@research-copilot/plugin 1.1.16 → 1.1.18

package/dist/skills/claims-drafting/SKILL.md

@@ -0,0 +1,239 @@
+---
+name: claims-drafting
+description: "Draft patent claims for an invention. Use when user says \"撰写权利要求\", \"draft claims\", \"写权利要求书\", \"claim drafting\", or wants to create patent claims. The core skill of the patent pipeline."
+argument-hint: [invention-disclosure-path]
+allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch
+---
+
+# Claims Drafting: The Core Patent Skill
+
+Draft patent claims based on: **$ARGUMENTS**
+
+This is the most critical skill in the patent pipeline. Claims define the legal scope of protection -- everything else (specification, figures, abstract) exists to support and enable the claims.
+
+## Constants
+
+- `REVIEWER_MODEL = gpt-5.5` — External examiner for claim quality review
+- `MAX_CLAIM_REVISION_ROUNDS = 3` — Maximum revision iterations
+- `CLAIM_STYLE = "auto"` — `US` (Jepson or open), `EP` (two-part mandatory), `CN` (two-part), `auto` (detect from jurisdiction)
+- `MIN_INDEPENDENT_CLAIMS = 2` — Typically method + system. For utility model (实用新型): apparatus/device only, NO method claims.
+- `MAX_TOTAL_CLAIMS = 20` — Practical limit (USPTO includes 20 in base fee)
+- `PATENT_TYPE = "invention"` — `invention` (发明专利) or `utility_model` (实用新型, apparatus claims only)
+
+## Inputs
+
+1. `patent/INVENTION_DISCLOSURE.md` — structured invention with core/supporting/optional features
+2. `patent/PRIOR_ART_REPORT.md` — prior art to avoid
+3. `patent/NOVELTY_ASSESSMENT.md` — novelty analysis with suggested amendments
+4. Target jurisdiction from invention disclosure or `$ARGUMENTS`
+
+## Shared References
+
+Load `../shared-references/patent-writing-principles.md` for claim drafting principles, antecedent basis rules, and common pitfalls.
+Load `../shared-references/patent-format-cn.md` for CN claim format (其特征在于).
+Load `../shared-references/patent-format-us.md` for US claim format (comprising, means-plus-function).
+Load `../shared-references/patent-format-ep.md` for EP two-part form (characterised in that).
+
+## Workflow
+
+### Step 1: Determine Claim Style and Patent Type
+
+Based on patent type and jurisdiction:
+
+**If `PATENT_TYPE = utility_model` (实用新型)**:
+- CN jurisdiction ONLY
+- Apparatus/device claims ONLY — no method, no product-by-process
+- `MIN_INDEPENDENT_CLAIMS = 1` (single apparatus claim is sufficient)
+- Claim format: "1. 一种[主题]，其特征在于，包括：[组件描述]。"
+
+Based on target jurisdiction:
+
+| Jurisdiction | Claim Style | Characterising Phrase | Preamble Format |
+|-------------|------------|----------------------|-----------------|
+| CN | Two-part (两部式) | 其特征在于 | 一种...的方法/装置，包括： |
+| US | Open (preferred) | comprising | A method for..., comprising: |
+| EP | Two-part (mandatory) | characterised in that | A method for..., comprising [known], characterised in that [inventive] |
+| ALL | Draft CN + US + EP | All of the above | All of the above |
+
+### Step 2: Draft Independent Claims
+
+**CRITICAL — Claims numbering (CN format):**
+- Claims must be numbered 1, 2, 3, ... continuously without gaps
+- Independent and dependent claims are INTERMIXED in final numbering
+- Do NOT group independent claims separately from dependent claims
+- Example correct: Claim 1 (independent, product), Claim 2 (depends on 1), Claim 3 (depends on 1), Claim 4 (independent, method), Claim 5 (depends on 4)...
