Data Locflow logo

Data Locflow

Community
GuangyaoYin
data-locflow

为任意研究区建立、迁移或核验 LOC-FLOW 地震目录工作流,涵盖连续波形、PhaseNet拾取、REAL关联、绝对与双差定位、震级、定位误差和可复现图件。用于项目配置、输入/目录验收、后端适配与流程整理;一般地震知识问答或独立背景制图无需启用。

Overview

PublisherGuangyaoYin
Repositoryskills
Skill namedata-locflow
Stars
64
Forks
2
Bundled files
13
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 13 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by GuangyaoYin on GitHub. Read the source before you install it.

Installation

Install the Data Locflow AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/GuangyaoYin/skills/tree/main/skills/data-locflow
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/GuangyaoYin/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/data-locflow .claude/skills/data-locflow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Data Locflow in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Data Locflow on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Data Locflow is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Data Loc-Flow

帮助用户将自己的连续波形、台站部署与响应、速度模型和项目配置转为可追溯地震目录及结果图。保持研究区无关:地区、日期、仪器、采样率、科学阈值、事件数量和震级经验系数均来自当前项目,不从历史案例或父目录补齐。

按任务加载

先读 能力与实现边界,确定本次是设计、检查、实现适配器、科学运行还是绘图。只继续读取本次所需资料:

工作阅读/使用
初始化、接入新区域、补全配置数据契约、项目profile、assets/config/workflow.example.json
检测、关联、定位及后端迁移检测与定位
测幅、震级、校准、定位误差震级与不确定性
文件组织、缓存、恢复与发布复现规范
图件规划或绘制已有结果图件规范、assets/config/figure_plan.json

assets/schemas/的CSV仅演示格式,不是任何实际区域的模型或台站。不要加载全部参考来处理一次窄修改;绘图任务只读取已验收结果,不因此重跑检测或定位。

处理项目

  1. 明确本次输入、已有结果和要交付的内容。利用用户已提供的数据与配置,先检查可独立推进的部分;缺失信息集中列出,区分能从可靠元数据确定的值与真正需要用户提供的内容。
  2. 定位至少需要波形、台站坐标/有效时段、适用速度模型和时间/坐标/深度基准。物理震级另需要逐通道时段的响应、增益、单位及适用的震级方法。只有输入包已可靠包含这些信息时,用户才可能只填写波形和模型路径。
  3. 在用户项目的独立run目录创建配置和产物。按需从assets复制模板;不要向安装的skill目录写入项目状态或结果。脚本的相对输入路径基于配置文件目录,输出路径应明确指向项目run。
  4. 科学参数无通用默认值时保留未设置,给出元数据推导或小样本试验方案;不要暗中复制采样率、深度范围、概率/CC门槛、Vp/Vs、震级系数或扰动次数。资源批大小与科学筛选阈值分开记录。
  5. 运行本次所需的管理检查,保留报告与实际检查范围。科学阶段使用已安装并核验版本的后端;确认接口、模型、走时表、时基和身份映射后,再按任务授权推进。后端未接通时,具体说明缺少哪个接口,继续完成已授权的实现/整理工作,不伪造结果。

科学数据约束

  • 主链为PhaseNet → REAL → VELEST → ph2dt/hypoDD_dtct → FDTCC → hypoDD_dtcc。可按用户任务替换后端,但需保持标准表、事件UID、绝对到时和各阶段来源;不要把每次重编号的整数ID直接跨阶段或跨月份连接。
  • 固定模型、权重、可执行文件和参数版本。验证走时表节点与排列、读表声明和实际查询范围;hypoDD的NLAY、TOP和VEL长度严格一致。更换位置/原时不得改变原始绝对到时。
  • 物理测幅支路与归一化拾取支路分开。响应路径存在不等于响应已验证;更换响应、幅值算子、单位、距离定义或标度时重新核验适用性。最终位置变化后核验缓存幅值并重算距离项与震级质量。
  • 目录默认使用magnitude+magnitude_type;ML、Ms、Mw等分开保留,不自动转换或混合统计。旧列名只能显式映射;缺震级/误差不得补0。
  • 区分形式误差、观测扰动、事件对重采样、台站删减、模型敏感性与独立绝对约束。成功运行、残差下降、簇变紧或QC标签不能单独证明高精度。精度视图依据项目预先冻结的标准,误差只用于实际完成该试验的事件。
  • 模板匹配是可选分支:新增事件须本地定位、去重并保留实际定位阶段与到时来源;不得继承模板位置或其他来源事件的误差。

