ctxora 6.2.2 → 6.3.0

package/src/harness_context/skills/ecc/scientific-db-uspto-database/SKILL.md

@@ -0,0 +1,178 @@
+---
+name: uspto-database
+description: USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs. Use when a task needs official United States patent or trademark records from USPTO systems.
+metadata:
+  origin: community
+---
+
+# USPTO Database
+
+Use this skill when a task needs official United States patent or trademark
+records from USPTO systems.
+
+## When to Use
+
+- Searching granted patents or pre-grant publications.
+- Checking patent application status, file-wrapper data, assignments, or
+  public prosecution history.
+- Looking up trademark status, documents, or assignment history.
+- Building reproducible prior-art, portfolio, or IP landscape research logs.
+- Comparing USPTO records with secondary tools such as Google Patents,
+  Lens.org, Semantic Scholar, or company patent pages.
+
+Do not use this skill to give legal advice. Treat it as a data-gathering and
+record-verification workflow.
+
+## Source Selection
+
+Prefer official USPTO or USPTO-supported surfaces first:
+
+- Open Data Portal (ODP): current home for migrated USPTO datasets and APIs.
+- Patent File Wrapper: public patent application bibliographic data and file
+  wrapper records.
+- PatentSearch API: PatentsView search API for granted patents and pre-grant
+  publication datasets.
+- TSDR Data API: trademark status and document retrieval.
+- Patent and Trademark Assignment Search: ownership transfer records.
+- PTAB data in ODP: Patent Trial and Appeal Board proceedings.
+
+Use secondary sources only as convenience indexes. When the answer matters,
+cross-check the official record.
+
+## Authentication and Secrets
+
+Many USPTO API flows require an API key. Store keys in environment variables or
+a secret manager, never in committed files or pasted transcripts.
+
+Common environment names:
+
+```bash
+export USPTO_API_KEY="..."
+export PATENTSVIEW_API_KEY="..."
+```
+
+For PatentSearch, send the key with the `X-Api-Key` header. For TSDR, follow
+the current USPTO API Manager instructions and rate-limit guidance.
+
+## PatentSearch Workflow
+
+Use PatentSearch for broad patent and pre-grant publication search when the
+question is about trends, inventors, assignees, classifications, dates, or
+portfolio slices.
+
+Workflow:
+
+1. Identify the endpoint from the current PatentSearch reference or Swagger UI.
+2. Build a JSON query with explicit filters.
+3. Request only the fields needed for the analysis.
+4. Sort and paginate deterministically.
+5. Record the endpoint, query body, date, data currency note, and result count.
+
+Python request skeleton:
+
+```python
+import os
+import requests
+
+API_KEY = os.environ["PATENTSVIEW_API_KEY"]
+BASE = "https://search.patentsview.org/api/v1"
+
+payload = {
+    "q": {
+        "_and": [
+            {"patent_date": {"_gte": "2024-01-01"}},
+            {"assignees.assignee_organization": {"_text_any": ["Google", "Alphabet"]}},
+        ]
+    },
+    "f": ["patent_id", "patent_title", "patent_date"],
+    "s": [{"patent_date": "desc"}],
+    "o": {"per_page": 100, "page": 1},
+}
+
+response = requests.post(
+    f"{BASE}/patent/",
