Agent skill

Patent Disclosure Handoff

by Light0305 in Light0305/Light-skills

Builds an evidence-backed invention disclosure packet from a project or research result for attorney or patent-agent review, without giving legal advice.

MITAuto-check passedLegal & Compliance

Install Patent Disclosure Handoff

skills CLI
$ npx skills add Light0305/Light-skills --skill light-patent-disclosure -a claude-code

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

GitHub CLI
$ gh skill install Light0305/Light-skills light-patent-disclosure --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/Light0305/Light-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/light-patent-disclosure .claude/skills/light-patent-disclosure && 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
light-patent-disclosure
GitHub stars
640
Token cost
~2k tokens
SKILL.md length
950 words
Files
5 (incl. scripts, references)
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

Builds an evidence-backed invention disclosure packet from a project or research result for attorney or patent-agent review, without giving legal advice.

  • Works in 7 steps: Intake the decision facts and risk triage → Build the evidence packet → Mine patent points with… → …
  • Preparing a technical disclosure document for a patent attorney
  • SKILL.md covers Non-negotiable boundaries, Workflow and ACT / ASK / NEVER
  • Runs Python scripts from its folder; calls python

What it does

This skill assembles an invention disclosure packet from a real project or research result, for a patent attorney or agent to review. The packet states the problem solved, the technical means, how it differs from nearby work, the embodiments that support claim breadth, the figures needed and what counsel still has to decide. It covers patent-point mining, public search and prior-art records, claim and support mapping and the final handoff.

The boundaries are strict. It is not legal advice, never marks anything ready to file, delivers only DRAFT, NEEDS_USER_INPUT or READY_FOR_ATTORNEY_REVIEW, and guarantees nothing about grant, novelty, validity or ownership. Unverified facts such as dates, assignees, inventors, public disclosures or priority are written as UNKNOWN, PLANNED or UNAVAILABLE with the next check. Evidence comes from real artifacts like repository files, design docs, lab notes and experiment logs, kept with relative locators and SHA-256 values. Patent figures must be programmatic or vector sources such as Mermaid, Graphviz, PlantUML or SVG, not AI-generated bitmaps.

Intake starts with jurisdiction and route (for example a Chinese invention or utility model, a US provisional, PCT or EP), applicants, inventors, public disclosure dates and deadlines. Reference files hold the interview and search rules and a resource map, and a disclosure_gate.py script and an example JSON packet template are included.

When your agent uses it

  • Preparing a technical disclosure document for a patent attorney
  • Mining patentable points from a software or research project
  • Recording prior-art search results and mapping claims to supporting evidence
  • Creating patent figures from diagram code

Example prompts

  • “Turn this repository into an invention disclosure packet for our patent attorney, with evidence paths.”
  • “Mine patent points from my lab notes and experiment logs, and mark anything unverified as UNKNOWN.”
  • “Draw patent figures for the system architecture using Mermaid.”
  • “整理一份技术交底书,管辖区还没定,先列出需要补充的事实。”

Requirements

  • Python to run scripts/disclosure_gate.py

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Intake the decision facts and risk triage
  2. Build the evidence packet
  3. Mine patent points with problem-solution-effect discipline
  4. Do prior-art / novelty-context work honestly
  5. Build the claim ladder
  6. Draft the disclosure for counsel
  7. Run the machine gate before delivery

What it can do on your machine

Read from SKILL.md and the folder at commit 6b44f57. 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 1 file 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

    No URLs in SKILL.md.

    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 Handoff loads about 2k tokens when it runs, and up to ~4.5k if it reads all its reference files. Until then it costs about 138 tokens; SKILL.md has 950 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~138
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.5k

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 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 Light0305/Light-skills at commit 6b44f57, republished under its MIT licence (© Light0305). 950 words, ~2,031 tokens.

Download SKILL.mdSave it as .claude/skills/light-patent-disclosure/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
light-patent-disclosure
description
Prepare evidence-backed patent invention disclosure materials for attorney or patent-agent review. Use when the user asks for 专利点挖掘, 技术交底书, 现有技术/查新记录, claim/patent-point support mapping, invention disclosure drafts, patent figures, or a handoff package for a software/research/project invention. This is an off-DAG engineering/IP handoff skill: it does not provide legal advice, does not submit filings, does not guarantee novelty, grant, allowance, validity or registration, and emits no Light research findings or back-edges.

Patent disclosure handoff

Turn a real project or research result into an attorney-reviewable invention disclosure packet: what problem is solved, what technical means solve it, why it differs from nearby work, what embodiments support the breadth, what figures are needed, and what counsel still needs to decide.