+- Example WRONG: Claim 1 (independent), Claim 5 (independent), Claim 8 (independent), then Claim 2, 3, 4, 6, 7, 9, 10 as dependents
+
+**CRITICAL — No empirical content in claims:**
+- Claims describe ONLY structural features or method steps
+- Do NOT include signal characteristics, detection principles, measurement results
+- WRONG: "产生负脉冲信号" / "谐振频率下降" — these are results, not features
+- RIGHT: "所述开口谐振环的开口处形成用于检测通过流体中颗粒物的间隙传感区域"
+
+For each claim category identified in INVENTION_DISCLOSURE.md:
+
+**Method Claim (broadest)**:
+1. Start with preamble identifying the category and purpose
+2. List the core inventive features (from the "Core Inventive Concept" section)
+3. Include enough known features for context (but not more than necessary)
+4. Use open transition ("comprising" / "包括")
+5. Each element should be separated by semicolons or on separate lines
+6. Apply jurisdiction-specific format:
+   - CN: 前序部分 + "其特征在于" + 特征部分
+   - US: Preamble + "comprising:" + elements
+   - EP: Preamble + known features + "characterised in that" + inventive features
+
+**System/Apparatus Claim**:
+1. Mirror the method claim in structural form
+2. Each method step becomes a "module configured to..." or "component for..."
+3. Same hierarchy of known vs. inventive features
+
+**Quality checks for each independent claim**:
+- [ ] Single sentence (US/EP) or properly structured (CN)
+- [ ] Antecedent basis: "a" first, "the" thereafter for each element
+- [ ] No relative terms without definition
+- [ ] No result-to-be-achieved limitations
+- [ ] Transitional phrase is appropriate (open preferred)
+- [ ] Preamble does not import unnecessary limitations
+- [ ] Each element is necessary for patentability
+- [ ] Claim scope is broadest defensible over prior art
+
+### Step 3: Draft Dependent Claims
+
+For each independent claim, draft 5-10 dependent claims that:
+
+1. **Narrow the core inventive features**: Specific implementations, parameters, ranges
+2. **Cover preferred embodiments**: Features from the specification's detailed description
+3. **Provide fallback positions**: If the independent claim is rejected, these narrower claims may survive
+4. **Cover alternatives**: Different ways to achieve the same inventive result
+
+**Dependent claim format**:
+- CN: "根据权利要求X所述的[主题]，其特征在于，所述[特征]具体为..."
+- US: "The [method/system] of claim X, wherein the [element] comprises [limitation]."
+- EP: "The [method/system] according to claim X, characterised in that [limitation]."
+
+**Rules for dependent claims**:
+- Each must add at least one meaningful limitation
+- Must reference a prior claim by number
+- Must not merely repeat the parent claim
+- Should not be cumulative (each claim should be independently useful as a fallback)
+- Multiple dependent claims (US: only "or" references, not "and")
+
+### Step 4: Claim-to-Specification Mapping
+
+Create a preliminary mapping to verify enablement:
+
+| Claim Element | Must be described in specification | Reference numeral |
+|---------------|-----------------------------------|-------------------|
+| [element 1] | Yes/No | [numeral] |
+| [element 2] | Yes/No | [numeral] |
+
+If any element lacks specification support, add it to the specification requirements.
+
+### Step 5: Cross-Model Examiner Review
+
+Start the examiner review with a dedicated Codex reviewer agent at xhigh reasoning:
+
+```
+spawn_agent:
+  model: gpt-5.5
+  reasoning_effort: xhigh
+  message: |
+    You are a senior patent examiner at the [USPTO/CNIPA/EPO].
+    Review the following patent claims for quality and patentability.
+
+    CLAIMS: [all claims]
+
+    PRIOR ART: [prior art references from PRIOR_ART_REPORT.md]
+
+    INVENTION: [summary from INVENTION_DISCLOSURE.md]
+
+    Analyze each claim for:
+    1. Clarity (35 USC 112(b) / Art 84 EPC): Are terms definite?
