@wentorai/research-plugins 1.1.0 → 1.2.0

package/skills/domains/cs/llm-aiops-guide/SKILL.md

@@ -0,0 +1,70 @@
+---
+name: llm-aiops-guide
+description: "Papers on LLMs for IT operations and AIOps research"
+metadata:
+  openclaw:
+    emoji: "🖥️"
+    category: "domains"
+    subcategory: "cs"
+    keywords: ["AIOps", "LLM operations", "IT automation", "log analysis", "incident management", "DevOps AI"]
+    source: "https://github.com/Jun-jie-Huang/awesome-LLM-AIOps"
+---
+
+# LLM for AIOps Guide
+
+## Overview
+
+A curated collection of research on applying LLMs to IT Operations (AIOps) — log analysis, anomaly detection, incident management, root cause analysis, and automated remediation. Tracks how foundation models are transforming traditional rule-based operations tooling into intelligent, adaptive systems. Relevant for CS researchers at the intersection of systems, NLP, and operations.
+
+## Research Areas
+
+```
+LLM for AIOps
+├── Log Analysis
+│   ├── Log parsing (template extraction)
+│   ├── Anomaly detection (from log sequences)
+│   ├── Log summarization
+│   └── Root cause from logs
+├── Incident Management
+│   ├── Incident triage and routing
+│   ├── Severity classification
+│   ├── Similar incident retrieval
+│   └── Resolution recommendation
+├── Root Cause Analysis
+│   ├── Topology-aware diagnosis
+│   ├── Multi-signal correlation
+│   └── Causal inference
+├── Monitoring & Alerting
+│   ├── Metric anomaly detection
+│   ├── Alert correlation
+│   ├── Noise reduction
+│   └── Capacity planning
+└── Automated Remediation
+    ├── Runbook generation
+    ├── Script generation
+    ├── Self-healing systems
+    └── Change impact analysis
+```
+
+## Key Papers
+
+| Paper | Year | Focus |
+|-------|------|-------|
+| LogPPT | 2023 | Few-shot log parsing with prompt tuning |
+| OpsEval | 2024 | Benchmark for evaluating LLMs in AIOps |
+| D-Bot | 2024 | LLM-based database diagnosis |
+| RCAgent | 2024 | Agent for root cause analysis |
+| LogAgent | 2024 | Autonomous log analysis agent |
+
+## Use Cases
+
+1. **Literature tracking**: Follow LLM-AIOps research evolution
+2. **System design**: Learn intelligent operations patterns
+3. **Benchmark comparison**: Evaluate AIOps approaches
+4. **Research planning**: Identify under-explored AIOps problems
+5. **Industry applications**: Bridge research to production AIOps
+
+## References
+
+- [awesome-LLM-AIOps](https://github.com/Jun-jie-Huang/awesome-LLM-AIOps)
+- [OpsEval Benchmark](https://arxiv.org/abs/2310.07637)

package/skills/domains/cs/software-heritage-api/SKILL.md

@@ -0,0 +1,200 @@
+---
+name: software-heritage-api
+description: "Archive and retrieve source code history via Software Heritage API"
+metadata:
+  openclaw:
+    emoji: "💾"
+    category: "domains"
+    subcategory: "cs"
+    keywords: ["Software Heritage", "code archive", "source code preservation", "SWHID", "code provenance", "open source"]
+    source: "https://www.softwareheritage.org/"
+---
+
+# Software Heritage API
+
+## Overview
+
+Software Heritage is the universal archive of software source code, preserving 18B+ source files from 280M+ software origins (GitHub, GitLab, Bitbucket, CRAN, PyPI, Debian, etc.). Each artifact receives a persistent SWHID (SoftWare Heritage IDentifier) for reliable citation in research. The API enables code search, provenance tracking, and historical analysis. Free, no authentication for read access.
