education-data-source-ccd
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 "education-data-source-ccd":https://skillpi.com/zh/skills/deepskill-b7a427f5ed7a270771df264ec21ade71bdce015cad538cadb7b76ff3316d3739。安装前核对上游来源和版本:https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/17-DAAF-Contribution-Community-daaf/dot-claude/skills/education-data-source-ccd/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/17-DAAF-Contribution-Community-daaf/dot-claude/skills/education-data-source-ccd --skill education-data-source-ccd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
本条目面向分析数据与指标归因场景,提供“education-data-source-ccd”技能的目录入口。公开标签:learning、教育数据、K-12、公立学校。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: education-data-source-ccd
description: >-
CCD — federal universe of all U.S. public K-12 schools (~100K) and districts (~18K). Enrollment, staffing, finance, directory data (1986-present). Use for public school analysis by grade/race/sex. Public only; excludes private and postsecondary.
metadata:
audience: any-agent
domain: data-source
skill-authored: "2026-02-09"
skill-last-updated: "2026-02-09"
---
# CCD Data Source Reference
Common Core of Data (CCD) — the federal complete-universe database of all U.S. public K-12 schools and districts (~100,000 schools, ~18,000 districts), collecting enrollment, staffing, finance, and directory data annually (1986-present). Use when analyzing public school enrollment by grade/race/sex, district finances, school staffing, or directory attributes. Public schools and districts only; excludes private schools and postsecondary. Note significant variable encoding and race/ethnicity definition changes over time.
The CCD is the Department of Education's comprehensive, annual, national database of all public elementary and secondary schools and school districts in the United States. It is the only federal dataset that provides a complete universe census (not a sample) of U.S. public K-12 education.
> **CRITICAL: Value Encoding**
>
> The Education Data Portal uses **integer codes** for categorical variables that
> differ from NCES's original string codes. Always verify codes against codebooks.
>
> | Context | `school_type` | `charter` | `urban_centric_locale` |
> |---------|---------------|-----------|------------------------|
> | **Portal (integers)** | `1` (Regular) | `0` (No) / `1` (Yes) | `11` (City-Large) |
> | NCES original | `1-Regular school` | `Yes` / `No` | `11-City: Large` |
>
> **Note:** `charter` and `magnet` use `0/1` encoding, NOT `1=Yes / 2=No` as some NCES documentation shows.
>
> See `./references/variable-definitions.md` for complete encoding tables.
## What is CCD?
- **Primary K-12 database**: DOE's authoritative source for public elementary/secondary education statistics
- **Universe survey**: Covers ALL public schools and districts, not a sample
- **Annual collection**: Data submitted by State Education Agencies (SEAs) each year
- **Six major components**: Directory, Membership, Staffing, Finance (state and district), Dropout/Completers
- **Coverage**: ~100,000 public schools and ~18,000 school districts nationwide
- **Historical depth**: Data available from 1986 to present (varies by component)
- **Collector**: National Center for Education Statistics (NCES) via EDFacts
- **Available through**: Education Data Portal mirrors (5 of 6 survey components; see Data Access section for details)
## Reference File Structure
| File | Purpose | When to Read |
|------|---------|--------------|
| `survey-components.md` | Detailed coverage of each CCD survey component | Understanding what data is collected |
| `data-collection.md` | How data flows from schools to NCES, timelines, respondent universe | Understanding data provenance and timing |
| `variable-definitions.md` | Key variables, coding schemes, special values | Interpreting specific data elements |
| `data-quality.md` | Missing data patterns, suppression, state variations | Assessing data reliability |
| `historical-changes.md` | Definition changes, code revisions over time | Longitudinal analysis |
## Decision Trees
### What CCD component do I need?
```
What information do you need?
├─ School/district names, addresses, contacts → Directory
│ └─ See ./references/survey-components.md#directory
├─ Student enrollment counts → Membership
│ ├─ By grade → Membership (grade disaggregation)
│ ├─ By race/ethnicity → Membership (race disaggregation)
│ ├─ By sex → Membership (sex disaggregation)
│ └─ See ./references/survey-components.md#membership
├─ Staff/teacher counts → Staffing
│ └─ See ./references/survey-components.md#staffing
├─ Revenue and expenditure → Finance
│ ├─ State-level totals → National Public Education Financial Survey
│ ├─ District-level detail → School District Finance Survey (F-33)
│ └─ See ./references/survey-components.md#finance
├─ Graduation/dropout rates → Dropout and Completers
│ └─ See ./references/survey-components.md#dropout-completers
└─ School type, charter status, locale → Directory
└─ See ./references/survey-components.md#directory
```
### Is this a data quality issue?
```
Unexpected data values?