+    2. Written description support: Does the spec support all claim scope?
+    3. Anticipation (102/Art 54): Would any single reference anticipate?
+    4. Obviousness (103/Art 56): Would any combination render obvious?
+    5. Claim scope: Are independent claims broad enough to be valuable?
+    6. Dependent claims: Do they provide meaningful fallback positions?
+    7. Antecedent basis: Any issues with "a"/"the" usage?
+    8. Indefinite terms: Any functional/result language issues?
+
+    For each issue found, provide:
+    - The specific claim number and element
+    - The problem (cite statute/rule)
+    - A suggested fix
+
+    Provide an overall PATENTABILITY SCORE: 1-10.
+```
+
+### Step 6: Revision Loop
+
+If the examiner review identifies issues:
+
+1. Address all CRITICAL issues (anticipation, obviousness, indefiniteness)
+2. Address MAJOR issues (scope too narrow, missing support, weak fallbacks)
+3. Consider MINOR issues (antecedent basis, formatting)
+4. Re-submit to the same examiner via `send_input` using the saved reviewer id
+5. Repeat up to `MAX_CLAIM_REVISION_ROUNDS` times
+
+```text
+send_input:
+  target: [saved reviewer id from Step 5]
+  message: |
+    Here is the revised claim set after addressing the previous office action.
+
+    Revised claims:
+    [full revised claims]
+
+    Focus only on unresolved or newly introduced issues.
+```
+
+### Step 7: Output
+
+Write `patent/CLAIMS.md`:
+
+```markdown
+## Patent Claims
+
+### Independent Claims
+
+#### Claim 1 — Method
+[formatted claim text]
+
+#### Claim X — System/Apparatus
+[formatted claim text]
+
+### Dependent Claims
+
+#### Claim 2 (depends on 1)
+[formatted claim text]
+
+#### Claim 3 (depends on 1)
+[formatted claim text]
+...
+
+### Claims Summary Table
+
+| Claim | Type | Depends On | Key Limitation | Prior Art Avoidance |
+|-------|------|-----------|----------------|---------------------|
+| 1 | Method | — | [core inventive features] | [what makes it novel over prior art] |
+| 2 | Method | 1 | [narrowing] | [additional distinguishing] |
+| X | System | — | [mirrors claim 1] | [same as claim 1] |
+...
+
+### Examiner Review Summary
+[Key findings and how they were addressed]
+```
+
+## Key Rules
+
+- Claims are the single most important part of the patent. Everything else supports them.
+- Draft independent claims first, then dependent claims.
+- Independent claims must be broadest defensible scope over prior art -- not broader, not narrower.
+- Each dependent claim should be independently useful as a fallback position.
+- Antecedent basis is mandatory: "a processor" first, "the processor" thereafter.
+- Use "comprising" (open) unless there is a specific reason for "consisting of" (closed).
+- Never include result-to-be-achieved language in claims ("configured to achieve high accuracy").
+- Never fabricate claim language -- every element must come from the actual invention.
+- If drafting for ALL jurisdictions, produce separate claim sets for CN, US, and EP.
+- If reviewer delegation is unavailable in the current Codex host, stop and ask the user to enable Codex agent support before continuing the examiner loop.

package/dist/skills/comm-lit-review/SKILL.md

@@ -0,0 +1,299 @@
+---
+name: comm-lit-review
+description: "Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary."
+allowed-tools: Bash(*), Read, Glob, Grep, WebSearch, WebFetch, Write, mcp__zotero__*, mcp__obsidian-vault__*
+---
+
+# Comm Lit Review Claude Single
+
+Research topic: $ARGUMENTS
+
+## Purpose
+
+Use this skill for communications-domain literature review when the topic is about:
+
+- wireless communications
+- cellular systems, `4G/5G/6G`, `NR`, `NTN`
+- satellite, `LEO`, `GEO`, integrated space-air-ground systems
+- Wi-Fi, WLAN, mesh, ad hoc, sidelink, V2X
+- routing, scheduling, resource allocation, beamforming
+- rate adaptation, link adaptation, `ACM`, `HARQ`, `CSI` feedback
+- transport protocols and congestion control in communication networks
+- cross-layer optimization for communication systems
+
+If the center of gravity is generic ML architecture research, pure control theory without communications literature, or software/API documentation rather than papers, fall back to a general literature skill.