+
+## API Endpoints
+
+### Base URL
+
+```
+https://archive.softwareheritage.org/api/1
+```
+
+### Search Origins (Repositories)
+
+```bash
+# Search for repositories
+curl "https://archive.softwareheritage.org/api/1/origin/search/scikit-learn/?limit=10"
+
+# Get origin metadata
+curl "https://archive.softwareheritage.org/api/1/origin/https://github.com/scikit-learn/scikit-learn/get/"
+
+# List visits (snapshots) of an origin
+curl "https://archive.softwareheritage.org/api/1/origin/https://github.com/scikit-learn/scikit-learn/visits/"
+```
+
+### Retrieve Content
+
+```bash
+# Get a specific file by its SHA1 hash
+curl "https://archive.softwareheritage.org/api/1/content/sha1:adc83b19e793491b1c6ea0fd8b46cd9f32e592fc/"
+
+# Get raw file content
+curl "https://archive.softwareheritage.org/api/1/content/sha1:adc83b19e793491b1c6ea0fd8b46cd9f32e592fc/raw/"
+
+# Get directory listing
+curl "https://archive.softwareheritage.org/api/1/directory/{sha1_git}/"
+```
+
+### Resolve SWHIDs
+
+```bash
+# Resolve a SWHID to its object
+curl "https://archive.softwareheritage.org/api/1/resolve/swh:1:cnt:adc83b19e793491b1c6ea0fd8b46cd9f32e592fc/"
+
+# Get snapshot
+curl "https://archive.softwareheritage.org/api/1/snapshot/{sha1_git}/"
+
+# Get revision (commit)
+curl "https://archive.softwareheritage.org/api/1/revision/{sha1_git}/"
+```
+
+### Save Code Now
+
+```bash
+# Request archival of a repository
+curl -X POST "https://archive.softwareheritage.org/api/1/origin/save/git/url/https://github.com/user/repo/"
+```
+
+## SWHID Format
+
+SoftWare Heritage persistent IDentifiers:
+
+```
+swh:1:{type}:{hash}
+
+Types:
+  cnt  → Content (file)
+  dir  → Directory
+  rev  → Revision (commit)
+  rel  → Release (tag)
+  snp  → Snapshot
+
+Examples:
+  swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2  (file)
+  swh:1:rev:309cf2674ee7a0749978cf8265ab91a60aea0f7d  (commit)
+  swh:1:snp:c7c108084bc0bf3d81436bf980b46e98571c7b17  (snapshot)
+
+With qualifiers:
+  swh:1:cnt:{hash};origin=https://github.com/user/repo;visit=swh:1:snp:{hash};path=/src/main.py
+```
+
+## Python Usage
+
+```python
+import requests
+import time
+
+BASE_URL = "https://archive.softwareheritage.org/api/1"
+
+
+def search_origins(query: str, limit: int = 10) -> list:
+    """Search Software Heritage for archived repositories."""
+    resp = requests.get(
+        f"{BASE_URL}/origin/search/{query}/",
+        params={"limit": limit},
+        timeout=30,
+    )
+    resp.raise_for_status()
+    return [
+        {
+            "url": o.get("url"),
+            "has_visits": o.get("has_visits"),
+        }
+        for o in resp.json()
+    ]
+
+
+def get_origin_visits(origin_url: str) -> list:
+    """Get archival snapshots for a repository."""
+    resp = requests.get(
+        f"{BASE_URL}/origin/{origin_url}/visits/",
+        timeout=30,
+    )
+    resp.raise_for_status()
+    return [
+        {
+            "date": v.get("date"),
+            "status": v.get("status"),
+            "snapshot": v.get("snapshot"),
+            "type": v.get("type"),
+        }
+        for v in resp.json()
+    ]
+
+
+def get_directory(sha1_git: str) -> list:
+    """List files in an archived directory."""
+    resp = requests.get(
+        f"{BASE_URL}/directory/{sha1_git}/",
+        timeout=30,
+    )
+    resp.raise_for_status()
+    return [
+        {
+            "name": entry.get("name"),
+            "type": entry.get("type"),
+            "target": entry.get("target"),
+        }
+        for entry in resp.json()
+    ]
+
+
+def save_code_now(repo_url: str) -> dict:
+    """Request Software Heritage to archive a repository."""
+    resp = requests.post(
+        f"{BASE_URL}/origin/save/git/url/{repo_url}/",
+        timeout=30,
+    )
+    resp.raise_for_status()
+    return resp.json()
+
+
+# Example: find archived ML frameworks
+origins = search_origins("pytorch", limit=5)
+for o in origins:
+    print(f"Archived: {o['url']}")
+
+# Example: get snapshot history
+visits = get_origin_visits("https://github.com/pytorch/pytorch")
+for v in visits[:5]:
+    print(f"[{v['date'][:10]}] {v['status']} — {v['type']}")
+
+# Example: request archival
+# result = save_code_now("https://github.com/my-org/my-research-code")
+# print(f"Save request: {result['save_request_status']}")
+```
+
+## Use Cases
+
+1. **Code citation**: Cite specific code versions in papers using SWHIDs
+2. **Reproducibility**: Archive the exact code used in experiments
+3. **Provenance tracking**: Trace code evolution and authorship
+4. **Software archaeology**: Study historical codebases
+5. **Compliance**: Ensure open-source license compliance through archival
+
+## Rate Limits
+
+- Unauthenticated: 120 requests/hour
+- Authenticated (free token): 1200 requests/hour
+
+## References
+
+- [Software Heritage](https://www.softwareheritage.org/)
+- [API Documentation](https://archive.softwareheritage.org/api/)
+- [SWHID Specification](https://docs.softwareheritage.org/devel/swh-model/persistent-identifiers.html)
+- Di Cosmo, R. & Zacchiroli, S. (2017). "Software Heritage: Why and How to Preserve Software Source Code." *iPRES 2017*.