Read references/patent-resource-map.md before jurisdiction- or filing-sensitive work. It records the peer skills, official sources, borrowed mechanisms and honest boundaries. Read references/patent-interview-and-search.md before patent-point mining, public search, claim-ladder drafting or attorney handoff. It contains the detailed interview, search and QC rules.

Non-negotiable boundaries

  1. This skill is not legal advice and never certifies READY_TO_FILE. Deliver only DRAFT, NEEDS_USER_INPUT, or READY_FOR_ATTORNEY_REVIEW.
  2. Do not guarantee grant, novelty, inventive step, non-infringement, validity, ownership, freedom to operate, or registration outcome.
  3. Preserve uncertainty. If a search, date, assignee, inventor, public disclosure, foreign-filing rule, or priority fact is not verified, write UNKNOWN, PLANNED, or UNAVAILABLE with the next check.
  4. Evidence comes from real artifacts: repository files, design docs, lab notes, papers, experiment logs, issue discussions or user-supplied records. Keep relative locators and SHA-256. Do not invent implementation details.
  5. Patent figures must be programmatic/vector/manual sources such as Mermaid, Graphviz, PlantUML or SVG. Do not use AI-generated bitmap images for patent drawings.
  6. Keep the skill off the research DAG. It has no stage, no STAGE_GATES, no ROUTES, no light.findings.v1, and no scientific back-edge.

Workflow

1. Intake the decision facts and risk triage

Ask for or mark UNKNOWN:

  • jurisdiction and intended route: CN invention/utility model, US provisional, US nonprovisional, PCT, EP, or undecided;
  • owner/applicant, inventors/contributors, employment or sponsor constraints;
  • public disclosures, papers, demos, GitHub releases, sales, thesis defense, posters, standards submissions, and their dates;
  • deadline, prior filings, priority claim, secrecy/export/confidentiality risk;
  • whether a licensed attorney or patent agent will review the output.

Record risk_triage for public disclosure, ownership/inventorship, foreign-filing/secrecy and trade-secret redaction. Stop for the user when a public disclosure, ownership dispute, foreign filing strategy, secrecy review, or filing deadline could change the next action.

2. Build the evidence packet

Scan only files placed in scope. For each source artifact record:

  • id, relative path, sha256, freshness/date if known;
  • what claim element or embodiment it supports;
  • whether private or third-party confidential content must be redacted before sharing with outside counsel.

If the source is a paper, product demo, notebook, API contract, dataset or diagram, bind the exact locator. Do not let chat memory become evidence.

3. Mine patent points with problem-solution-effect discipline

For each candidate patent point, write:

  • technical problem, not business desire;
  • concrete technical means, algorithm, architecture, protocol, data structure, control loop, signal processing, model pipeline, hardware arrangement or UI interaction rule;
  • technical effect and measurable advantage;
  • distinguishing features versus the closest known work;
  • fallback embodiments, alternatives, parameter ranges and failure cases;
  • support artifact IDs for every feature.

Prefer one strong, defensible invention story over a pile of vague features. Ask targeted questions for tacit knowledge that the repo cannot show. Keep a short inventor interview log: problem, failed alternatives, key insight, constraints, contributors, disclosure dates and known prior art.

4. Do prior-art / novelty-context work honestly

Search the relevant official or public sources available in the current environment, then record:

  • databases/pages searched, query strings, date, filters and failures;
  • nearest results with locators and relationship to the invention;
  • whether the search is VERIFIED, PLANNED, UNKNOWN, or UNAVAILABLE.

Keep inventor_known_prior_art separate from prior_art. The former is what the team already knows; the latter is the agent-run public search log. A verified public search records searched_sources; if non-patent literature is not searched, write why.

Do not call this a legal novelty opinion. If search coverage is shallow, say so and list the missing source or professional search still needed.

Show full SKILL.md (342 more words)Show less
5. Build the claim ladder

Before drafting final sections, write a claim strategy:

  • broadest defensible technical point;
  • dependent/fallback positions and why each is narrower;
  • enablement support summary: embodiments, variants, parameter ranges, edge cases and alternatives;
  • artifact support for every strategy item.

If the broad point is unsupported, narrow it or mark it as counsel question.