+
+## Constants
+
+- **PAPER_LIBRARY**: Check local PDFs in this order:
+  1. `papers/` in the current project
+  2. `literature/` in the current project
+  3. Custom path specified by the user in `AGENTS.md` under `## Paper Library`
+- **MAX_LOCAL_PAPERS = 20**: Maximum number of local PDFs to scan. If there are more, prioritize by filename and first-page relevance.
+
+## Source Selection
+
+Parse `$ARGUMENTS` for a `— sources:` directive.
+
+- If `— sources:` is specified, only search the listed sources.
+- If not specified, default to:
+  - `zotero`
+  - `obsidian`
+  - `local`
+  - `ieee`
+  - `sciencedirect`
+  - `acm`
+  - `web`
+
+Valid source values:
+
+- `zotero`
+- `obsidian`
+- `local`
+- `ieee`
+- `sciencedirect`
+- `acm`
+- `web`
+- `all`
+
+If `all` is specified, interpret it as the full default source set.
+
+## Retrieval Order
+
+This is a knowledge-base-first skill. Search in this order unless the user overrides it:
+
+1. `Zotero`
+2. `Obsidian`
+3. local `papers/` and `literature/`
+4. `IEEE Xplore`
+5. `ScienceDirect`
+6. `ACM Digital Library`
+7. broader web
+
+Graceful degradation rules:
+
+- If an unrequested source is unavailable, do not fail.
+- Skip it silently and continue to the next source.
+- If the user explicitly requested a source and it is unavailable, stop and tell the user what must be configured. Do not silently downgrade an explicitly requested source policy.
+
+## External Search Policy
+
+For external search:
+
+- prefer `IEEE Xplore` first
+- then `ScienceDirect`
+- then `ACM`
+- then broader web only when needed
+
+Publication policy:
+
+- prefer peer-reviewed journals and major conferences
+- label workshop papers as `workshop`
+- label arXiv-only or author-hosted versions as `preprint`
+- if both preprint and formal version exist, cite the formal version first
+
+Time-window policy:
+
+- if the user does not specify a year range, include both a short foundational set and a recent set
+- recommended split:
+  - `foundational`: before 2022
+  - `recent`: 2022 to present
+
+## Venue Priority
+
+Within each database tier, search venue tiers in this order.
+
+### Tier A
+
+Journals:
+
+- `IEEE Journal on Selected Areas in Communications (JSAC)`
+- `IEEE/ACM Transactions on Networking (ToN)`
+- `IEEE Transactions on Wireless Communications (TWC)`
+- `IEEE Transactions on Communications (TCOM)`
+
+Conferences:
+
+- `ACM SIGCOMM`
+- `USENIX NSDI`
+- `ACM MobiCom`
+- `ACM CoNEXT`
+- `IEEE INFOCOM`
+
+### Tier B
+
+Journals:
+
+- `IEEE Transactions on Vehicular Technology (TVT)`
+- `IEEE Wireless Communications Letters (WCL)`
+- `IEEE Communications Letters`
+- `Computer Networks`
+- `Computer Communications`
+- `Ad Hoc Networks`
+- `Physical Communication`
+
+Conferences:
+
+- `IEEE ICC`
+- `IEEE GLOBECOM`
+- `IEEE WCNC`
+- `IEEE PIMRC`
+- `ACM MobiHoc`
+
+### Tier C
+
+- other relevant IEEE journals and transactions
+- other relevant Elsevier journals
+- other clearly relevant ACM conferences and workshops
+- topic-specific satellite, optical, vehicular, IoT, aerial, or edge communications venues
+
+Usage rules:
+
+- start from Tier A
+- widen to Tier B if needed
+- widen to Tier C if still sparse
+- only then broaden to full web search
+- by default this is a soft priority, not a hard whitelist
+- if the user says `only top venues`, `top journals only`, or `top conferences only`, treat Tier A as a hard filter
+
+## Workflow
+
+### Step 0a: Search Zotero Library
+
+Skip this step if Zotero MCP is not configured or `zotero` is not enabled.