package/skills/domains/economics/nber-working-papers-api/SKILL.md

@@ -0,0 +1,177 @@
+---
+name: nber-working-papers-api
+description: "Access NBER working papers and economic research datasets"
+metadata:
+  openclaw:
+    emoji: "📈"
+    category: "domains"
+    subcategory: "economics"
+    keywords: ["NBER", "working papers", "economics research", "macroeconomics", "economic policy", "recession dating"]
+    source: "https://www.nber.org/"
+---
+
+# NBER Working Papers and Data API
+
+## Overview
+
+The National Bureau of Economic Research (NBER) is the leading U.S. economics research organization, publishing 1,200+ working papers annually by top economists. NBER papers are among the most cited in economics. The website provides structured access to working papers, researcher profiles, and macroeconomic datasets. Free metadata access; some full text requires subscription.
+
+## Working Papers Access
+
+### RSS/Atom Feeds
+
+```bash
+# Latest working papers feed
+curl "https://www.nber.org/papers.rss"
+
+# Papers by program
+curl "https://www.nber.org/programs/ef/papers.rss"  # Economic Fluctuations
+curl "https://www.nber.org/programs/ls/papers.rss"  # Labor Studies
+curl "https://www.nber.org/programs/io/papers.rss"  # Industrial Organization
+```
+
+### Working Paper Search
+
+```bash
+# Search via NBER website (HTML scraping needed)
+curl "https://www.nber.org/api/v1/working_page_listing/contentType/working_paper/?page=1&perPage=20&q=inflation+expectations"
+
+# Get specific paper metadata
+curl "https://www.nber.org/api/v1/working_page_listing/contentType/working_paper/?page=1&perPage=1&q=w28104"
+```
+
+### NBER Data Portal
+
+```bash
+# Macroeconomic history data
+# Available at: https://data.nber.org/
+
+# Business cycle dates
+curl "https://data.nber.org/data/cycles/business_cycle_dates.json"
+
+# CPS labor data extracts
+# https://data.nber.org/cps/
+```
+
+## NBER Programs
+
+| Code | Program | Focus |
+|------|---------|-------|
+| `ef` | Economic Fluctuations and Growth | Macro, business cycles |
+| `ls` | Labor Studies | Employment, wages |
+| `io` | Industrial Organization | Markets, competition |
+| `pe` | Public Economics | Taxation, spending |
+| `he` | Health Economics | Healthcare markets |
+| `de` | Development Economics | Developing countries |
+| `if` | International Finance | Exchange rates, capital flows |
+| `it` | International Trade | Trade policy |
+| `me` | Monetary Economics | Central banking |
+| `cf` | Corporate Finance | Firm finance |
+| `ap` | Asset Pricing | Financial markets |
+| `ed` | Education | Education economics |
+| `ag` | Aging | Demographics |
+| `ch` | Children | Child welfare |
+| `le` | Law and Economics | Legal institutions |
+| `env` | Environment and Energy | Environmental policy |
+| `pol` | Political Economy | Political institutions |
+
+## Python Usage
+
+```python
+import requests
+from xml.etree import ElementTree
+
+
+def get_latest_papers(program: str = None,
+                      count: int = 20) -> list:
+    """Get latest NBER working papers via RSS."""
+    if program:
+        url = f"https://www.nber.org/programs/{program}/papers.rss"
+    else:
+        url = "https://www.nber.org/papers.rss"
+
+    resp = requests.get(url, timeout=30)
+    resp.raise_for_status()
+
+    root = ElementTree.fromstring(resp.content)
+    papers = []
+    for item in root.findall(".//item")[:count]:
+        papers.append({
+            "title": item.findtext("title", ""),
+            "link": item.findtext("link", ""),
+            "description": item.findtext("description", "")[:300],
+            "pub_date": item.findtext("pubDate", ""),
+        })
+    return papers
+
+
+def search_papers(query: str, page: int = 1,
+                  per_page: int = 20) -> list:
+    """Search NBER working papers."""