可直接执行的管理工具

scripts/locflow.py仅需要Python 3.11+标准库;可选波形头检查需ObsPy。以下用SKILL_ROOT表示本次实际加载的skill文件夹,用RUN表示用户项目输出目录;不要假设skill安装在某个固定用户名路径。

bash
# 只生成计划;模板中未配置的输入会原样列出,不启动后端。
python "$SKILL_ROOT/scripts/locflow.py" plan \
  --config "$RUN/config/project.json" --output "$RUN/reports/plan.json"

# -1检查全部匹配文件的头;0不检查头,正数只抽查对应文件数。
python "$SKILL_ROOT/scripts/locflow.py" preflight \
  --config "$RUN/config/project.json" --header-limit -1 \
  --output "$RUN/reports/preflight.json"

python "$SKILL_ROOT/scripts/locflow.py" audit-catalog \
  --catalog "$RUN/products/catalogs/catalog_complete.csv" \
  --output "$RUN/reports/catalogue_acceptance.json"

# 若源表缺类型列,只有用户或可信元数据明确标度后才使用fallback。
python "$SKILL_ROOT/scripts/locflow.py" audit-catalog \
  --catalog "$RUN/input/legacy_catalog.csv" \
  --magnitude-column local_ml --default-magnitude-type ML \
  --output "$RUN/reports/legacy_acceptance.json"

python "$SKILL_ROOT/scripts/locflow.py" check-hypodd-model \
  --input "$RUN/config/hypoDD.inp" --output "$RUN/reports/layers.json"

check-travel-table还需显式提供--table、--distance-max-deg、--distance-step-deg、--depth-max-km和--depth-step-km;数值应来自同一张表的生成记录。它仅支持参考文档中的REAL/FDTCC十列约定,其他格式需适配。

检查命令退出0表示本项通过、2表示失败。plan的WRITTEN只表示计划写出;空模板预检FAIL正常。audit-catalog只验收非空、震级与类型齐全的complete视图,不验收允许缺测的all视图,也不证明科学精度。

结果与交付

维护一个主目录,并按需要派生all、complete和high_precision视图。保留输入哈希、配置/模型/后端版本、lineage、接受与拒绝原因、误差方法和来源。缓存恢复必须核对依赖签名,不以旧.done或文件存在当作成功。

绘图消费冻结结果;根据输入生成适用图,不用旧图或占位数据补齐。默认不放图名、备注或样本数提示,保留轴名、单位、色标、图例与必要标识;静态输出PNG+TXT/JSON/TSV。范围、分期、投影和深度色标由项目决定,色标上限不能过滤科学目录;地质、断层及外部目录为可选背景。

交付时说明本次生成/修改了什么、实际执行哪些检查/后端、结果位置及仍未验证的部分。当前skill包含流程知识、模板与五项管理命令,不自带完整科学计算后端或自动绘图实现;创建或调用skill不表示已完成原始波形到高精度目录的端到端验证。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Data Locflow AI skill do?

为任意研究区建立、迁移或核验 LOC-FLOW 地震目录工作流,涵盖连续波形、PhaseNet拾取、REAL关联、绝对与双差定位、震级、定位误差和可复现图件。用于项目配置、输入/目录验收、后端适配与流程整理;一般地震知识问答或独立背景制图无需启用。

Why use Data Locflow on TypingMind?

Because you install it once and use it with any model. Data Locflow is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Data Locflow in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/GuangyaoYin/skills/tree/main/skills/data-locflow. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Data Locflow?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Data Locflow?

As many as you like. As long as a model supports skills, you can use Data Locflow with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Data Locflow AI skill free?

It is published on GitHub by GuangyaoYin. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