Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Access 4M+ economics working papers and articles via RePEc API
.claude/skills/brycewang-stanford-repec-economics-api/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 65% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 41% | 0% |
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.
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"
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"
bash# Get citations for a paper curl "https://citec.repec.org/api/plain/RePEc:nbr:nberwo:28104" # Response: list of citing paper handles
bash# Get download/view statistics curl "https://logec.repec.org/scripts/paperstat.pf?h=RePEc:nbr:nberwo:28104"
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| 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) |
pythonimport 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}")
| 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 |
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"
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 15,514 | 28,101 | +81% | 1 | 1 | 0% | 2,604 | 4,299 | +65% | 0 | 0 | — |
case-02 | pass→pass | 17,468 | 7,593 | -57% | 1 | 1 | 0% | 3,046 | 2,932 | -4% | 0 | 0 | — |
case-03 | fail→pass | 13,939 | 3,432 | -75% | 1 | 1 | 0% | 2,171 | 2,300 | +6% | 0 | 0 | — |
case-04 | fail→pass | 11,406 | 2,747 | -76% | 1 | 1 | 0% | 1,992 | 2,099 | +5% | 0 | 0 | — |
case-05 | fail→pass | 14,438 | 1,795 | -88% | 1 | 1 | 0% | 1,392 | 1,992 | +43% | 0 | 0 | — |
case-06 | fail→pass | 9,174 | 2,954 | -68% | 1 | 1 | 0% | 1,534 | 2,169 | +41% | 0 | 0 | — |
case-07 | fail→pass | 6,850 | 1,905 | -72% | 1 | 1 | 0% | 1,205 | 1,965 | +63% | 0 | 0 | — |
case-08 | pass→pass | 7,895 | 3,119 | -60% | 1 | 1 | 0% | 1,303 | 2,338 | +79% | 0 | 0 | — |
case-09 | pass→pass | 7,605 | 4,076 | -46% | 1 | 1 | 0% | 1,417 | 2,505 | +77% | 0 | 0 | — |
case-10 | pass→pass | 6,190 | 3,654 | -41% | 1 | 1 | 0% | 1,110 | 2,237 | +102% | 0 | 0 | — |
case-11 | fail→pass | 14,267 | 7,161 | -50% | 1 | 1 | 0% | 2,579 | 2,839 | +10% | 0 | 0 | — |
case-12 | pass→pass | 3,907 | 1,996 | -49% | 1 | 1 | 0% | 742 | 1,948 | +163% | 0 | 0 | — |
case-13 | fail→fail | 12,648 | 7,360 | -42% | 1 | 1 | 0% | 1,790 | 3,192 | +78% | 0 | 0 | — |
case-14 | pass→pass | 4,264 | 1,917 | -55% | 1 | 1 | 0% | 610 | 1,915 | +214% | 0 | 0 | — |
case-15 | pass→pass | 2,586 | 1,744 | -33% | 1 | 1 | 0% | 415 | 1,841 | +344% | 0 | 0 | — |
case-16 | fail→pass | 12,807 | 5,613 | -56% | 1 | 1 | 0% | 1,970 | 2,495 | +27% | 0 | 0 | — |
case-17 | pass→pass | 12,576 | 2,028 | -84% | 1 | 1 | 0% | 2,120 | 1,976 | -7% | 0 | 0 | — |
case-18 | fail→pass | 9,347 | 2,516 | -73% | 1 | 1 | 0% | 1,681 | 2,102 | +25% | 0 | 0 | — |
case-19 | fail→pass | 10,052 | 3,161 | -69% | 1 | 1 | 0% | 1,389 | 2,218 | +60% | 0 | 0 | — |
case-20 | pass→pass | 17,830 | 11,577 | -35% | 1 | 1 | 0% | 3,285 | 3,971 | +21% | 0 | 0 | — |
case-21 | pass→pass | 5,874 | 3,569 | -39% | 1 | 1 | 0% | 1,172 | 2,326 | +98% | 0 | 0 | — |
case-22 | pass→pass | 16,120 | 14,906 | -8% | 1 | 1 | 0% | 2,736 | 4,190 | +53% | 0 | 0 | — |
case-23 | pass→pass | 2,859 | 1,744 | -39% | 1 | 1 | 0% | 477 | 1,907 | +300% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +43 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.