├─ Negative numbers (-1, -2, -3, -9) → Missing data codes
│ └─ See ./references/variable-definitions.md#missing-data-codes
├─ Very different from prior year → Check for definition changes
│ └─ See ./references/historical-changes.md
├─ State appears as outlier → Check state-specific reporting
│ └─ See ./references/data-quality.md#state-variations
├─ Large number of zeros → Check suppression rules
│ └─ See ./references/data-quality.md#suppression
└─ Locale codes don't match → Pre/post 2006 locale system change
└─ See ./references/historical-changes.md#locale-codes
```
### Can I compare across time?
```
Building a time series?
├─ Race/ethnicity categories → Major change in 2010
│ └─ See ./references/historical-changes.md#race-ethnicity
├─ Locale codes → Completely revised in 2006
│ └─ See ./references/historical-changes.md#locale-codes
├─ School/district IDs → Check for ID changes
│ └─ See ./references/variable-definitions.md#identifiers
├─ Free/reduced lunch → CEP and direct certification changes
│ └─ See ./references/data-quality.md#frpl
└─ Finance data → Definition changes and inflation
└─ See ./references/historical-changes.md#finance
```
## Quick Reference: CCD Components
| Component | Level | Key Variables | Years | Update Cycle |
|-----------|-------|---------------|-------|--------------|
| Directory | School, LEA, State | Name, address, type, status, locale, charter | 1986+ | Annual |
| Membership | School, LEA, State | Enrollment by grade, race, sex | 1986+ | Annual |
| Staffing | School, LEA, State | FTE teachers, staff by category | 1987+ | Annual |
| Finance (State) | State | Revenue, expenditure by source/function | 1989+ | Annual (1-2 yr lag) |
| Finance (District) | LEA | Revenue, expenditure, per-pupil | 1989+ | Annual (2 yr lag) |
| Dropout/Completers | LEA, State | Dropout counts, diploma recipients | 1991+ | Annual |
> **Note:** Not all components listed above are available through the Portal mirrors. See the Data Access section for which datasets are mirrored.
### Key Identifiers
| Portal Column | Format | Level | Example | Notes |
|---------------|--------|-------|---------|-------|
| `ncessch` | 12 characters | School | `010000100100` | State FIPS (2) + LEA suffix (5) + School (5) |
| `leaid` | 7 characters | District | `0100001` | State FIPS (2) + State-assigned (5) |
| `fips` | 2 digits | State | `01` | Federal Information Processing Standard |
> **ID Type Warning:** `ncessch` and `leaid` may be String or Int64 depending on the dataset.
> In the Schools Directory, `ncessch` is String (preserving leading zeros); in enrollment data,
> `ncessch` is Int64. In the Districts Directory, `leaid` is Int64; in Finance data, `leaid` is String.
> Always check the actual dtype and cast as needed when joining across datasets.
### Missing Data Codes
The Portal uses both `null` and negative integer codes to represent missing/special values. The specific pattern varies by dataset:
| Code | Meaning | When Used |
|------|---------|-----------|
| `null` | Not available | Common in Directory fields that don't apply to all years |
| `-1` | Missing/not reported | Data not reported by state |
| `-2` | Not applicable | Item doesn't apply to this entity |
| `-3` | Suppressed | Data suppressed for privacy |
| `-9` | Not reported | State did not report this item |
> **Check actual data.** Some datasets use `null` where others use `-1` for effectively the same condition. Always check the observed values in the data before applying a blanket missing-value filter.
### School Types (`school_type`)
| Code | Type | Description |
|------|------|-------------|
| 1 | Regular | Standard public school |
| 2 | Special Education | Focuses on students with disabilities |
| 3 | Vocational | Career/technical education focus |
| 4 | Alternative | Non-traditional programs |
| 5 | Reportable Program | Program within another school (2007-08+) |
### LEA Types (`agency_type`)
| Code | Type | Description |
|------|------|-------------|
| 1 | Regular | Locally governed school district |
| 2 | Component | District sharing superintendent with others |
| 3 | Supervisory Union | Admin services for multiple districts |
| 4 | Regional Agency | Education service agency |
| 5 | State-operated | State-run schools (deaf, blind, correctional) |
| 6 | Federal-operated | Federal schools (BIE, DoDEA) |
| 7 | Charter Agency | All schools are charters (2007-08+) |
| 8 | Other | Doesn't fit other categories (2007-08+) |
| 9 | Specialized Agency | Specialized public agency (observed in data) |
### Grade -1 Encoding
In CCD enrollment data:
