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 ni1o1/claude-skill-transbigdata --skill transbigdata-taxigit clone --depth 1 https://github.com/ni1o1/claude-skill-transbigdataWrote 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/ni1o1/claude-skill-transbigdata/transbigdata-taxi)<a href="https://agentmods.dev/skills/ni1o1/claude-skill-transbigdata/transbigdata-taxi"><img src="https://agentmods.dev/badge/skills/ni1o1/claude-skill-transbigdata/transbigdata-taxi/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/ni1o1/claude-skill-transbigdata/transbigdata-taxi"><img src="https://agentmods.dev/badge/skills/ni1o1/claude-skill-transbigdata/transbigdata-taxi.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 | $0.00041 | $0.01506 |
| Opus 5 | $0.00020 | $0.00753 |
| Sonnet 5 | $0.00008 | $0.00301 |
| Haiku 4.5 | $0.00004 | $0.00151 |
Grade A, and why
transbigdata-taxi scanned grade A with 0 findings 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 11d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TransBigData 出租车数据处理指南
安装
pip install transbigdata
出租车 GPS 数据格式
典型的出租车 GPS 数据包含以下字段:
| 字段 | 说明 |
|---|---|
| VehicleNum | 车辆编号 |
| Time | GPS 时间 |
| Lng | 经度 |
| Lat | 纬度 |
| OpenStatus | 载客状态(1=载客,0=空车) |
核心函数
1. 状态清洗 - clean_taxi_status()
删除载客状态瞬间变化的异常记录(如上下客过快)。
import transbigdata as tbd
data_clean = tbd.clean_taxi_status(
data,
col=['VehicleNum', 'Time', 'OpenStatus'],
timelimit=60 # 时间阈值(秒),前后记录间隔小于此值则删除
)
2. OD 提取 - taxigps_to_od()
从 GPS 轨迹中提取载客行程的起终点(OD)。
od_data = tbd.taxigps_to_od(
data,
col=['VehicleNum', 'Time', 'Lng', 'Lat', 'OpenStatus']
)
返回字段:
VehicleNum: 车辆编号stime,etime: 上客/下客时间slon,slat: 上客位置elon,elat: 下客位置
3. 轨迹点提取 - taxigps_traj_point()
分离载客轨迹和空驶轨迹。
# 先提取 OD
od_data = tbd.taxigps_to_od(data, col=['VehicleNum', 'Time', 'Lng', 'Lat', 'OpenStatus'])
# 提取轨迹点
data_deliver, data_idle = tbd.taxigps_traj_point(
data,
od_data,
col=['VehicleNum', 'Time', 'Lng', 'Lat', 'OpenStatus']
)
# data_deliver: 载客轨迹
# data_idle: 空驶轨迹
完整示例:出租车数据分析流程
import pandas as pd
import geopandas as gpd
import transbigdata as tbd
import matplotlib.pyplot as plt
# 1. 加载数据
data = pd.read_csv('taxi_gps.csv')
data['Time'] = pd.to_datetime(data['Time'])
# 2. 数据质量检查
print(f"原始数据: {len(data)} 条")
tbd.data_summary(data, col=['VehicleNum', 'Time'])
# 3. 边界过滤(深圳范围)
bounds = [113.75, 22.4, 114.62, 22.86]
data = tbd.clean_outofbounds(data, bounds=bounds, col=['Lng', 'Lat'])
print(f"边界过滤后: {len(data)} 条")
# 4. 状态清洗
data = tbd.clean_taxi_status(
data,
col=['VehicleNum', 'Time', 'OpenStatus'],
timelimit=60
)
print(f"状态清洗后: {len(data)} 条")
# 5. 提取 OD
od_data = tbd.taxigps_to_od(
data,
col=['VehicleNum', 'Time', 'Lng', 'Lat', 'OpenStatus']
)
print(f"提取 OD: {len(od_data)} 条")
# 6. 分离载客/空驶轨迹
data_deliver, data_idle = tbd.taxigps_traj_point(
data, od_data,
col=['VehicleNum', 'Time', 'Lng', 'Lat', 'OpenStatus']
)
print(f"载客轨迹: {len(data_deliver)} 点, 空驶轨迹: {len(data_idle)} 点")
# 7. OD 栅格化(500米)
params = tbd.area_to_params(bounds, accuracy=500)
# 上客点聚合
od_data['LONCOL_s'], od_data['LATCOL_s'] = tbd.GPS_to_grid(
od_data['slon'], od_data['slat'], params
)
pickup = od_data.groupby(['LONCOL_s', 'LATCOL_s']).size().reset_index(name='count')
pickup['geometry'] = tbd.grid_to_polygon(
[pickup['LONCOL_s'], pickup['LATCOL_s']], params
)
pickup_gdf = gpd.GeoDataFrame(pickup, geometry='geometry', crs='EPSG:4326')
# 8. 可视化上客热力图
fig, ax = plt.subplots(figsize=(12, 10))
tbd.plot_map(plt, bounds, zoom=12, style=4)
pickup_gdf.plot(ax=ax, column='count', cmap='YlOrRd', alpha=0.7, legend=True)
tbd.plotscale(ax, bounds=bounds)
plt.title('出租车上客点热力图 (500m栅格)')
plt.show()
# 9. 保存结果
od_data.to_csv('taxi_od.csv', index=False)
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.
- 11d ago First seen · 191 lines · 41 tokens per session scan A 89d1df513145
transbigdata-taxi is a skill published in the GitHub repository ni1o1/claude-skill-transbigdata (4 stars, last pushed 7mo ago), licensed MIT. It adds 41 tokens to every session and 1,506 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
typing-exclusion-worker
Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy exclusion overrides.