Skip to content
Agentmart
Submit a tool

aact-bulk-trials

使用 AACT (Aggregate Analysis of ClinicalTrials.gov) PostgreSQL 数据库进行大批量临床试验历史分析与数据挖掘。触发场景包括:AACT 查询、临床试验批量分析、PostgreSQL 试验数据、全量 NCT 检索、试验数据挖掘、clinical trials…

Skill by EthanYoQ

IndexedMIT★ 11
Write a review

Chalk Labs

Need help deploying aact-bulk-trials?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/ethanyoq-aact-bulk-trials-d5d32e

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

使用 AACT (Aggregate Analysis of ClinicalTrials.gov) PostgreSQL 数据库进行大批量临床试验历史分析与数据挖掘。触发场景包括:AACT 查询、临床试验批量分析、PostgreSQL 试验数据、全量 NCT 检索、试验数据挖掘、clinical trials data warehouse、疾病领域全景分析、设计相似试验匹配、跨年度试验趋势聚合。本 skill 通过 SQL 接口处理百万级试验记录,支持云端公共 PostgreSQL 服务(aact-db.ctti-clinicaltrials.org)和每日 dump 本地还原两种连接方式,自动检测并优先使用本地高性能模式。

Use cases: backend, data

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/aact-bulk-trials

What's inside

Skill name
aact-bulk-trials
Description
使用 AACT (Aggregate Analysis of ClinicalTrials.gov) PostgreSQL 数据库进行大批量临床试验历史分析与数据挖掘。触发场景包括:AACT 查询、临床试验批量分析、PostgreSQL 试验数据、全量 NCT 检索、试验数据挖掘、clinical trials data warehouse、疾病领域全景分析、设计相似试验匹配、跨年度试验趋势聚合。本 skill 通过 SQL 接口处理百万级试验记录,支持云端公共 PostgreSQL 服务(aact-db.ctti-clinicaltrials.org)和每日 dump 本地还原两种连接方式,自动检测并优先使用本地高性能模式。
License
MIT
Instructions
369 lines in SKILL.md · view on GitHub

Before installing

  • Instructions read files in your home folder (~/.ssh, ~/.aws…)

Files (1)

  • SKILL.md

SKILL.md (first lines)

# AACT Bulk Trials · 批量临床试验数据仓库

## 1. 职责边界

**只做**:基于 AACT PostgreSQL 数据库的批量、历史、聚合性临床试验数据分析。
**不做**:
- 实时单条 NCT 查询(→ 使用 `clinical-trials-v2` skill)
- 文献检索(→ 使用 `pubmed-search` / `europepmc-search`)
- 临床数据撰写报告(→ 使用 `clinical-reports`)

**典型用例**:
- "分析血液科所有 IFI(侵袭性真菌感染)相关历史试验的设计趋势"
- "找出过去 10 年 AML 领域全部 III 期试验的赞助商分布"
- "匹配某个 NCT 的设计相似试验(同 condition + intervention + phase)"
- "按国家维度聚合 CAR-T 试验的 status 分布"

---

## 2. 与 clinical-trials-v2 的差异

| 维度 | clinical-trials-v2 | aact-bulk-trials(本 skill) |
|------|-------------------|----------------------------|
| 数据源 | ClinicalTrials.gov v2 REST API | AACT PostgreSQL 镜像(每日同步) |
| 单次容量 | ≤ 1000 条 | 单 SQL 可处理百万级 |
| 网络 | 强依赖 | 本地模式离线可用 |
| 延迟 | 低(实时) | T+1(每日 dump) |
| 适用场景 | 单试验细节、最新状态 | 批量聚合、历史趋势、跨表 JOIN |

---

## 3. 两种连接方式

skill 启动时自动检测优先级:**本地 dump (B) → 云端 (A) → 报错指引**。

### 方式 A · 云端公共 PostgreSQL(推荐零部署)

- Host: `aact-db.ctti-clinicaltrials.org`
- Port: `5432`
- Database: `aact`
- 注册免费账号: https://aact.ctti-clinicaltrials.org/users/sign_up
- 适合:偶发查询、无本地 PostgreSQL、可接受网络延迟

