data-collection
安装方式
先用 Prompt 核对来源,也可切换到安装命令或下载可用的安装包。
用 AI 助手安装
复制提示词,让助手先核对固定版本和依赖。
查看 Prompt收起 Prompt
先检查当前 Agent 是否已安装 SkillPI Skill Finder。如果尚未安装,请按官方仓库的说明安装并启用:https://github.com/Findskills/skillpi。然后使用 Skill Finder 打开此 SkillPI 详情页并定位 "data-collection":https://skillpi.com/zh/skills/deepskill-02e1b5fed623d5f789938434b964fc8e890aff293dc056e50fbc1e8ec894a702。安装前核对上游来源和版本:https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/60-regisely-superpapers/skills/data-collection/SKILL.md。来源不一致时停止并说明差异。核对通过后,用 Skill Finder 安装目标 Skill,并报告安装路径和来源版本。
此命令从 GitHub 来源仓库获取指定技能。运行前请先查看源文件。
npx skills add https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/60-regisely-superpapers/skills/data-collection --skill data-collection来源与配置
查看 GitHub 源码brycewang-stanford/Auto-Empirical-Research-Skills固定提交 bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba
配置方式待核实
请查看原始来源中的适用工具、依赖和权限要求。
安装实测待补充
本条目面向资料查询与搜索场景,提供“data-collection”技能的目录入口。公开标签:learning、数据源、API、爬虫。请通过固定上游版本核对实际功能、依赖与权限;此页为 Skillπ 独立编写的用途介绍和原站链接,不代表运行安全保证。原文与附件依各自许可开放。
文件浏览
--- name: data-collection description: Use when collecting data for a research project, downloading time series, building a dataset, accessing economic or social data APIs, or scraping data from a non-API source. Handles source discovery, respectful collection, local caching, and manifest documentation. --- # Data Collection ## Overview This skill guides data collection from the research question to a versionable artifact in `data/raw/`. It is field-agnostic and open-ended about sources — the `references/common-sources.md` file is a starting point, not a boundary. For any research question, the skill uses web search to find appropriate sources beyond the common list. ## When to Use - "I need data on X" - "Download the unemployment series" - "Build a dataset of country-level GDP" - "Scrape this website for paper data" - "Where can I get data about Y?" - Any new project's collection phase ## Mandatory Steps 1. **Identify data needs from the research question.** Variables, units (country, firm, individual, pixel), frequency, period, geography, and any necessary keys for merging across sources. 2. **Find appropriate sources.** Start with `references/common-sources.md`. If the user's needs are not covered there, search the web for the relevant source. Never invent a URL or API endpoint from memory. 3. **Prefer APIs over scraping.** APIs are versioned, documented, and legal. Scraping is the last resort when no API is available. 4. **When scraping is necessary, be respectful:** - Check and honor `robots.txt` - Rate limit — minimum one request per second, often slower - Exponential backoff on errors (e.g., 1s, 2s, 4s, 8s, cap at 60s) - Identifiable user agent with contact information - Cache aggressively — never re-download unnecessarily - Never scrape a source that explicitly prohibits automated access in its terms of service 5. **Save raw data in `data/raw/`** in a versionable format. Parquet is preferred for tabular data; CSV is acceptable for small datasets. Never edit raw files by hand. 6. **Document every dataset in `data/manifest.md`** following the format from `replication-driven-research`: name, source, URL or API endpoint, collection date, variables used, frequency, period, license or usage notes. 7. **Cache locally.** Check `data/raw/` before fetching. Only invoke the network if the file is missing or the user has explicitly requested a refresh. ## Source Discovery Process Follow this order when looking for a data source: 1. Check `references/common-sources.md` for known sources in the relevant domain. 2. Web-search for `"<topic>" open data API` or `"<topic>" dataset download`. 3. Check open science repositories: Harvard Dataverse, Zenodo, Open Science Framework, figshare. 