+    headers={"X-Api-Key": API_KEY, "Content-Type": "application/json"},
+    json=payload,
+    timeout=30,
+)
+response.raise_for_status()
+print(response.json())
+```
+
+Before reusing a query, verify current endpoint names, field paths, request
+parameters, and API-key availability in the live PatentSearch docs.
+
+## Trademark/TSDR Workflow
+
+Use TSDR when the task needs trademark case status, documents, images, owner
+history, or prosecution events.
+
+Workflow:
+
+1. Normalize the serial number or registration number.
+2. Check the current TSDR API instructions and required API-key header.
+3. Fetch status first, then documents only if needed.
+4. Respect the lower rate limit for PDF, ZIP, and multi-case downloads.
+5. Capture retrieval date and serial/registration identifier in the output.
+
+For large trademark pulls, prefer documented bulk-data flows rather than
+screen-scraping public pages.
+
+## File Wrapper and Prosecution History
+
+For application status, transaction history, and prosecution documents:
+
+- Start with ODP Patent File Wrapper search.
+- Use exact identifiers when available: application number, publication number,
+  patent number, or party name.
+- Record whether the record is a granted patent, pre-grant publication, or
+  pending application.
+- Cross-check document dates and status against the record detail page before
+  citing them.
+
+## Assignment Workflow
+
+For patent or trademark ownership:
+
+1. Search official assignment data by patent/application/registration number,
+   assignor, assignee, or reel/frame when available.
+2. Record conveyance text, execution date, recordation date, and parties.
+3. Distinguish assignment records from current legal ownership conclusions.
+4. If ownership is material, flag the result for attorney or subject-matter
+   review.
+
+## Reproducible Output
+
+Every USPTO research pass should include a log table:
+
+```markdown
+| Source | Date searched | Identifier/query | Filters | Results | Notes |
+| --- | --- | --- | --- | ---: | --- |
+| PatentSearch | 2026-05-11 | `assignee=Alphabet AND date>=2024` | patent endpoint | 118 | API docs checked before run |
+| TSDR | 2026-05-11 | `serial=90000000` | status only | 1 | API-key flow, no document bulk pull |
+```
+
+For final writeups, separate:
+
+- official record facts
+- inferred analysis
+- secondary-source convenience matches
+- unresolved gaps or records that require legal review
+
+## Review Checklist
+
+- Did you use an official USPTO or USPTO-supported source first?
+- Did you verify current endpoint and field names before running code?
+- Are API keys kept out of files, shell history, and output logs?
+- Does the query log include the date searched and exact request shape?
+- Are rate limits respected?
+- Are legal conclusions avoided or explicitly escalated?
+- Are secondary sources labeled as secondary?
+
+## References
+
+- [USPTO APIs catalog](https://developer.uspto.gov/api-catalog)
+- [USPTO Open Data Portal](https://data.uspto.gov/)
+- [PatentSearch API reference](https://search.patentsview.org/docs/docs/Search%20API/SearchAPIReference/)
+- [PatentSearch API updates](https://search.patentsview.org/docs/)
+- [TSDR API bulk download FAQ](https://developer.uspto.gov/faq/tsdr-api-bulk-download)