+
+If available:
+
+1. search by topic
+2. capture title, authors, year, venue
+3. pull user annotations, tags, or collections when present
+4. treat these as high-priority evidence because they reflect the user's existing library
+
+### Step 0b: Search Obsidian Vault
+
+Skip this step if Obsidian MCP is not configured or `obsidian` is not enabled.
+
+If available:
+
+1. search topic-related notes
+2. collect summaries, wikilinks, tags, and paper references
+3. treat these notes as the user's processed understanding of the topic
+
+### Step 0c: Scan Local Paper Library
+
+Run this step if `local` is enabled.
+
+1. locate PDFs from `papers/**/*.pdf` and `literature/**/*.pdf`
+2. de-duplicate against Zotero hits when possible
+3. read the first pages of relevant PDFs
+4. extract title, authors, year, problem, method, and relevance
+5. use local hits to guide and de-duplicate later external search
+
+### Step 1: Search External Primary Sources
+
+Use a layered search strategy. For communications topics, avoid random blog posts or tertiary summaries.
+
+Database ladder:
+
+1. `ieeexplore.ieee.org`
+2. `sciencedirect.com`
+3. `dl.acm.org`
+4. broader web using primary publisher pages, official conference sites, DOI pages, and author-hosted copies of already-identified formal papers
+
+Move to the next database tier only when:
+
+- the higher-priority tier is too sparse
+- the topic clearly publishes elsewhere
+- the user explicitly asks for broader coverage
+
+Within each database tier:
+
+1. start from Tier A venues
+2. widen to Tier B if needed
+3. widen to Tier C if still sparse
+
+### Step 2: Extract Paper-Level Facts
+
+For each relevant paper, capture:
+
+- Title
+- Authors
+- Year
+- Venue
+- Layer or system scope
+- Scenario and assumptions
+- Core method
+- Main result or claim
+- Limitation
+- Relevance to the user's topic
+- Source URL
+- Source origin: `zotero`, `obsidian`, `local`, `ieee`, `sciencedirect`, `acm`, or `web`
+
+Favor concrete numbers, assumptions, and problem definitions over generic paraphrases.
+
+Do not collapse transport-layer rate control and PHY/MAC rate adaptation into one bucket without saying so explicitly.
+
+## Synthesis Rules
+
+Group papers by technical axis rather than by search order. Common groupings:
+
+- `PHY/MAC` adaptation
+- transport and congestion control
+- `NTN` and satellite resource management
+- cross-layer or learning-based control
+- measurement and empirical studies
+
+When useful, explicitly separate:
+
+- foundational vs recent work
+- formal publications vs preprints
+- top-tier vs lower-tier venues
+- single-link vs multi-user formulations
+- simulation-only vs deployment-backed work
+- user-owned sources vs newly surfaced external papers
+
+If evidence is weak, say so instead of smoothing it over.