- `grade = -1` means **Pre-Kindergarten**, NOT missing data
- `grade = 99` means **Total** across all grades
**Do NOT filter `grade >= 0`** — this removes all Pre-K students!
```python
# WRONG - removes Pre-K students!
df = df.filter(pl.col("grade") >= 0)
# CORRECT
pre_k = df.filter(pl.col("grade") == -1) # Pre-K only
k12 = df.filter(pl.col("grade").is_between(0, 12)) # K-12
total = df.filter(pl.col("grade") == 99) # All grades
```
### Portal Column Name Mapping
> **Variable Name Mapping:** The Portal column `urban_centric_locale` contains locale codes. Some documentation may refer to this as simply `locale`. Use `urban_centric_locale` when filtering or selecting columns in Portal data.
### Dataset-to-Component Mapping
| Mirror Dataset | CCD Component | Path |
|----------------|---------------|------|
| Schools CCD Directory | School Directory | `ccd/schools_ccd_directory` |
| Schools CCD Enrollment | School Membership | `ccd/schools_ccd_enrollment_{year}` |
| Districts LEA Directory | LEA Directory | `ccd/school-districts_lea_directory` |
| Districts CCD Enrollment | LEA Membership | `ccd/schools_ccd_lea_enrollment_{year}` |
| Districts CCD Finance | F-33 District Finance | `ccd/districts_ccd_finance` |
### Data Collection Flow
```
Schools → Local Education Agencies (LEAs)
↓
State Education Agencies (SEAs)
↓
EDFacts Submission System
↓
NCES Quality Review & Editing
↓
CCD Public Data Files
```
**Timeline**: Data for school year 20XX-YY typically submitted spring 20YY, released fall 20YY (preliminary) to spring 20YY+1 (provisional/final).
## Data Access
Datasets for CCD are available via the mirror system. See `datasets-reference.md` for canonical paths, `mirrors.yaml` for mirror configuration, and `fetch-patterns.md` for fetch code patterns.
**Key datasets (5 datasets; see `datasets-reference.md` for the authoritative list):**
| Dataset | Type | Path | Codebook |
|---------|------|------|----------|
| School Directory | Single | `ccd/schools_ccd_directory` | `ccd/codebook_schools_ccd_directory` |
| School Enrollment | Yearly (1986-2023) | `ccd/schools_ccd_enrollment_{year}` | `ccd/codebook_schools_ccd_enrollment` |
| District Directory | Single | `ccd/school-districts_lea_directory` | `ccd/codebook_districts_ccd_directory` |
| District Enrollment | Yearly (1986-2023) | `ccd/schools_ccd_lea_enrollment_{year}` | `ccd/codebook_districts_ccd_enrollment` |
| District Finance | Single | `ccd/districts_ccd_finance` | `ccd/codebook_districts_ccd_finance` |
> **Not in Portal mirrors:** The following CCD components are documented in this skill for reference but are **not available** through the Education Data Portal mirrors:
> - **Dropout/Completers** — completion and dropout data by demographics
> - **State Finance (NPEFS)** — state-level education revenue and expenditure
>
> For these components, access NCES directly at https://nces.ed.gov/ccd/.
Codebooks are `.xls` files co-located with data in all mirrors. Use `get_codebook_url()` from `fetch-patterns.md` to construct download URLs:
```python
url = get_codebook_url("ccd/codebook_schools_ccd_directory")
```
> **Truth Hierarchy:** When interpreting variable values, apply this priority:
> 1. **Actual data file** (what you observe in the parquet/CSV) -- this IS the truth
> 2. **Live codebook** (.xls in mirror) -- authoritative documentation, may lag
> 3. **This skill documentation** -- convenient summary, may drift from codebook
>
> If this documentation contradicts the codebook, trust the codebook. If the codebook contradicts observed data, trust the data and investigate.
### Filtering
All filtering is done locally with Polars after download:
```python
import polars as pl
# Filter by state (California)
df = df.filter(pl.col("fips") == 6)
# Filter by year
df = df.filter(pl.col("year").is_in([2020, 2021, 2022]))
# Get totals only (enrollment)
df = df.filter(pl.col("grade") == 99)
# Get specific grades (K-12)
df = df.filter(pl.col("grade").is_between(0, 12))
```
### Finance Data Notes
- **Finance data lag:** The latest available year in the mirror is **2020** (empirically verified). Finance data typically lags 2+ years behind current school year.