### 方式 B · 本地 dump 还原(高性能 · 离线分析)

- 下载每日 dump(约 2.27 GB pg_dump custom format):https://aact.ctti-clinicaltrials.org/downloads
- 要求:本地 PostgreSQL 16+
- 还原命令:
  ```bash
  createdb aact
  pg_restore -d aact -j 4 --no-owner --no-privileges /path/to/postgres_data.dmp
  ```
- 适合:批量挖掘、跨年度聚合、设计相似性匹配、整库扫描

### 配置文件 `~/.config/aact.local.yaml`

```yaml
# 优先模式:local 或 cloud;auto 表示自动检测(默认)
mode: auto

local:
  host: localhost
  port: 5432
  database: aact
  user: postgres
  password: ${AACT_LOCAL_PASSWORD}  # 从环境变量读取

cloud:
  host: aact-db.ctti-clinicaltrials.org
  port: 5432
  database: aact
  user: ${AACT_CLOUD_USER}
  password: ${AACT_CLOUD_PASSWORD}

defaults:
  query_limit: 1000          # 防爆默认 LIMIT
  cursor_threshold: 50000    # 超过该行数自动切 server-side cursor
  statement_timeout: 120000  # 毫秒
```

**密钥管理铁律**:永远不要把 password 明文写进 yaml;用 `${VAR}` 占位符 + 环境变量。

---

## 4. AACT Schema 关系图(精简版)

```
                        ┌──────────────┐
                        │   studies    │  主表 nct_id 主键
                        │  (~500K 行)   │
                        └──────┬───────┘
                               │ nct_id (1-N)
        ┌─────────────┬────────┼────────┬──────────────┬───────────────┐
        │             │        │        │              │               │
   ┌────▼─────┐ ┌─────▼────┐ ┌─▼──────┐ ┌─▼───────┐ ┌──▼──────┐ ┌──────▼──────┐
   │conditions│ │interv-   │ │outcomes│ │sponsors │ │facilities│ │eligibilities│
   │(MeSH)    │ │entions   │ │        │ │         │ │(国家/址) │ │(入排标准)   │
   └──────────┘ └──────────┘ └────┬───┘ └─────────┘ └─────────┘ └─────────────┘
                                  │
                            ┌─────▼──────────┐
                            │outcome_analyses│  统计学结果
                            └────────────────┘

  Results-only 子树(仅有结果上传的试验):
  studies → result_groups → results_baseline / outcome_measurements
```

**关键表**:
- `studies` — 总览(phase, study_type, overall_status, start_date, completion_date, enrollment)
- `conditions` — MeSH 适应症(downcase_name 用于不区分大小写匹配)
- `interventions` — 干预(intervention_type: Drug/Biological/Device/Procedure)
- `outcomes` — 结局指标定义
- `outcome_analyses` — 统计分析(p_value, ci_lower_limit, method)
- `sponsors` — 赞助商(lead_or_collaborator, agency_class: NIH/INDUSTRY/OTHER)
- `eligibilities` — 入排(gender, minimum_age, maximum_age, criteria 全文)
- `facilities` — 站点(country, city, status)
- `result_groups` — 结果分组(arm/group 标识)
- `results_baseline` — baseline 人口学

完整 schema:https://aact.ctti-clinicaltrials.org/schema

From EthanYoQ/Skill-hub, MIT.

More from EthanYoQ/Skill-hub

Signals

Stars
11
Forks
4
Open issues
0
Last commit (this folder)
Sep 19, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from EthanYoQ

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get aact-bulk-trials running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying aact-bulk-trials?

CallGet help
Cite this page

aact-bulk-trials skill. Agent Mart. https://agentmart.dev/skills/ethanyoq-aact-bulk-trials-d5d32e (last updated 2026-10-24)