6. Draft the disclosure for counsel

Use a plain, editable structure:

  1. title and technical field;
  2. background and nearest known approaches;
  3. technical problem;
  4. summary of the technical solution;
  5. beneficial technical effects;
  6. figure list and programmatic figure sources;
  7. detailed embodiments, variants and fallback implementations;
  8. draft patent points or draft claims with element-level support;
  9. novelty/difference table;
  10. open questions for attorney or patent agent review.

Claims are only drafts for review. Keep terminology consistent with the description and avoid over-broad elements unsupported by artifacts.

7. Run the machine gate before delivery

Create a packet following templates/patent-disclosure-packet.example.json, then run:

bash
python scripts/disclosure_gate.py --packet patent-disclosure-packet.json --base <project-root> --as-of 2026-07-05
python scripts/disclosure_gate.py --selftest

The gate must pass before saying the packet is ready for attorney review. It checks risk triage, inventor-known prior art, public search coverage, claim ladder, support mapping, figure source, QC flags and anti-overclaim language. A failed gate means fix the packet, lower the claim, or mark the missing fact.

ACT / ASK / NEVER

ACT:

  • bind every invention feature and draft claim element to source artifacts;
  • use official/current sources for jurisdiction-specific requirements;
  • produce counsel-facing open questions, not hidden assumptions;
  • generate figures as Mermaid/Graphviz/PlantUML/SVG or other auditable vector sources;
  • record prior-art search limits instead of pretending completeness.

ASK:

  • jurisdiction and filing route;
  • whether public disclosure has already happened and when;
  • ownership/inventor facts that are not in the repository;
  • whether to redact trade secrets before outside review;
  • whether a risky broad claim should be narrowed or left as counsel question.

NEVER:

  • submit, file, sign, pay fees, or interact with patent offices on the user's behalf;
  • promise grant/allowance/registration, novelty, inventive step or FTO;
  • turn generated pictures into patent drawings;
  • infer inventorship, ownership, disclosure dates or legal status from code alone;
  • route this skill into the Light research DAG.

© Light0305, 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/light-patent-disclosure of Light0305/Light-skills.

  • SKILL.md
  • references/patent-interview-and-search.md
  • references/patent-resource-map.md
  • scripts/disclosure_gate.py
  • templates/patent-disclosure-packet.example.json

Open the folder on GitHubat commit 6b44f57

Compare with similar skills

Patent Disclosure Handoff 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 Handoff compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Patent Disclosure Handoff this skillLight0305/Light-skills640—~2kAutomated safety check: PassMIT
Patent Disclosure Draftingillusionaireal/oh-my-patent104—~2.4kAutomated safety check: PassMIT
Patent Disclosure Skilltrsoliu/mini-wiki116—~1.7kAutomated safety check: NotesMIT
Contract Reviewzh-xx/legal-assistant-skills174—~1.6kAutomated safety check: PassApache-2.0
Patent Diagram GeneratorRobThePCGuy/Claude-Patent-Creator196—~1.7kAutomated safety check: NotesMIT
Patentfigdavila7/claude-code-templates33k—~1.2kAutomated safety check: PassMIT

Similar skills

  • Patent Disclosure Drafting

    illusionaireal/oh-my-patent

    Turns technical ideas, documents or code into traceable patent disclosures, with search planning, patent review, figure drawing and the ability to resume a project.

    104 GitHub stars~2.4k tokensUpdated 2 days ago
    Legal & ComplianceAuto-check passed
  • Patent Disclosure Skill

    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…

    116 GitHub stars~1.7k tokensUpdated 6 days ago
    Legal & ComplianceAuto-check: notes
  • 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
  • Patent Diagram Generator

    RobThePCGuy/Claude-Patent-Creator

    Create patent-style technical diagrams including flowcharts, block diagrams, and system architectures using Graphviz with reference numbering

    196 GitHub stars~1.7k tokensUpdated 4 days ago
    Legal & ComplianceAuto-check: notes
  • Patentfig

    davila7/claude-code-templates

    Generate patent-office-compliant figures via the PatentFig AI API — patent line art from text (PNG or SVG), vectorize drawings to SVG/DXF/vector PDF, AI-upscale images, and convert to filing-ready…

    33k GitHub stars~1.2k tokensUpdated yesterday
    Legal & ComplianceAuto-check passed
  • Linkfox Zhihuiya Fulltext Image

    linkfox-ai/linkfox-skills

    通过专利ID或公开号获取专利文件中的全文附图(图纸、示意图、图表)。当用户询问专利图片、专利图纸、专利示意图、专利插图、全文附图、专利图表、专利技术图或想查看、下载专利文件中的嵌入图片、patent fulltext drawings, patent diagrams, technical drawings, patent images…

    107 GitHub starsUsed in 1 repo~1.6k tokens
    Legal & ComplianceAuto-check passed

More from Light0305/Light-skills

All 23 skills in this repo
  • Citation Verification

    Light0305/Light-skills

    Verifies that every reference in a manuscript is real, correctly identified and actually supports its claim, and produces a citation registry for typesetting.