+    resp = requests.get(
+        "https://www.nber.org/api/v1/working_page_listing/"
+        "contentType/working_paper/",
+        params={"q": query, "page": page, "perPage": per_page},
+        timeout=30,
+    )
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for item in data.get("results", []):
+        results.append({
+            "title": item.get("title"),
+            "authors": item.get("authors", ""),
+            "number": item.get("wp_number", ""),
+            "date": item.get("date", ""),
+            "url": f"https://www.nber.org/papers/{item.get('wp_number', '')}",
+            "abstract": item.get("description", "")[:300],
+            "program": item.get("programs", []),
+        })
+    return results
+
+
+def get_business_cycle_dates() -> list:
+    """Get NBER official business cycle dates."""
+    resp = requests.get(
+        "https://data.nber.org/data/cycles/business_cycle_dates.json",
+        timeout=30,
+    )
+    resp.raise_for_status()
+    return resp.json()
+
+
+# Example: latest macro working papers
+papers = get_latest_papers(program="ef", count=5)
+for p in papers:
+    print(f"{p['title']}")
+    print(f"  {p['link']}")
+
+# Example: search for AI economics papers
+results = search_papers("artificial intelligence labor market")
+for r in results:
+    print(f"[{r['number']}] {r['title']}")
+    print(f"  Authors: {r['authors']}")
+
+# Example: recession dates
+cycles = get_business_cycle_dates()
+for c in cycles[-3:]:
+    print(f"Peak: {c.get('peak')} → Trough: {c.get('trough')}")
+```
+
+## Key Datasets
+
+| Dataset | Description |
+|---------|-------------|
+| Business Cycle Dates | Official US recession start/end dates |
+| CPS Extracts | Current Population Survey labor data |
+| Macrohistory Database | 150 years of macro indicators |
+| Patent Data | Patent citation and classification |
+| Trade Data | Bilateral trade statistics |
+
+## References
+
+- [NBER](https://www.nber.org/)
+- [NBER Working Papers](https://www.nber.org/papers)
+- [NBER Data](https://data.nber.org/)
+- [NBER Programs](https://www.nber.org/programs-projects/programs)

package/skills/domains/economics/repec-economics-api/SKILL.md

@@ -0,0 +1,188 @@
+---
+name: repec-economics-api
+description: "Access 4M+ economics working papers and articles via RePEc API"
+metadata:
+  openclaw:
+    emoji: "📊"
+    category: "domains"
+    subcategory: "economics"
+    keywords: ["RePEc", "economics papers", "working papers", "IDEAS", "EconPapers", "economic research"]
+    source: "https://ideas.repec.org/"
+---
+
+# RePEc (Research Papers in Economics) API
+
+## Overview
+
+RePEc is the largest decentralized bibliographic database for economics, indexing 4.4M+ items (working papers, journal articles, books, software) from 2,600+ publishers. It powers IDEAS and EconPapers — the two most-used economics paper search engines. The API provides metadata access and citation data. Free, no authentication required for basic access.
