{"full_name":"brycewang-stanford/Auto-Empirical-Research-Skills","owner":"brycewang-stanford","name":"Auto-Empirical-Research-Skills","shard":"1","url":"https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills","description":"🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文，并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.","homepage":"https://copaper.ai","topics":["academic-research","agent-skills","ai-agent","awesome-list","communication","economics","education","empirical-research","international-relations","political-science","psychology","public-administration","reproducible-research","skills-library","social-science"],"tag_pages":["agent-skills","ai-agent","awesome-list","communication","education"],"language":"Stata","license":"NOASSERTION","avatar":"https://avatars.githubusercontent.com/u/199214463?u=43b60729db2944f813d91af41064efe18e939070&v=4","created_at":"2026-04-03T06:31:20Z","pushed_at":"2026-11-09T13:27:49Z","metrics":{"stars":5028,"forks":578,"watchers":13,"issues":7,"prs":70,"releases":1,"issues_open":0,"issues_closed":7,"prs_open":0,"prs_closed":19,"prs_merged":51,"discussions":1},"growth":{"day":{"stars":10,"forks":1,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[4977,5000,5008,5009,5014,5018,5028],"forks":[574,575,576,576,576,577,578],"watchers":[null,13,13,13,13,13,13],"issues_open":[null,0,0,0,0,0,0],"prs_open":[null,0,0,0,0,0,0]},"boards":{},"same_owner":[],"issues":[],"discussions":[{"number":41,"title":"👋 欢迎 & 社区指南 / Welcome & Community Guide","comments":1,"category":"Announcements","created_at":"2026-07-02T10:49:52Z"}],"latest_release":{"name":"AERS v2026.07 — first tagged release","tag":"v2026.07","published_at":"2026-07-02T05:15:07Z","body":"## Highlights\n\n- **First tagged release.** Every gate is green: `make check` (validate + 183 unit tests + eval-harness + numeric benchmarks), validate-catalog, quality-evals, and OpenSSF Scorecard on `main`.\n- **Rigor double loop at 13 method families.** Each family closes taxonomy tag → eval scenario (does the agent avoid the method's known traps?) → deterministic numeric benchmark (does it recover the true effect?). New this cycle: heterogeneous treatment effects (CATE) and quantile treatment effects (QTE).\n- **Paper-WorkFlow flagship at 29/29 executable rigor gates**, now merged to its `main` with a drift-gated README badge — the credibility artifact is checked by CI, so it can never silently go stale ([RIGOR.md](https://github.com/brycewang-stanford/Paper-WorkFlow/blob/main/RIGOR.md)).\n- **1,150 vendored skills / 69 collections**, all license-audited, security-scanned, tracked in a machine-readable catalog with CI-enforced freshness, and importable as a single whole-repo router skill.\n- **Hardened weekly upstream syncs**: synced trees must pass the full gate before merge; this cycle both sync PRs were verified, patched (StatsPAI's SkillOpt execution-gate card restored), and merged.\n- **First-party plugin marketplace** (Python / R / Stata empirical-analysis plugins + guide) shipped in the previous cycle, now under a tagged version.\n\n## Known Follow-Ups\n\n- Ecosystem benchmark comparison (AERS vs econometrics agents on the shared benchmark suite) — [PLAN-2026-07 week 3](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/main/docs/PLAN-2026-07.md).\n- Decomposition (Oaxaca–Blinder) and shift-share (Bartik) method families (weeks 3–4).\n- GitHub Pages catalog site, README demo screenshots, five-language README consistency script (week 4).\n\n## Catalog\n\n- Top-level collections: **69**\n- `SKILL.md` files: **1150**\n- Cataloged agent tools: **335** ([`tools/CATALOG.md`](../tools/CATALOG.md))\n\n## Methodological rigor\n\n- Method families in the coverage map: **13** ([`RIGOR_COVERAGE.md`](RIGOR_COVERAGE.md))\n- Eval scenarios: **26** (138 rubric items, 122 auto-checkable) ([`../eval-harness/`](../eval-harness/README.md))\n- Benchmark tasks: **13** (70 gold checks, 58 required) ([`../benchmark/`](../benchmark/README.md))\n\n### Method families (skills tagged)\n\n- `iv`: 27\n- `rdd`: 25\n- `panel-fe`: 19\n- `staggered-did`: 17\n- `bayesian`: 13\n- `did`: 10\n- `event-study`: 10\n- `matching`: 10\n- `synthetic-control`: 10\n- `cate`: 8\n- `dml`: 8\n- `survival`: 3\n- `quantile`: 2\n\n### Eval scenarios by category\n\n- `causal-identification`: 14\n- `citation-hygiene`: 1\n- `reproducibility`: 2\n- `research-integrity`: 1\n- `runtime-safety`: 1\n- `statistical-validity`: 2\n- `writing-compliance`: 3\n- `writing-style`: 2\n\n## License buckets\n\n- AGPL-3.0: 1\n- Apache-2.0: 1\n- CC-BY-NC-4.0 (non-commercial): 1\n- CC-BY-SA-4.0: 1\n- CC-BY-SA-4.0 (repository default): 4\n- GPL-3.0: 1\n- MIT: 35\n- MIT Non-Commercial: 1\n- Mixed (per-skill; see folder): 2\n- UNKNOWN - check upstream: 22\n\n## Quality gates\n\n- `make check` — catalog/provenance/audit/eval freshness, repo hygiene,\n  Paper-WorkFlow gates, stdlib unit tests, eval-harness lint + graded smoke,\n  and the strict numeric benchmark (reference-gold drift fails the build).\n- External links and OpenSSF Scorecard run on their scheduled workflows.\n","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}