Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add EthanYoQ/Skill-hub --skill aact-bulk-trialsgit clone --depth 1 https://github.com/EthanYoQ/Skill-hubWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ethanyoq/skill-hub/aact-bulk-trials)<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/aact-bulk-trials"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/aact-bulk-trials/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/aact-bulk-trials"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/aact-bulk-trials.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00313 | $0.02461 |
| Opus 5.5 | $0.00125 | $0.00984 |
| Sonnet 5.5 | $0.00063 | $0.00492 |
| Haiku 4.5 | $0.00031 | $0.00246 |
Grade B, and why
aact-bulk-trials scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| `psql: connection refused`（本地） | 本地 PostgreSQL 未启动 | macOS: `brew services start postgresql@16` / Linux: `sudo systemctl start postgresql` / Windows: `Start-Service postgresql-x64-16` | How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AACT Bulk Trials · 批量临床试验数据仓库
1. 何时调用本 skill
调用本 skill 当用户请求：
- 疾病领域全景分析（"过去 10 年血液病所有 NCT 试验按 phase/sponsor 聚合"）
- 跨年度趋势聚合（"AML 领域 III 期试验赞助商分布"）
- 设计相似试验匹配（"找与 NCT12345678 设计相似的其他试验"）
- 整库扫描 / 百万级 JOIN（条件 + 干预 + 结果跨表）
不要调用本 skill（应转其他）：
- 单条 NCT 最新状态查询 →
clinical-trials-v2（实时 API · 互补） - 文献检索 →
pubmed-search/europepmc-search - 临床报告撰写 →
clinical-reports
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 |
2. 上下游 skill 协作
clinical-trials-v2 ────┐
(实时单查 · 互补) │
▼
aact-bulk-trials → medical-evidence-grading → evidence-appendix-sync
(本 skill · 批量SQL) (上层 · 批量 grade) (终下游 · 报告附录)
- 上游：用户原始批量挖掘需求（市场调研、疾病全景、设计相似性）
- 平级互补：
clinical-trials-v2（单条实时） /pubmed-search（文献） - 下游：
medical-evidence-grading（用本 skill 输出的 NCT 列表批量评级） →evidence-appendix-sync（终态报告附录 C）
3. 核心能力速查（5 个 SQL 模板）
所有签名见 references/sql-templates.md，参数化 SQL 防注入，默认 LIMIT 1000。
| 函数 | 签名（参数） | 用途 |
|---|---|---|
query_trials_by_condition |
(condition_term, year_from, year_to, phase, limit) |
按适应症 + 年份 + phase 检索 |
query_trials_by_intervention |
(intervention_name, intervention_type, limit) |
按干预名 + 类型检索 |
query_trials_results_summary |
(nct_id_list) |
已上传 results 的试验统计摘要 |
bulk_disease_landscape |
(disease_term, year_from, year_to) |
疾病四维聚合（phase/status/sponsor/国家） |
find_similar_design_trials |
(reference_nct_id, limit) |
设计相似试验匹配 |
完整 SQL 见 → references/sql-templates.md
4. 双连接快速决策
skill 启动时自动检测：本地 dump (B) → 云端 (A) → 报错指引。
| 模式 | 何时用 | 性能 |
|---|---|---|
| 本地 dump（B） | 批量挖掘 / 整库扫描 / 跨年度聚合 | 典型 < 5s |
| 云端公共（A） | 偶发查询 / 无本地 PostgreSQL | 200ms - 2s |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 166 lines · 313 tokens per session scan B 80b42e5e0048
aact-bulk-trials is a skill published in the GitHub repository EthanYoQ/Skill-hub (11 stars, last pushed 10d ago), licensed MIT. It adds 313 tokens to every session and 2,461 once invoked, about $0.0013 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-13.
Other skills, from other repositories
geospatial-data-pipeline
Process, analyze, and visualize geospatial data at scale. Handles drone imagery, GPS tracks, GeoJSON optimization, coordinate transformations, and tile generation. Use for mapping apps, drone data processing, location-based services. Activate on "geospatial", "GIS", "PostGIS", "GeoJSON", "map tiles", "coordinate…
fetch-meta-from-kb
Fetch recent journals rows directly from PostgreSQL and return a JSON array containing doi, title, abstract, and date (filtered by rolling DAYS on createdat). Use when users need raw paper payloads for downstream processing without LLM filtering or hotspot report generation.
geo-infer-space
H3 hexagonal spatial indexing and multi-backend spatial operations. Use when working with H3 cells, spatial indexing, coordinate systems, raster/vector operations, or any spatial backend dispatch (H3, SRAI).
postgresql-table-design
Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
sql-optimization-patterns
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.