- Finance dataset has 163 columns -- by far the most complex CCD dataset
- Some finance columns use `_total` suffix (e.g., `exp_current_instruction_total`)
- `leaid` is String type in Finance data (unlike the Districts Directory where it is Int64)
## Common Pitfalls
| Pitfall | Issue | Solution |
|---------|-------|----------|
| Summing grades | Misses ungraded students | Use `grade=99` (total) instead |
| Assuming `-1` is missing | In grade data, `-1` = Pre-K | Check variable format in codebook |
| Cross-state comparison | Different state definitions | Check state methodology first |
| Using FRPL as poverty measure | CEP schools show 100% | Supplement with MEPS or SAIPE data |
| Locale time series | 2006 code system change | Analyze pre/post-2006 separately |
| Charter school counts | Early years incomplete | Verify against state records pre-2010 |
| Dropout rate comparison | State definitions vary | Within-state comparisons only |
| Using NCES string codes | Portal uses integers | See variable-definitions.md for mappings |
| Assuming `charter=1/2` | Portal uses `0=No, 1=Yes` | Empirically verified; not NCES `1=Yes, 2=No` |
| ID type across datasets | `leaid`/`ncessch` may be String or Int64 | Always check dtype before joining |
## Coverage Notes
### What CCD Includes
- All public schools (traditional, charter, magnet, alternative)
- All public school districts and LEAs
- Bureau of Indian Education (BIE) schools
- Department of Defense Education Activity (DoDEA) schools
- State-operated schools (deaf, blind, correctional)
### What CCD Excludes
- Private schools (use Private School Universe Survey - PSS)
- Homeschool students
- Postsecondary institutions (use IPEDS)
- Detailed student-level data (CCD is aggregate only)
## Related Data Sources
| Source | Relationship | When to Use |
|--------|--------------|-------------|
| `education-data-source-edfacts` | CCD nonfiscal data flows through EDFacts | Same underlying data |
| `education-data-source-crdc` | Biennial; uses CCD school IDs | Need discipline, course access, equity data |
| `education-data-source-saipe` | Uses CCD district IDs | Need poverty estimates (better than FRPL) |
| `education-data-source-meps` | School-level poverty estimates | Need school-level poverty (better than FRPL) |
| `education-data-source-ipeds` | Separate system for postsecondary | Need college/university data |
| PSS | Private school equivalent | Need private school data |
| `education-data-source-nhgis` | Census geography crosswalks | Need school-Census links |
| `education-data-explorer` | Parent discovery skill | Finding available datasets |
| `education-data-query` | Data fetching (mirror system) | Downloading parquet/CSV files via `fetch_from_mirrors()` |
## Topic Index
| Topic | Reference File |
|-------|---------------|
| Directory survey | `./references/survey-components.md` |
| Membership survey | `./references/survey-components.md` |
| Staffing survey | `./references/survey-components.md` |
| Finance surveys | `./references/survey-components.md` |
| Dropout/completers | `./references/survey-components.md` |
| Data collection process | `./references/data-collection.md` |
| EDFacts submission | `./references/data-collection.md` |
| Respondent universe | `./references/data-collection.md` |
| NCES identifiers | `./references/variable-definitions.md` |
| Missing data codes | `./references/variable-definitions.md` |
| Grade codes | `./references/variable-definitions.md` |
| Race/ethnicity codes | `./references/variable-definitions.md` |
| Locale codes | `./references/variable-definitions.md` |
| State-level variations | `./references/data-quality.md` |
| Missing data patterns | `./references/data-quality.md` |
| FRPL limitations | `./references/data-quality.md` |
| Data suppression | `./references/data-quality.md` |
| Locale code changes (2006) | `./references/historical-changes.md` |
| Race/ethnicity changes (2010) | `./references/historical-changes.md` |
| LEA type changes (2007) | `./references/historical-changes.md` |
| ID changes over time | `./references/historical-changes.md` |
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
提供美国联邦 K-12 公立学校完整数据库(CCD)的详细技术参考
评分依据
description 明确说明适用场景(按年级/种族/性别分析公立学校)
评分依据
文档结构清晰,包含决策树、快速参考、常见问题等实用模块
评分依据
提供了完整的数据集路径和代码本访问方式
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。
文档引用的域名或地址
这些地址可能用于文档链接或示例,不是已批准的联网清单。使用前核对实际目的地及发送的数据。
- nces.ed.gov
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。