+
+## Access Methods
+
+### IDEAS Search API
+
+```bash
+# Search economics papers
+curl "https://ideas.repec.org/cgi-bin/htsearch?q=monetary+policy+inflation&cmd=Search&fmt=json"
+
+# Search specific types
+# Working papers
+curl "https://ideas.repec.org/cgi-bin/htsearch?q=fiscal+stimulus&ul=%%2Fp%%2F&fmt=json"
+
+# Journal articles
+curl "https://ideas.repec.org/cgi-bin/htsearch?q=trade+liberalization&ul=%%2Fa%%2F&fmt=json"
+```
+
+### RePEc Simple API
+
+```bash
+# Get metadata for a handle
+curl "https://api.repec.org/handle?handle=RePEc:nbr:nberwo:28104"
+
+# Author profile by short-id
+curl "https://api.repec.org/author?short-id=ppi1"
+
+# List items in a series
+curl "https://api.repec.org/series?series=RePEc:nbr:nberwo"
+```
+
+### CitEc Citation Data
+
+```bash
+# Get citations for a paper
+curl "https://citec.repec.org/api/plain/RePEc:nbr:nberwo:28104"
+
+# Response: list of citing paper handles
+```
+
+### LogEc Usage Statistics
+
+```bash
+# Get download/view statistics
+curl "https://logec.repec.org/scripts/paperstat.pf?h=RePEc:nbr:nberwo:28104"
+```
+
+## RePEc Handle Structure
+
+```
+RePEc:{archive}:{series}:{id}
+
+Examples:
+RePEc:nbr:nberwo:28104   → NBER Working Paper 28104
+RePEc:aea:aecrev:v:114:y:2024:i:1:p:1-25  → AER article
+RePEc:ecm:emetrp:v:92:y:2024:i:3:p:821-845 → Econometrica article
+RePEc:red:sed024:1234    → SED 2024 meeting paper
+```
+
+### Major Archives
+
+| Prefix | Publisher |
+|--------|-----------|
+| `nbr` | National Bureau of Economic Research (NBER) |
+| `aea` | American Economic Association |
+| `ecm` | Econometric Society |
+| `wbk` | World Bank |
+| `imf` | International Monetary Fund |
+| `fed` | Federal Reserve System |
+| `cpr` | Centre for Economic Policy Research (CEPR) |
+
+## Python Usage
+
+```python
+import requests
+
+IDEAS_URL = "https://ideas.repec.org/cgi-bin/htsearch"
+CITEC_URL = "https://citec.repec.org/api/plain"
+
+
+def search_economics(query: str, max_results: int = 20,
+                     paper_type: str = None) -> list:
+    """Search economics papers on IDEAS/RePEc."""
+    params = {
+        "q": query,
+        "cmd": "Search",
+        "fmt": "json",
+        "ps": max_results,
+    }
+    if paper_type == "working_papers":
+        params["ul"] = "%2Fp%2F"
+    elif paper_type == "articles":
+        params["ul"] = "%2Fa%2F"
+
+    resp = requests.get(IDEAS_URL, params=params, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for item in data.get("matches", []):
+        results.append({
+            "title": item.get("title", ""),
+            "url": item.get("url", ""),
+            "handle": item.get("handle", ""),
+            "authors": item.get("authors", ""),
+            "date": item.get("date", ""),
+            "abstract": item.get("abstract", "")[:300],
+        })
+    return results
+
+
+def get_citations(handle: str) -> list:
+    """Get papers citing a given RePEc handle."""
+    resp = requests.get(f"{CITEC_URL}/{handle}", timeout=30)
+    resp.raise_for_status()
+    citations = []
+    for line in resp.text.strip().split("\n"):
+        line = line.strip()
+        if line and line.startswith("RePEc:"):
+            citations.append(line)
+    return citations
+
+
+def search_working_papers(topic: str) -> list:
+    """Search specifically for working papers."""
+    return search_economics(topic, paper_type="working_papers")
+
+
+# Example: find monetary policy research
+papers = search_economics("central bank digital currency", max_results=10)
+for p in papers:
+    print(f"[{p['date']}] {p['title']}")
+    print(f"  {p['authors']}")
+
+# Example: citation analysis
+if papers and papers[0].get("handle"):
+    cites = get_citations(papers[0]["handle"])
+    print(f"\nCited by {len(cites)} papers")
+    for c in cites[:5]:
+        print(f"  {c}")
+```
+
+## Key Data Products
+
+| Product | URL | Description |
+|---------|-----|-------------|
+| IDEAS | ideas.repec.org | Full-text search engine |
+| EconPapers | econpapers.repec.org | Alternative search interface |
+| CitEc | citec.repec.org | Citation analysis |
+| LogEc | logec.repec.org | Usage statistics |
+| AuthorService | authors.repec.org | Author profiles and rankings |
+| CollEc | collec.repec.org | Institutional research output |
+
+## Rankings
+
+RePEc publishes monthly rankings of economists, institutions, and journals based on citations, downloads, and h-index:
+
+```bash
+# Top economists
+curl "https://ideas.repec.org/top/top.person.all.html"
+
+# Top institutions
+curl "https://ideas.repec.org/top/top.inst.all.html"
+```
+
+## References
+
+- [IDEAS/RePEc](https://ideas.repec.org/)
+- [EconPapers](https://econpapers.repec.org/)
+- [RePEc Author Service](https://authors.repec.org/)
+- [CitEc](https://citec.repec.org/)
+- Zimmermann, C. (2013). "Academic Rankings with RePEc." *Econometrics* 1(3): 249-264.