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 | $0.00825 |
| Opus 5 | $0.00046 | $0.00413 |
| Sonnet 5 | $0.00019 | $0.00165 |
| Haiku 4.5 | $0.00009 | $0.00082 |
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 2d 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.
What it actually says
案卷会稿
单 agent 协调者。先 Read prompts/guardrails.md，再 Read prompts/intake.md。 禁止跳过 intake 直接派工。
本包只调度与记案卷，不写交底正文、不出四件套。派工时 Read 对方 SKILL.md 并按该包执行；禁止调用其他子技能的 tools/。
加载顺序（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（见下表）。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，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。
命令
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
案卷目录默认 outputs/docket/{case_id}/（gitignore 的 outputs/）。机读前缀：DOCKET_DIR: / DOCKET_YAML: / DOCKET_OK: / DOCKET_ERROR:。
不做：审查答复、政策简报、著录检索当会稿引擎、多 agent 分发、把聊天摘要当成技术事实。
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 1.5 KB
- prompts/intake.md 2.3 KB
- prompts/resume.md 985 B
- prompts/round_close.md 1.4 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 1.1 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.
- 2d 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 (8,909 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 825 once invoked, about $0.0005 per session on Opus 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.
compliance-checker
Check affiliate content for FTC compliance and platform rules. Triggers on: "check my content for compliance", "FTC disclosure check", "is this legal", "review for compliance", "check affiliate disclosure", "am I FTC compliant", "audit my content", "compliance review", "legal check", "platform rules check", "check…
competitive-intelligence
Analyze competitor IP portfolios — comparative patent portfolio reports with strategy inference. Budget: 120 patent families, 15 claim parses, 40 web searches.
claim-analysis
Deep claim scope analysis — decompose independent/dependent claims and assess protection scope breadth. Budget: 30 patent families, 30 claim parses, 20 web searches.
appropriateness-bounding
Establish acceptability standards through RAND/UCLA Appropriateness Method or Consensus Conference protocols.