@wentorai/research-plugins 1.3.2 → 1.4.2

package/index.ts

@@ -1,16 +1,26 @@
 import type { OpenClawPluginApi } from "openclaw/plugin-sdk";
-import { createSemanticScholarTools } from "./src/tools/semantic-scholar.js";
 import { createOpenAlexTools } from "./src/tools/openalex.js";
 import { createCrossRefTools } from "./src/tools/crossref.js";
 import { createArxivTools } from "./src/tools/arxiv.js";
 import { createPubMedTools } from "./src/tools/pubmed.js";
 import { createUnpaywallTools } from "./src/tools/unpaywall.js";
+import { createEuropePmcTools } from "./src/tools/europe-pmc.js";
+import { createOpenCitationsTools } from "./src/tools/opencitations.js";
+import { createDoajTools } from "./src/tools/doaj.js";
+import { createDblpTools } from "./src/tools/dblp.js";
+import { createBiorxivTools } from "./src/tools/biorxiv.js";
+import { createOpenAireTools } from "./src/tools/openaire.js";
+import { createZenodoTools } from "./src/tools/zenodo.js";
+import { createOrcidTools } from "./src/tools/orcid.js";
+import { createInspireHepTools } from "./src/tools/inspire-hep.js";
+import { createHalTools } from "./src/tools/hal.js";
+import { createOsfPreprintsTools } from "./src/tools/osf-preprints.js";
+import { createDataCiteTools } from "./src/tools/datacite.js";
+import { createRorTools } from "./src/tools/ror.js";
+// ChemRxiv: REMOVED — blocked by Cloudflare WAF, returns HTML challenge instead of JSON
 
 export default function activate(api: OpenClawPluginApi) {
-  api.registerTool(
-    (ctx) => createSemanticScholarTools(ctx, api),
-    { names: ["get_paper", "get_citations"] },
-  );
+  // --- Existing tools ---
 
   api.registerTool(
     (ctx) => createOpenAlexTools(ctx, api),
@@ -36,4 +46,77 @@ export default function activate(api: OpenClawPluginApi) {
     (ctx) => createUnpaywallTools(ctx, api),
     { names: ["find_oa_version"] },
   );
+
+  // --- Phase 1: New free API tools ---
+
+  api.registerTool(
+    (ctx) => createEuropePmcTools(ctx, api),
+    { names: ["search_europe_pmc", "get_epmc_citations", "get_epmc_references"] },
+  );
+
+  api.registerTool(
+    (ctx) => createOpenCitationsTools(ctx, api),
+    { names: ["get_citations_open", "get_references_open", "get_citation_count"] },
+  );
+
+  api.registerTool(
+    (ctx) => createDoajTools(ctx, api),
+    { names: ["search_doaj"] },
+  );
+
+  api.registerTool(
+    (ctx) => createDblpTools(ctx, api),
+    { names: ["search_dblp", "search_dblp_author"] },
+  );
+
+  api.registerTool(
+    (ctx) => createBiorxivTools(ctx, api),
+    { names: ["search_biorxiv", "search_medrxiv", "get_preprint_by_doi"] },
+  );
+
+  api.registerTool(
+    (ctx) => createOpenAireTools(ctx, api),
+    { names: ["search_openaire"] },
+  );
+
+  // --- Phase 2: Domain-specific tools ---
+
+  api.registerTool(
+    (ctx) => createZenodoTools(ctx, api),
+    { names: ["search_zenodo", "get_zenodo_record"] },
+  );
+
+  api.registerTool(
+    (ctx) => createOrcidTools(ctx, api),
+    { names: ["search_orcid", "get_orcid_works"] },
+  );
+
+  api.registerTool(
+    (ctx) => createInspireHepTools(ctx, api),
+    { names: ["search_inspire", "get_inspire_paper"] },
+  );
+
+  api.registerTool(
+    (ctx) => createHalTools(ctx, api),
+    { names: ["search_hal"] },
+  );
+
+  api.registerTool(
+    (ctx) => createOsfPreprintsTools(ctx, api),
+    { names: ["search_osf_preprints"] },
+  );
+
+  // --- Phase 3: Infrastructure tools ---
+
+  api.registerTool(
+    (ctx) => createDataCiteTools(ctx, api),
+    { names: ["search_datacite", "resolve_datacite_doi"] },
+  );
+
+  api.registerTool(
+    (ctx) => createRorTools(ctx, api),
+    { names: ["search_ror"] },
+  );
+
+  // ChemRxiv: blocked by Cloudflare — moved to Layer 2 (Browser RPA)
 }

