.agents/skills/patent-disclosure-skill in trsoliu/mini-wiki) into .agents/skills/patent-disclosure-skill in your project. Codex loads it when a task matches its description.

Can I use Patent Disclosure Skill 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 trsoliu/mini-wiki --skill patent-disclosure-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/patent-disclosure-skill, .gemini/skills/patent-disclosure-skill, .github/skills/patent-disclosure-skill and .opencode/skills/patent-disclosure-skill in your project.

What does Patent Disclosure Skill need to run?

Going by SKILL.md and its folder, Patent Disclosure Skill needs the command-line tools its instructions call (pip). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Write, Edit, Grep, Glob, WebSearch, Bash.

Does Patent Disclosure Skill access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Patent Disclosure Skill safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Patent Disclosure Skill use?

Patent Disclosure Skill is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Patent Disclosure Skill use?

About 1.7k tokens (SKILL.md is roughly 6.8k 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 3.8k tokens, read only when the agent opens those files.

What are the alternatives to Patent Disclosure Skill?

Skills that share tags, products or a category with Patent Disclosure Skill: Patent Disclosure Skill (qzzqzzb/OpenClaudeScience, 106 stars), Paper to Chinese Patent Drafter (Yuan1z0825/nature-skills, 47k stars), Paper To Cn Patent (snipp-zha/Paper-to-patent-Skill, 107 stars) and File Intel (earlyaidopters/second-brain, 194 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Patent Disclosure Skill?

trsoliu (a GitHub user) maintains it in trsoliu/mini-wiki, which has 116 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 5, 2026.

Source: trsoliu/mini-wiki on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.