中国专利.skill is a Chinese-language agent skill for finding patentable ideas, writing patent disclosure documents, explaining published patents, tracking examination policies, and helping prepare examination responses. It is for developers and researchers working with Chinese invention, utility-model, and design patents, with workflows that can store related research in Obsidian.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add handsomestWei/patent-disclosure-skill --skill patent-docketgit clone --depth 1 https://github.com/handsomestWei/patent-disclosure-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/handsomestwei/patent-disclosure-skill/patent-docket)<a href="https://agentmods.dev/skills/handsomestwei/patent-disclosure-skill/patent-docket"><img src="https://agentmods.dev/badge/skills/handsomestwei/patent-disclosure-skill/patent-docket/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/handsomestwei/patent-disclosure-skill/patent-docket"><img src="https://agentmods.dev/badge/skills/handsomestwei/patent-disclosure-skill/patent-docket.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00093 | $0.01056 |
| Opus 5.5 | $0.00037 | $0.00422 |
| Sonnet 5.5 | $0.00019 | $0.00211 |
| Haiku 4.5 | $0.00009 | $0.00106 |
Grade A, and why
patent-docket scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 26d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
案卷会稿
用途
单 agent 协调者：立案、分诊、派工、记轮次。按发明人/工程师给的材料一趟串起交底书和申请文件。本包只调度与记案卷，不写交底正文、不出四件套。
何时用
须用户点名（交底申请一起做、从零出交底和申请、一条龙、帮写交底再出申请、按清单改、会稿、案卷、/patent-docket）。只写交底，或已有交底只出四件套时，不进案卷。
输入
发明人/工程师材料；已有则读磁盘上的交底 md、申请 md、问题清单。状态以 outputs/docket/{case_id}/docket.yaml 为准。缺技术事实就问人，不编、不以聊天记忆当事实。
步骤
先 Read prompts/guardrails.md，再 Read prompts/intake.md。 派工时 Read 对方 SKILL.md 并按该包执行。对方包自己跑自己的 tools/。
每次进入都走：
prompts/guardrails.mdprompts/intake.md（判定from_zero/from_disclosure/from_application/resume）- 按 intake 结果只加载下列之一，不要一次读完所有 prompt：
- 新开或从零 →
prompts/bootstrap.md - 已有
docket.yaml→prompts/resume.md
- 新开或从零 →
- 之后按
docket.yaml的phase只读对应文件。阶段表在references/phases.yaml。
phase |
再读 |
|---|---|
bootstrap_disclosure / wait_disclosure / dispatch_disclosure |
prompts/dispatch_disclosure.md |
bootstrap_application / wait_application / dispatch_application |
prompts/dispatch_application.md |
triage |
prompts/triage.md → references/issue_taxonomy.md |
ask_human |
prompts/ask_human.md |
round_close |
prompts/round_close.md |
terminal_* |
prompts/round_close.md（只做收口陈述 + ## 交付后请确认，不再派工） |
阶段合法跳转：references/phases.yaml。机器校验：tools/validate_docket.py。tracker 落盘：tools/emit_tracker.py。交接只传路径：references/handoff_contract.md。
轮次上限 config.yaml 的 max_rounds（默认 3），细则 references/max_rounds.md。从零：首套交底 + 首套申请记为第 1 轮。之后每「分诊 → 派工 → 再出申请并核清单」加 1 轮。第 3 轮结束后必须停。
python skills/patent-docket/tools/init_docket.py --case-id 案件slug --mode from_zero
python skills/patent-docket/tools/validate_docket.py --yaml outputs/docket/案件slug/docket.yaml
python skills/patent-docket/tools/emit_tracker.py --yaml outputs/docket/案件slug/docket.yaml
机读前缀：DOCKET_DIR: / DOCKET_YAML: / DOCKET_OK: / DOCKET_ERROR:。
护栏
- 细则
prompts/guardrails.md。本包只改outputs/docket/。 - 禁止为销问题清单条目而编造结构、参数、步骤、查新命中。
产出物
outputs/docket/{case_id}/：docket.yaml、TRACKER.md（只由 emit_tracker.py 生成）、可选 ROUND-{n}.md。交底正文与四件套分别在交底包、申请包目录。收口对话末块标题 交付后请确认。
What ships with it
31 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/tracker_readme.md 312 B
- config.yaml 144 B
- examples/README.md 194 B
- prompts/ask_human.md 1.1 KB
- prompts/bootstrap.md 1.4 KB
- prompts/dispatch_application.md 1.4 KB
- prompts/dispatch_disclosure.md 1.4 KB
- prompts/emit_tracker.md 502 B
- prompts/guardrails.md 1.3 KB
- prompts/intake.md 2.3 KB
- prompts/resume.md 985 B
- prompts/round_close.md 1.9 KB
- prompts/triage.md 1.4 KB
- README.md 1.4 KB
- references/dispositions.yaml 958 B
- references/docket.schema.yaml 692 B
- references/handoff_contract.md 1.1 KB
- references/issue_taxonomy.md 2.5 KB
- references/max_rounds.md 1.3 KB
- references/phase_machine.md 877 B
- references/phases.yaml 1.9 KB
- tests/__init__.py 24 B runs code
- tests/test_docket.py 6.7 KB runs code
- tools/docket_config.py 990 B runs code
- tools/docket_paths.py 1.4 KB runs code
- tools/docket_spec.py 1.8 KB runs code
- tools/emit_tracker.py 5.2 KB runs code
- tools/init_docket.py 4.4 KB runs code
- tools/README.md 381 B
- tools/stdio_utf8.py 1.4 KB runs code
- tools/validate_docket.py 5.9 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 26d ago Changed · +12 lines f3e981e00cad
- 1mo ago Changed 722ef51d36cc
- 1mo ago First seen · 51 lines · 93 tokens per session scan A 48b8a550a89e
patent-docket is a skill published in the GitHub repository handsomestWei/patent-disclosure-skill (12,313 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 1,056 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other skills, from other repositories
phase-closeout
A Chinese-language stage closer that summarizes completed work, records decisions, updates project status, and prepares the next conversation.
vendor-review
Evaluate a vendor — cost analysis, risk assessment, and recommendation. Use when reviewing a new vendor proposal, deciding whether to renew or replace a contract, comparing two vendors side-by-side, or building a TCO breakdown and negotiation points before procurement sign-off.
launch-review
Full launch review against your framework and risk calibration. Use when the user says "review this launch", "legal review for [feature]", "can we ship this", "what are the legal issues with [product]", or references a launch tracker ticket or PRD that needs a category-by-category review memo.
client-intake
Structured intake — practice-area templates, cross-area issue spotting, conflict flags, and triage classification. Produces a formatted case summary the student analyzes and the professor reviews. Does NOT decide case acceptance. Use when starting a new client intake, running an intake interview, or writing up a new…
matter-close
Close a matter — capture outcome, final exposure, and lessons, then archive it out of the active portfolio without deleting the record. Use when the user wants to close a matter, says "[matter] is done", or needs to record a settlement, dismissal, judgment, withdrawal, or consolidation outcome.
comments
Review open NPRM comment periods, log decisions, track deadlines. Use when an NPRM has a comment window open and you need to surface deadlines, decide whether to file, or record a filing / not-filing / waived decision (--decide CMT-ID).