    640 GitHub stars~3.4k tokensUpdated 3 mo ago
    Auto-check passed
  • Light Research Orchestrator

    Light0305/Light-skills

    Coordinates and recovers multi-stage Light research projects from a single passport file, with checkpoints, stale-work tracking and rerouting only when you approve.

    640 GitHub stars~3.8k tokensUpdated 3 mo ago
    Auto-check passed
  • Light Project Structure

    Light0305/Light-skills

    Audits, scaffolds and safely migrates research project folder structures, keeping existing repositories read-only until you approve exact moves from a plan.

    640 GitHub stars~3k tokensUpdated 3 mo ago
    Auto-check: notes
  • Prepares draft materials for a China software copyright registration from a real project: application worksheet, source deposit plan, operation manual and consistency checks.

    640 GitHub stars~1.9k tokensUpdated 3 mo ago
    Auto-check passed
  • Light System Design

    Light0305/Light-skills

    Evidence-based workflow for designing or modernizing a software system: current-state inventory, options, API and schema contracts, migration plans, ADRs and verification.

    640 GitHub stars~3.6k tokensUpdated 3 mo ago
    Auto-check passed
  • Light Typesetting

    Light0305/Light-skills

    Build and preflight submission-ready LaTeX/PDF artifacts for Light stage 11.

    640 GitHub stars~3.3k tokensUpdated 3 mo ago
    Auto-check passed

Works with

Questions about Patent Disclosure Handoff

What does Patent Disclosure Handoff do?

Builds an evidence-backed invention disclosure packet from a project or research result for attorney or patent-agent review, without giving legal advice. This skill assembles an invention disclosure packet from a real project or research result, for a patent attorney or agent to review. The packet states the problem solved, the technical means, how it differs from nearby work, the embodiments that support claim breadth, the figures needed and what counsel still has to decide.

When should I use Patent Disclosure Handoff?

Patent Disclosure Handoff fits situations like: preparing a technical disclosure document for a patent attorney; mining patentable points from a software or research project; recording prior-art search results and mapping claims to supporting evidence; creating patent figures from diagram code.

How do I install Patent Disclosure Handoff in Claude Code?

Run `npx skills add Light0305/Light-skills --skill light-patent-disclosure -a claude-code`. Or copy the skill folder (skills/light-patent-disclosure in Light0305/Light-skills) into .claude/skills/light-patent-disclosure in your project. Claude Code loads it when a task matches its description.

How do I install Patent Disclosure Handoff in Codex?

Run `npx skills add Light0305/Light-skills --skill light-patent-disclosure -a codex`. Or copy the skill folder (skills/light-patent-disclosure in Light0305/Light-skills) into .agents/skills/light-patent-disclosure in your project. Codex loads it when a task matches its description.

Can I use Patent Disclosure Handoff 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 Light0305/Light-skills --skill light-patent-disclosure -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/light-patent-disclosure, .gemini/skills/light-patent-disclosure, .github/skills/light-patent-disclosure and .opencode/skills/light-patent-disclosure in your project.

What does Patent Disclosure Handoff need to run?

Going by SKILL.md and its folder, Patent Disclosure Handoff needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python to run scripts/disclosure_gate.py.

Does Patent Disclosure Handoff access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Patent Disclosure Handoff 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 Patent Disclosure Handoff use?

Patent Disclosure Handoff 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 Patent Disclosure Handoff use?

About 2k tokens (SKILL.md is roughly 8.1k 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 2.4k tokens, read only when the agent opens those files.

What are the alternatives to Patent Disclosure Handoff?

Skills that share tags, products or a category with Patent Disclosure Handoff: Patent Disclosure Drafting (illusionaireal/oh-my-patent, 104 stars), Patent Disclosure Skill (trsoliu/mini-wiki, 116 stars), Contract Review (zh-xx/legal-assistant-skills, 174 stars) and Patent Diagram Generator (RobThePCGuy/Claude-Patent-Creator, 196 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Patent Disclosure Handoff?

Light0305 (a GitHub user) maintains it in Light0305/Light-skills, which has 640 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on July 6, 2026.

Source: Light0305/Light-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.