package/openclaw.plugin.json

@@ -1,8 +1,8 @@
 {
   "id": "research-plugins",
-  "version": "1.3.2",
+  "version": "1.4.0",
   "name": "Research Plugins",
-  "description": "432 academic research skills, 12 agent tools, 150 MCP configs (reference-only) & 6 curated lists for Research-Claw",
+  "description": "438 academic research skills, 34 agent tools across 18 API modules & 6 curated lists for Research-Claw",
   "skills": [
     "./skills/analysis",
     "./skills/domains",
@@ -14,15 +14,6 @@
   "configSchema": {
     "type": "object",
     "additionalProperties": false,
-    "properties": {
-      "semanticScholarApiKey": { "type": "string" }
-    }
-  },
-  "uiHints": {
-    "semanticScholarApiKey": {
-      "label": "Semantic Scholar API Key (optional)",
-      "help": "Get free key from semanticscholar.org for higher rate limits.",
-      "sensitive": true
-    }
+    "properties": {}
   }
 }

package/package.json

@@ -1,8 +1,8 @@
 {
   "name": "@wentorai/research-plugins",
-  "version": "1.3.2",
+  "version": "1.4.2",
   "type": "module",
-  "description": "432 academic research skills, 13 agent tools, 150 MCP configs (reference-only), and 6 curated lists for Research-Claw and AI agents",
+  "description": "438 academic research skills, 34 agent tools across 18 API modules, and 6 curated lists for Research-Claw and AI agents",
   "keywords": [
     "agent-skills",
     "claude",
@@ -17,7 +17,6 @@
   ],
   "files": [
     "skills/",
-    "mcp-configs/",
     "curated/",
     "src/",
     "index.ts",
@@ -27,8 +26,7 @@
   ],
   "scripts": {
     "validate": "node --experimental-strip-types scripts/validate.ts",
-    "catalog": "node --experimental-strip-types scripts/catalog.ts",
-    "sync-registry": "node --experimental-strip-types scripts/sync-registry.ts"
+    "catalog": "node --experimental-strip-types scripts/catalog.ts"
   },
   "engines": {
     "node": ">=22.6.0"

package/skills/analysis/statistics/SKILL.md

@@ -12,7 +12,7 @@ Select the skill matching the user's need, then `read` its SKILL.md.
 | [bayesian-statistics-guide](./bayesian-statistics-guide/SKILL.md) | Bayesian inference methods including prior selection, MCMC, and model comparison |
 | [data-anomaly-detection](./data-anomaly-detection/SKILL.md) | Detect anomalies and outliers in research data using statistical methods |
 | [hypothesis-testing-guide](./hypothesis-testing-guide/SKILL.md) | Statistical hypothesis testing, power analysis, and significance reporting |
-| [meta-analysis-guide](./meta-analysis-guide/SKILL.md) | Conduct systematic meta-analyses with effect size pooling and heterogeneity a... |
+| [meta-analysis-guide](./meta-analysis-guide/SKILL.md) | Conduct systematic meta-analyses with effect size pooling and heterogeneity |
 | [ml-experiment-tracker](./ml-experiment-tracker/SKILL.md) | Plan reproducible ML experiment runs with parameters and metrics tracking |
 | [modeling-strategy-guide](./modeling-strategy-guide/SKILL.md) | Strategic statistical modeling, experimentation, and causal inference |
 | [nonparametric-tests-guide](./nonparametric-tests-guide/SKILL.md) | Apply Mann-Whitney, Kruskal-Wallis, and other nonparametric methods |