+
+## Output
+
+Use a literature table with these columns:
+
+| Paper | Venue | Year | Layer | Scenario | Method | Key Result | Limitation | Relevance | Source |
+|---|---|---:|---|---|---|---|---|---|---|
+
+`Source` should indicate where the paper came from first:
+
+- `zotero`
+- `obsidian`
+- `local`
+- `ieee`
+- `sciencedirect`
+- `acm`
+- `web`
+
+After the table, summarize in this order:
+
+1. what the field is mostly trying to solve
+2. how papers cluster into `2-4` approaches
+3. what the user already had vs what was newly surfaced
+4. where the evidence is strong vs weak
+5. what research gap remains
+
+End with `Practical Takeaway`:
+
+- dominant current approach
+- likely saturated direction
+- promising open direction
+
+## Key Rules
+
+- Do not silently downgrade explicitly requested sources, account-backed databases, or primary-database constraints. Report the missing configuration instead.
+
+- Never fail because Zotero or Obsidian MCP is missing.
+- Prefer user-owned sources first when available, but do not let them replace external validation.
+- Prefer primary formal sources over summaries or tertiary commentary.
+- Prefer `IEEE` and `ScienceDirect` first, `ACM` second, and only then broader web search unless the user asks otherwise.
+- Search venue tiers from top to broad within each database tier.
+- Treat venue tiers as soft ranking by default and hard constraint only when the user explicitly asks for top-only search.
+- Do not pretend a preprint is peer reviewed.
+- If the topic spans multiple layers, say that the literature itself is split across layers.

package/dist/skills/comm-lit-review/references/domain-taxonomy.md

@@ -0,0 +1,57 @@
+# Communications Domain Taxonomy
+
+Use this file to decide whether the request should trigger this skill and how to organize the review.
+
+## Typical trigger topics
+
+- Wireless communications
+- Cellular systems, `4G/5G/6G`, `NR`, `NTN`
+- Satellite, `LEO`, `GEO`, integrated space-air-ground networks
+- Wi-Fi, WLAN, mesh, ad hoc, sidelink, V2X
+- Routing, scheduling, resource allocation, beamforming
+- Rate adaptation, link adaptation, ACM, HARQ, CSI feedback
+- Transport protocols and congestion control in communication networks
+- Cross-layer optimization for communication systems
+
+## Common grouping axes
+
+### By layer
+
+- PHY
+- MAC
+- Network
+- Transport
+- Cross-layer
+
+### By environment
+
+- Terrestrial wireless
+- Satellite / NTN
+- UAV / aerial
+- Vehicular / sidelink
+- IoT / LPWAN
+
+### By method
+
+- Model-based control
+- Optimization
+- Learning-based
+- Prediction-based
+- Measurement / trace-driven
+
+## Boundary cases
+
+Use this skill if the paper's main contribution is still about a communication system, even if it uses ML.
+
+Examples that should still trigger:
+
+- DRL for Wi-Fi rate adaptation
+- GNN for radio resource allocation
+- LSTM for satellite link prediction
+- learning-based congestion control for LEO
+
+Prefer a different skill if the center of gravity is elsewhere:
+
+- pure ML architecture research with communications as a toy application
+- generic control theory without communications-specific literature
+- software/API documentation rather than research papers

package/dist/skills/comm-lit-review/references/output-template.md

@@ -0,0 +1,37 @@
+# Output Template
+
+## Default literature table
+
+Use a table with these columns unless the user requests a different format:
+
+| Paper | Venue | Year | Layer | Scenario | Method | Key Result | Limitation | Relevance |
+|---|---|---:|---|---|---|---|---|---|
+
+## Narrative structure
+
+After the table, summarize in this order:
+
+1. What the field is mostly trying to solve
+2. How papers cluster into 2-4 main approaches
+3. What assumptions dominate the literature
+4. Where the evidence is strong vs weak
+5. What research gap remains
+
+## Recommended distinctions
+
+Call out these distinctions when relevant:
+
+- foundational vs recent
+- formal publication vs preprint
+- simulation vs measurement
+- single-link vs multi-user or system-level
+- reactive vs predictive
+- single-layer vs cross-layer
+
+## Minimal closing section
+
+End with a short section titled `Practical Takeaway` that states:
+
+- the current dominant approach
+- the likely saturated direction
+- the most promising open direction