4. Check the topic's primary institutional source (central bank, statistical agency, international organization, regulatory body). 5. If none of the above work, escalate to the user — manual acquisition may be required (e.g., contacting authors, subscribing to a database). ## Anti-Patterns - Scraping a source whose `robots.txt` prohibits it - Hitting an API without rate limiting - Re-downloading data that already exists in `data/raw/` - Raw data without a manifest entry - Editing a raw data file manually to "fix" issues - Collecting data without specifying the period and frequency upfront - Trusting a URL invented from memory - Merging datasets without documenting the merge keys ## Verification Before Completion - [ ] Data saved under `data/raw/` in a versionable format (parquet preferred) - [ ] Manifest entry added for every new dataset - [ ] Collection logic lives in a script under `code/`, not an interactive session - [ ] Source license checked and recorded in the manifest - [ ] Cache honored — no unnecessary re-downloads - [ ] Rate limiting applied for scraping - [ ] Raw files are untouched after initial download
版本历史
-
v2026.07
GitHub ↗
原版更新说明
## Highlights - **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`. - **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). - **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)). - **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. - **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. - **First-party plugin marketplace** (Python / R / Stata empirical-analysis plugins + guide) shipped in the previous cycle, now under a tagged version. ## Known Follow-Ups - 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). - Decomposition (Oaxaca–Blinder) and shift-share (Bartik) method families (weeks 3–4). - GitHub Pages catalog site, README demo screenshots, five-language README consistency script (week 4). ## Catalog - Top-level collections: **69** - `SKILL.md` files: **1150** - Cataloged agent tools: **335** ([`tools/CATALOG.md`](../tools/CATALOG.md)) ## Methodological rigor - Method families in the coverage map: **13** ([`RIGOR_COVERAGE.md`](RIGOR_COVERAGE.md)) - Eval scenarios: **26** (138 rubric items, 122 auto-checkable) ([`../eval-harness/`](../eval-harness/README.md)) - Benchmark tasks: **13** (70 gold checks, 58 required) ([`../benchmark/`](../benchmark/README.md)) ### Method families (skills tagged) - `iv`: 27 - `rdd`: 25 - `panel-fe`: 19 - `staggered-did`: 17 - `bayesian`: 13 - `did`: 10 - `event-study`: 10 - `matching`: 10 - `synthetic-control`: 10 - `cate`: 8 - `dml`: 8 - `survival`: 3 - `quantile`: 2 ### Eval scenarios by category - `causal-identification`: 14 - `citation-hygiene`: 1 - `reproducibility`: 2 - `research-integrity`: 1 - `runtime-safety`: 1 - `statistical-validity`: 2 - `writing-compliance`: 3 - `writing-style`: 2 ## License buckets - AGPL-3.0: 1 - Apache-2.0: 1 - CC-BY-NC-4.0 (non-commercial): 1 - CC-BY-SA-4.0: 1 - CC-BY-SA-4.0 (repository default): 4 - GPL-3.0: 1 - MIT: 35 - MIT Non-Commercial: 1 - Mixed (per-skill; see folder): 2 - UNKNOWN - check upstream: 22 ## Quality gates - `make check` — catalog/provenance/audit/eval freshness, repo hygiene, Paper-WorkFlow gates, stdlib unit tests, eval-harness lint + graded smoke, and the strict numeric benchmark (reference-gold drift fails the build). - External links and OpenSSF Scorecard run on their scheduled workflows.
当前收录版本
0.0.1
质量评测
满分 100。前四项来自 DeepSkill 收录的质量报告。
评分依据
覆盖研究项目数据收集全流程,从需求识别到数据落地,实用价值高
评分依据
触发词覆盖全面,包括自然语言查询与具体任务指令
评分依据
Mandatory Steps 与 Source Discovery Process 逻辑清晰
评分依据
明确优先使用 API,次选合规 scraping,降低法律风险
计算方式
取前四项原始分值的算术平均,四舍五入取整。可通过收录报告核对各项评分与说明,运行记录需单独查证。
权限与使用前检查
根据当前主文档自动整理,命中内容可能是示例或防护说明;不是实际权限声明,也未覆盖附件、外部依赖或运行行为。
未从主文档识别到上述常见操作,不能据此判断无需权限或没有风险。
安全评级与访问范围
risk · 静态证据核验,不代表运行安全保证。
使用前请由宿主核对并授权实际文件读写、外部服务和联网目的地;本站的核验不会授予任何运行权限。
用户讨论
还没有已核实的点评。