package/skills/analysis/statistics/meta-analysis-guide/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: meta-analysis-guide
-description: "Conduct systematic meta-analyses with effect size pooling and heterogeneity a..."
+description: "Conduct systematic meta-analyses with effect size pooling and heterogeneity"
 metadata:
   openclaw:
     emoji: "⚖️"

package/skills/domains/ai-ml/SKILL.md

@@ -1,9 +1,9 @@
 ---
 name: ai-ml-skills
-description: "26 ai & machine learning skills. Trigger: ML experiments, model training, deep learning, NLP, computer vision. Design: covers frameworks, benchmarks, paper reproduction, and AI research workflows."
+description: "27 ai & machine learning skills. Trigger: ML experiments, model training, deep learning, NLP, computer vision. Design: covers frameworks, benchmarks, paper reproduction, and AI research workflows."
 ---
 
-# AI & Machine Learning — 26 Skills
+# AI & Machine Learning — 27 Skills
 
 Select the skill matching the user's need, then `read` its SKILL.md.
 
@@ -19,6 +19,7 @@ Select the skill matching the user's need, then `read` its SKILL.md.
 | [domain-adaptation-papers-guide](./domain-adaptation-papers-guide/SKILL.md) | Comprehensive collection of domain adaptation research papers |
 | [generative-ai-guide](./generative-ai-guide/SKILL.md) | Curated guide to generative AI covering LLMs and diffusion models |
 | [graph-learning-papers-guide](./graph-learning-papers-guide/SKILL.md) | Conference papers on graph neural networks and graph learning |
+| [huggingface-api](./huggingface-api/SKILL.md) | Search and discover ML models, datasets, and Spaces on Hugging Face |
 | [huggingface-inference-guide](./huggingface-inference-guide/SKILL.md) | Run NLP and CV model inference via Hugging Face free-tier API |
 | [keras-deep-learning](./keras-deep-learning/SKILL.md) | Build and debug deep learning models with Keras and TensorFlow backend |
 | [kolmogorov-arnold-networks-guide](./kolmogorov-arnold-networks-guide/SKILL.md) | Papers and tutorials on KAN learnable activation networks |

package/skills/domains/ai-ml/generative-ai-guide/SKILL.md

@@ -8,6 +8,7 @@ metadata:
   openclaw:
     category: "domains"
     subcategory: "ai-ml"
+    emoji: "🤖"
     keywords:
       - generative-ai
       - large-language-models