package/src/harness_context/skills/ecc/scientific-pkg-gget/LICENSE.ecc

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Affaan Mustafa
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/src/harness_context/skills/ecc/scientific-pkg-gget/SKILL.md

@@ -0,0 +1,167 @@
+---
+name: gget
+description: gget CLI and Python workflow for quick genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and reproducible bioinformatics evidence logs. Use when a task needs quick bioinformatics lookup across genomic reference databases with the gget CLI or Python package.
+metadata:
+  origin: community
+---
+
+# gget
+
+Use this skill when a task needs quick bioinformatics lookup across genomic
+reference databases with the `gget` CLI or Python package.
+
+## When to Use
+
+- Finding Ensembl IDs, gene metadata, transcript details, or sequences.
+- Running quick BLAST or BLAT lookups without building a full local pipeline.
+- Fetching reference genome links and annotations from Ensembl.
+- Querying protein structure, pathway, cancer, expression, or disease-association
+  modules through a single interface.
+- Creating a reproducible first-pass evidence log before moving to heavier
+  tools such as Biopython, Snakemake, Nextflow, BLAST+, or database-specific
+  clients.
+
+Use a dedicated workflow instead of `gget` when the task requires regulated
+clinical interpretation, high-throughput production pipelines, or fine-grained
+control over database versions and local indexes.
+
+## Installation
+
+Use a clean Python environment.
+
+```bash
+python -m venv .venv
+. .venv/bin/activate
+python -m pip install --upgrade pip
+python -m pip install --upgrade gget
+gget --help
+```
+
+If `uv` is available:
+
+```bash
+uv venv
+. .venv/bin/activate
+uv pip install gget
+```
+
+Before relying on an older environment, upgrade `gget` and re-check the module
+docs. The upstream databases queried by `gget` change over time.
+
+## Basic Patterns
+
+CLI shape:
+
+```bash
+gget <module> [arguments] [options]
+```
+
+Python shape:
+
+```python
+import gget
+
+result = gget.search(["BRCA1"], species="human")
+print(result)
+```
+
+Common workflow:
+
+1. Identify the species, assembly, gene ID type, and database needed.
+2. Check the current module documentation for arguments.
+3. Run a small query first.
+4. Save output with an explicit filename and date.
+5. Record module name, version, arguments, and database assumptions.
+
+## Common Modules
+
+Use current upstream docs for exact arguments. These modules are common first
+choices:
+
+- `gget search`: find Ensembl IDs from search terms.
+- `gget info`: retrieve metadata for Ensembl, UniProt, or related IDs.
+- `gget seq`: fetch nucleotide or amino-acid sequences.
+- `gget ref`: retrieve reference genome download links.
+- `gget blast`: run a quick BLAST query.
+- `gget blat`: locate a sequence against supported genome assemblies.
+- `gget muscle`: run multiple sequence alignment.
+- `gget diamond`: run local sequence alignment against reference sequences.
+- `gget alphafold` and `gget pdb`: inspect protein-structure references.
+- `gget enrichr`, `gget opentargets`, `gget archs4`, `gget bgee`, `gget cbio`,
+  and `gget cosmic`: explore enrichment, target, expression, cancer, and disease
+  association data.
+
+Do not assume every module supports every Python version or dependency set.
+Some optional scientific dependencies have narrower version support than the
+core package.
+
+## Quick Examples
+
+Find genes:
+
+```bash
+gget search -s human brca1 dna repair -o brca1-search.json
+```
+
+Fetch gene metadata:
+
+```bash
+gget info ENSG00000012048 -o brca1-info.json
+```
+
+Fetch a sequence:
+
+```bash
+gget seq ENSG00000012048 -o brca1-seq.fa
+```
+
+Run a small BLAST query:
+
+```bash
+gget blast "MEEPQSDPSVEPPLSQETFSDLWKLLPEN" -l 10 -o blast-results.json
+```
+
+Python example:
+
+```python
+import gget
+
+genes = gget.search(["BRCA1", "DNA repair"], species="human")
+info = gget.info(["ENSG00000012048"])
+sequence = gget.seq("ENSG00000012048")
+```
+
+## Reproducibility Log
+
+For scientific outputs, include enough metadata to replay the query.
+
+```markdown
+| Date | gget version | Module | Query | Species/assembly | Output | Notes |
+| --- | --- | --- | --- | --- | --- | --- |
+| 2026-05-11 | `gget --version` | search | `BRCA1 DNA repair` | human | `brca1-search.json` | Docs checked before run |
+```
+
+Also record:
+
+- Python version and environment manager.
+- Any optional dependency installed through `gget setup`.
+- Database-specific identifiers returned by the query.
+- Whether output is JSON, CSV, FASTA, or a DataFrame export.
+- Any failures that were resolved by upgrading `gget`.
+
+## Review Checklist
+
+- Did you upgrade or verify the installed `gget` version?
+- Did you check the current upstream module docs before using arguments?
+- Is the species or assembly explicit?
+- Are identifiers preserved exactly, including Ensembl/UniProt prefixes?
+- Is the result labeled as database output rather than clinical interpretation?
+- Is the query reproducible from the saved command or Python snippet?
+- Are optional dependencies installed in an isolated environment?
+
+## References
+
+- [gget documentation](https://pachterlab.github.io/gget/)
+- [gget updates](https://pachterlab.github.io/gget/en/updates.html)
+- [gget GitHub repository](https://github.com/pachterlab/gget)
+- [gget Bioinformatics paper](https://doi.org/10.1093/bioinformatics/btac836)

package/src/harness_context/skills/ecc/scientific-thinking-literature-review/LICENSE.ecc

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Affaan Mustafa
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/src/harness_context/skills/ecc/scientific-thinking-literature-review/SKILL.md