package/skills/domains/ai-ml/huggingface-api/SKILL.md

@@ -0,0 +1,251 @@
+---
+name: huggingface-api
+description: "Search and discover ML models, datasets, and Spaces on Hugging Face"
+metadata:
+  openclaw:
+    emoji: "🤗"
+    category: "domains"
+    subcategory: "ai-ml"
+    keywords: ["Hugging Face", "ML models", "datasets", "model hub", "transformers", "NLP", "computer vision"]
+    source: "https://huggingface.co/docs/hub/api"
+---
+
+# Hugging Face Hub API
+
+## Overview
+
+The Hugging Face Hub is the largest open-source ML ecosystem, hosting over 1 million models, 200,000+ datasets, and 400,000+ Spaces (demo apps). The Hub API at `https://huggingface.co/api` provides programmatic access to search, discover, and retrieve metadata for all public resources without authentication.
+
+For academic researchers, the Hub API enables systematic model selection for benchmarking, dataset discovery for experiments, tracking community adoption metrics (downloads, likes), and building reproducible ML pipelines that reference specific model revisions by SHA.
+
+## Authentication
+
+**Read endpoints require no authentication.** All search and metadata queries work without a token.
+
+For write operations (uploading models, creating repos), set a User Access Token:
+
+```bash
+export HF_TOKEN="hf_..."
+# Pass via header:
+curl -H "Authorization: Bearer $HF_TOKEN" https://huggingface.co/api/...
+```
+
+Generate tokens at: https://huggingface.co/settings/tokens
+
+## Core Endpoints
+
+### Search Models
+
+```
+GET https://huggingface.co/api/models?search={query}&limit={n}&sort={field}&direction={-1|1}
+```
+
+**Parameters**: `search` (query string), `limit` (max results), `sort` (field: `downloads`, `likes`, `lastModified`, `trending`), `direction` (-1 descending, 1 ascending), `filter` (pipeline tag like `text-classification`), `author` (org/user filter), `library` (e.g. `transformers`, `pytorch`)
+
+**Example** -- top 2 models for "bert" by downloads:
+
+```bash
+curl -s "https://huggingface.co/api/models?search=bert&limit=2&sort=downloads&direction=-1"
+```
+
+```json
+[
+  {
+    "id": "google-bert/bert-base-uncased",
+    "likes": 2587,
+    "downloads": 71053483,
+    "pipeline_tag": "fill-mask",
+    "library_name": "transformers",
+    "tags": ["transformers","pytorch","tf","jax","bert","fill-mask","en",
+             "dataset:bookcorpus","dataset:wikipedia","arxiv:1810.04805",
+             "license:apache-2.0"]
+  },
+  {
+    "id": "google-bert/bert-base-multilingual-uncased",
+    "likes": 153,
+    "downloads": 5017183,
+    "pipeline_tag": "fill-mask",
+    "library_name": "transformers"
+  }
+]
+```
+
+### Get Model Details
+
+```
+GET https://huggingface.co/api/models/{owner}/{model_name}
+```
+
+Returns full metadata including `config.architectures`, `cardData` (license, datasets, language), `siblings` (file listing), `sha` (exact revision), and `lastModified`.
+
+```bash
+curl -s "https://huggingface.co/api/models/google-bert/bert-base-uncased"
+```
+
+Key fields in response:
+
+```json
+{
+  "id": "google-bert/bert-base-uncased",
+  "sha": "86b5e0934494bd15c9632b12f734a8a67f723594",
+  "lastModified": "2024-02-19T11:06:12.000Z",
+  "downloads": 71053483,
+  "config": { "architectures": ["BertForMaskedLM"], "model_type": "bert" },
+  "cardData": { "language": "en", "license": "apache-2.0",
+                "datasets": ["bookcorpus","wikipedia"] }
+}
+```
+
+### Search Datasets
+
+```
+GET https://huggingface.co/api/datasets?search={query}&limit={n}
+```
+
+**Parameters**: `search`, `limit`, `sort`, `direction`, `author`, `filter` (task tag like `question-answering`)
+
+```bash
+curl -s "https://huggingface.co/api/datasets?search=squad&limit=2"
+```
+
+```json
+[
+  {
+    "id": "rajpurkar/squad_v2",
+    "likes": 242,
+    "downloads": 36017,
+    "description": "Stanford Question Answering Dataset (SQuAD)...",
+    "tags": ["task_categories:question-answering","language:en",
+             "license:cc-by-sa-4.0","size_categories:100K<n<1M",
+             "arxiv:1806.03822"]
+  }
+]
+```
+
+### Get Dataset Details
+
+```
+GET https://huggingface.co/api/datasets/{owner}/{dataset_name}
+```
+
+```bash
+curl -s "https://huggingface.co/api/datasets/rajpurkar/squad_v2"
+```
+
+Returns `cardData` with structured metadata (task categories, languages, license, size), `description`, `paperswithcode_id` for cross-referencing, and `tags` with arXiv paper IDs.
+
+### Search Spaces
+
+```
+GET https://huggingface.co/api/spaces?search={query}&limit={n}
+```
+
+```bash
+curl -s "https://huggingface.co/api/spaces?search=chatbot&limit=2"
+```
+
+```json
+[
+  {
+    "id": "21Hg/chatbot",
+    "likes": 5,
+    "sdk": "docker",
+    "tags": ["docker","streamlit","region:us"]
+  },
+  {
+    "id": "lmarena-ai/chatbot-arena",
+    "likes": 234,
+    "sdk": "static"
+  }
+]
+```
+
+## Advanced Filters
+
+Combine filters via query params to narrow results:
+
+```bash
+# PyTorch text-generation models with 1000+ likes
+curl -s "https://huggingface.co/api/models?filter=text-generation&library=pytorch&sort=likes&direction=-1&limit=5"
+
+# Datasets for NER tasks in Chinese
+curl -s "https://huggingface.co/api/datasets?filter=token-classification&language=zh&limit=10"
+
+# Gradio Spaces sorted by trending
+curl -s "https://huggingface.co/api/spaces?filter=gradio&sort=trending&direction=-1&limit=5"
+```
+
+## Rate Limits
+
+- **Unauthenticated**: generous but undocumented; suitable for interactive use and small scripts
+- **Authenticated**: higher limits with Bearer token
+- **Best practice**: add `limit` parameter to avoid fetching thousands of results; cache responses locally for batch analysis
+- No strict per-minute quota is published; if you receive HTTP 429, back off exponentially
+
+## Academic Use Cases
+
+1. **Model selection for benchmarks**: Search by pipeline tag (`text-classification`, `token-classification`, `summarization`) and sort by downloads to find community-validated baselines
+2. **Dataset discovery**: Filter by `task_categories`, `language`, and `size_categories` tags to find training data matching your experimental requirements
+3. **Reproducibility**: Pin model versions using the `sha` field from model details -- load exact revisions with `revision="86b5e093..."` in transformers
+4. **Citation tracking**: Extract `arxiv:` tags from model/dataset metadata to trace foundational papers
+5. **Ecosystem analysis**: Aggregate download/like counts across model families to study adoption trends in ML research
+
+## Code Examples
+
+### Python with requests
+
+```python
+import requests
+
+# Search for top text-classification models
+resp = requests.get("https://huggingface.co/api/models", params={
+    "filter": "text-classification",
+    "sort": "downloads",
+    "direction": -1,
+    "limit": 10
+})
+models = resp.json()
+for m in models:
+    print(f"{m['id']:50s}  downloads={m.get('downloads',0):>12,}")
+
+# Get specific model metadata
+detail = requests.get("https://huggingface.co/api/models/google-bert/bert-base-uncased").json()
+print(f"SHA: {detail['sha']}")
+print(f"License: {detail['cardData'].get('license')}")
+```
+
+### Python with huggingface_hub library
+
+```python
+from huggingface_hub import HfApi
+
+api = HfApi()
+
+# Search models (returns ModelInfo objects)
+models = api.list_models(search="bert", sort="downloads", direction=-1, limit=5)
+for m in models:
+    print(f"{m.id}  downloads={m.downloads}")
+
+# Get full model info
+info = api.model_info("google-bert/bert-base-uncased")
+print(f"Pipeline: {info.pipeline_tag}, SHA: {info.sha}")
+
+# Search datasets
+datasets = api.list_datasets(search="squad", sort="downloads", direction=-1, limit=5)
+for d in datasets:
+    print(f"{d.id}  downloads={d.downloads}")
+
+# List Spaces
+spaces = api.list_spaces(search="chatbot", limit=5)
+for s in spaces:
+    print(f"{s.id}  sdk={s.sdk}")
+```
+
+## References
+
+- Hub API documentation: https://huggingface.co/docs/hub/api
+- huggingface_hub Python library: https://huggingface.co/docs/huggingface_hub/
+- Model Hub: https://huggingface.co/models
+- Dataset Hub: https://huggingface.co/datasets
+- Spaces: https://huggingface.co/spaces
+- OpenAPI spec: https://huggingface.co/docs/hub/api#openapi