@@ -0,0 +1,193 @@
+---
+name: literature-review
+description: Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging. Use when the task is to find, screen, synthesize, and cite a body of academic or technical literature.
+metadata:
+  origin: community
+---
+
+# Literature Review
+
+Use this skill when the task is to find, screen, synthesize, and cite a body of
+academic or technical literature.
+
+## When to Use
+
+- Building a systematic, scoping, or narrative literature review.
+- Synthesizing the state of the art for a research question.
+- Finding gaps, contradictions, or future-work directions.
+- Preparing citation-backed background sections for papers or reports.
+- Comparing evidence across peer-reviewed papers, preprints, patents, and
+  technical reports.
+
+## Review Types
+
+- **Narrative review**: broad synthesis; useful for orientation.
+- **Scoping review**: maps concepts, methods, and evidence gaps.
+- **Systematic review**: predefined protocol, reproducible search, explicit
+  screening and exclusion.
+- **Meta-analysis**: systematic review plus quantitative effect aggregation.
+
+Ask the user which level of rigor is needed. If unspecified, default to a
+scoping review for exploratory work and a systematic review for publication or
+clinical claims.
+
+## Workflow
+
+### 1. Define the Question
+
+Convert the prompt into a searchable research question.
+
+For clinical or biomedical work, use PICO:
+
+- Population
+- Intervention or exposure
+- Comparator
+- Outcome
+
+For technical work, use:
+
+- system or domain
+- method or intervention
+- comparison baseline
+- evaluation metric
+
+### 2. Plan the Search
+
+Create a search protocol before collecting sources:
+
+- databases to search
+- date range
+- languages
+- publication types
+- inclusion criteria
+- exclusion criteria
+- exact search strings
+
+Minimum useful database set:
+
+- PubMed for biomedical and life-sciences literature.
+- arXiv for CS, math, physics, quantitative biology, and preprints.
+- Semantic Scholar or Crossref for broad academic discovery.
+- Domain-specific sources when relevant, such as clinical-trial registries,
+  patent databases, standards bodies, or official technical docs.
+
+### 3. Search and Log Evidence
+
+Keep a search log that makes the review reproducible:
+
+```markdown
+| Database | Date searched | Query | Filters | Results | Export |
+| --- | --- | --- | --- | ---: | --- |
+| PubMed | 2026-05-11 | `("CRISPR"[tiab] OR "Cas9"[tiab]) AND "sickle cell"[tiab]` | 2020:2026, English | 86 | PMID list |
+| arXiv | 2026-05-11 | `CRISPR sickle cell gene editing` | q-bio, 2020:2026 | 9 | BibTeX |
+```
+
+Save raw IDs, URLs, DOIs, abstracts, and notes separately from the final prose.
+
+### 4. Deduplicate
+
+Deduplicate in this order:
+
+1. DOI
+2. PMID or arXiv ID
+3. exact title
+4. normalized title plus first author and year
+
+Record how many duplicates were removed.
+
+### 5. Screen Sources
+
+Screen in stages:
+
+1. title
+2. abstract
+3. full text
+
+For systematic work, record exclusion reasons:
+
+- wrong population
+- wrong intervention
+- wrong outcome
+- not primary research
+- duplicate
+- unavailable full text
+- outside date range
+
+### 6. Extract Data
+
+Use a structured extraction table:
+
+```markdown
+| Study | Design | Population/Data | Method | Comparator | Outcome | Key finding | Limitations |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| Author Year | RCT/cohort/review/etc. | sample or corpus | method | baseline | measured outcome | result | caveat |
+```
+
+For technical papers, include dataset, benchmark, metric, baseline, and
+reproducibility notes.
+
+### 7. Synthesize
+
+Group evidence by theme rather than summarizing papers one by one.
+
+Useful synthesis lenses:
+
+- strongest evidence
+- conflicting evidence
+- methodological weaknesses
+- population or dataset limits
+- recency and replication
+- practical implications
+- unanswered questions
+
+Separate claims by confidence:
+
+- **High confidence**: replicated, high-quality evidence across sources.
+- **Medium confidence**: plausible but limited by sample, method, or recency.
+- **Low confidence**: early, speculative, single-source, or weakly measured.
+
+### 8. Verify Citations
+
+Before finalizing:
+
+- verify DOI, PMID, arXiv ID, or official URL
+- check author names and publication year
+- do not cite a paper for a claim it does not make
+- mark preprints as preprints
+- distinguish reviews from primary evidence
+
+## Output Template
+
+```markdown
+# Literature Review: <Topic>
+
+Generated: <date>
+Review type: <narrative | scoping | systematic | meta-analysis>
+Search window: <dates>
+Databases: <list>
+
+## Research Question
+
+## Search Strategy
+
+## Inclusion and Exclusion Criteria
+
+## Evidence Summary
+
+## Thematic Synthesis
+
+## Gaps and Limitations
+
+## References
+
+## Search Log
+```
+
+## Pitfalls
+
+- Do not treat search snippets as evidence.
+- Do not mix preprints, reviews, and primary studies without labeling them.
+- Do not omit negative or conflicting findings.
+- Do not claim systematic-review rigor without a reproducible protocol.
+- Do not use a single database for a broad claim unless the scope is explicitly
+  limited to that database.

package/src/harness_context/skills/ecc/scientific-thinking-scholar-evaluation/LICENSE.ecc

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Affaan Mustafa
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.