package/skills/domains/biomedical/SKILL.md

@@ -1,20 +1,25 @@
 ---
 name: biomedical-skills
-description: "17 biomedical research skills. Trigger: medical research, clinical trials, genomics, bioinformatics. Design: domain databases, wet-lab/dry-lab methods, and ethical compliance guides."
+description: "24 biomedical research skills. Trigger: medical research, clinical trials, genomics, bioinformatics. Design: domain databases, wet-lab/dry-lab methods, and ethical compliance guides."
 ---
 
-# Biomedical Research — 17 Skills
+# Biomedical Research — 24 Skills
 
 Select the skill matching the user's need, then `read` its SKILL.md.
 
 | Skill | Description |
 |-------|-------------|
+| [alphafold-api](./alphafold-api/SKILL.md) | Query AlphaFold protein structure predictions by UniProt accession |
 | [bioagents-guide](./bioagents-guide/SKILL.md) | AI scientist framework for autonomous biological research workflows |
+| [biothings-api](./biothings-api/SKILL.md) | Query gene, variant, and drug annotations via BioThings APIs |
 | [clawbio-guide](./clawbio-guide/SKILL.md) | OpenClaw bioinformatics skill library for genomics pipelines |
 | [clinical-dialogue-agents-guide](./clinical-dialogue-agents-guide/SKILL.md) | Papers on AI agents for clinical dialogue and medical QA |
 | [clinical-research-guide](./clinical-research-guide/SKILL.md) | Design clinical studies and report using CONSORT, STROBE guidelines |
 | [clinicaltrials-api](./clinicaltrials-api/SKILL.md) | Clinical trial registry database search API |
+| [clinicaltrials-api-v2](./clinicaltrials-api-v2/SKILL.md) | Search and analyze clinical trials via the ClinicalTrials.gov v2 API |
 | [ena-sequence-api](./ena-sequence-api/SKILL.md) | Access nucleotide sequence data from the European Nucleotide Archive |
+| [enrichr-api](./enrichr-api/SKILL.md) | Perform gene set enrichment analysis using the Enrichr API |
+| [ensembl-rest-api](./ensembl-rest-api/SKILL.md) | Query gene, sequence, and variant data via the Ensembl REST API |
 | [epidemiology-guide](./epidemiology-guide/SKILL.md) | Epidemiological study designs, measures of association, and public health ana... |
 | [genomas-guide](./genomas-guide/SKILL.md) | Automate gene expression analysis with the GenoMAS multi-agent system |
 | [genomics-analysis-guide](./genomics-analysis-guide/SKILL.md) | Workflows for RNA-seq, GWAS, and variant calling in genomic research |
@@ -22,7 +27,9 @@ Select the skill matching the user's need, then `read` its SKILL.md.
 | [med-researcher-guide](./med-researcher-guide/SKILL.md) | Multi-agent system for biomedical literature review and synthesis |
 | [med-researcher-r1-guide](./med-researcher-r1-guide/SKILL.md) | Medical deep research agent with reasoning chain analysis |
 | [medgeclaw-guide](./medgeclaw-guide/SKILL.md) | AI research assistant for biomedicine, RNA-seq, and drug discovery |
+| [medical-data-api](./medical-data-api/SKILL.md) | Access FDA drug data and WHO global health statistics for research |
 | [medical-imaging-guide](./medical-imaging-guide/SKILL.md) | Medical image analysis with deep learning for research applications |
 | [ncbi-blast-api](./ncbi-blast-api/SKILL.md) | Run sequence similarity searches via the NCBI BLAST REST API |
 | [ncbi-datasets-api](./ncbi-datasets-api/SKILL.md) | Access genomes, genes, and taxonomy data via NCBI Datasets v2 API |
+| [pdb-structure-api](./pdb-structure-api/SKILL.md) | Search and retrieve 3D protein structures from the RCSB Protein Data Bank |
 | [quickgo-api](./quickgo-api/SKILL.md) | Browse and search Gene Ontology annotations via the QuickGO API |