Back to Skills

serialize-data-formats

pjt222
Updated 6 days ago
24 views
17
2
17
View on GitHub
Documentationapidata

About

This skill enables serialization and deserialization across formats like JSON, XML, YAML, Protobuf, and MessagePack. It helps developers choose the right format based on performance, size, and interoperability needs for APIs, storage, or system communication. Use it when selecting a wire format, optimizing data transfer, or migrating between serialization systems.

Quick Install

Claude Code

Recommended
Primary
npx skills add pjt222/agent-almanac -a claude-code
Plugin CommandAlternative
/plugin add https://github.com/pjt222/agent-almanac
Git CloneAlternative
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/serialize-data-formats

Copy and paste this command in Claude Code to install this skill

Documentation

序資式

選與行正資序式於用例、含正編解與性意。

  • 擇 API 通線式→用
  • 持結構資於盤或物儲→用
  • 異語系間交資→用
  • 優傳大或解速→用
  • 自一序式遷他→用

  • :所序資結構(譜或例)
  • :用例(API、儲、流、析)
  • :性需(大、速、譜強)
  • :標語/運限
  • :人讀需

一:擇正式

FormatHuman ReadableSchemaSizeSpeedBest For
JSONYesOptional (JSON Schema)MediumMediumREST APIs, config
XMLYesXSD, DTDLargeSlowEnterprise/legacy, SOAP
YAMLYesOptionalMediumSlowConfig, CI/CD, k8s
Protocol BuffersNoRequiredSmallFastgRPC, microservices
MessagePackNoNoneSmallFastReal-time, embedded
Arrow/ParquetNoBuilt-inVery SmallVery FastAnalytics, columnar

決樹:

  1. 需人改? → YAML(配)或 JSON(資)
  2. 需嚴譜 + 速 RPC? → Protocol Buffers
  3. 需最小線大? → MessagePack 或 Protobuf
  4. 需列析? → Apache Parquet
  5. 需內存交? → Apache Arrow
  6. 舊企接? → XML

得:式選附文錄理合用例需。

敗:需衝(如人讀且速)→重主用例、註衡。

二:行 JSON 序

import json
from datetime import datetime, date
from dataclasses import dataclass, asdict

@dataclass
class Measurement:
    sensor_id: str
    value: float
    unit: str
    timestamp: datetime

class CustomEncoder(json.JSONEncoder):
    def default(self, obj):
        if isinstance(obj, datetime):
            return obj.isoformat()
        if isinstance(obj, date):
            return obj.isoformat()
        if isinstance(obj, bytes):
            import base64
            return base64.b64encode(obj).decode('ascii')
        return super().default(obj)

measurement = Measurement("sensor-01", 23.5, "celsius", datetime.now())
json_str = json.dumps(asdict(measurement), cls=CustomEncoder, indent=2)

data = json.loads(json_str)
library(jsonlite)

df <- data.frame(sensor_id = "sensor-01", value = 23.5, unit = "celsius")
json_str <- jsonlite::toJSON(df, auto_unbox = TRUE, pretty = TRUE)

df_back <- jsonlite::fromJSON(json_str)

得:往返序保諸型準。

敗:型失(如日成串)→解步加顯型轉。

三:行 Protocol Buffers

定譜(.proto 檔):

syntax = "proto3";
package sensors;

message Measurement {
  string sensor_id = 1;
  double value = 2;
  string unit = 3;
  int64 timestamp_ms = 4;
}

message MeasurementBatch {
  repeated Measurement measurements = 1;
}

生並用:

protoc --python_out=. sensors.proto
protoc --go_out=. sensors.proto
from sensors_pb2 import Measurement, MeasurementBatch
import time

m = Measurement(
    sensor_id="sensor-01",
    value=23.5,
    unit="celsius",
    timestamp_ms=int(time.time() * 1000)
)
binary = m.SerializeToString()

m2 = Measurement()
m2.ParseFromString(binary)

得:二制出較等 JSON 小 3-10 倍。

敗:protoc 無→用語原 protobuf 庫(如 Python betterproto)。

四:行 MessagePack

import msgpack
from datetime import datetime

def encode_datetime(obj):
    if isinstance(obj, datetime):
        return {"__datetime__": True, "s": obj.isoformat()}
    return obj

def decode_datetime(obj):
    if "__datetime__" in obj:
        return datetime.fromisoformat(obj["s"])
    return obj

data = {"sensor_id": "sensor-01", "value": 23.5, "ts": datetime.now()}

packed = msgpack.packb(data, default=encode_datetime)

unpacked = msgpack.unpackb(packed, object_hook=decode_datetime, raw=False)

得:MessagePack 出於典載較 JSON 小 15-30%。

敗:語缺 MessagePack 支→退 JSON 加壓(gzip)。

五:行 Apache Parquet(列)

import pyarrow as pa
import pyarrow.parquet as pq
import pandas as pd

df = pd.DataFrame({
    "sensor_id": ["s-01", "s-02", "s-01", "s-03"] * 1000,
    "value": [23.5, 18.2, 24.1, 19.8] * 1000,
    "unit": ["celsius"] * 4000,
    "timestamp": pd.date_range("2025-01-01", periods=4000, freq="min")
})

table = pa.Table.from_pandas(df)
pq.write_table(table, "measurements.parquet", compression="snappy")

table_back = pq.read_table("measurements.parquet", columns=["sensor_id", "value"])
df_subset = table_back.to_pandas()
library(arrow)

df <- data.frame(sensor_id = rep("s-01", 1000), value = rnorm(1000))
arrow::write_parquet(df, "measurements.parquet")

df_back <- arrow::read_parquet("measurements.parquet", col_select = c("value"))

得:Parquet 檔較 CSV 小 5-20 倍於典表資。

敗:Arrow 無→用 fastparquet(Python)或 CSV + gzip 退。

六:較性

行基準於汝特資與用例:

import json, msgpack, time
import pyarrow as pa, pyarrow.parquet as pq

data = [{"id": i, "value": i * 0.1, "label": f"item-{i}"} for i in range(10000)]

start = time.perf_counter()
json_bytes = json.dumps(data).encode()
json_time = time.perf_counter() - start

start = time.perf_counter()
msgpack_bytes = msgpack.packb(data)
msgpack_time = time.perf_counter() - start

print(f"JSON:    {len(json_bytes):>8} bytes, {json_time*1000:.1f} ms")
print(f"MsgPack: {len(msgpack_bytes):>8} bytes, {msgpack_time*1000:.1f} ms")

得:基準果導產用式選。

敗:諸式性不足→考壓(zstd、snappy)為正交優。

  • 所選式合用例需(文錄理)
  • 往返序保諸資型
  • 邊例理:空集、null/None、Unicode、大數
  • 性基於代表載大基準
  • 誤理為畸入(雅敗非崩)
  • 譜文錄(JSON Schema、.proto 等)

  • 浮精:JSON 諸數為 IEEE 754 雙。財/十進精用串編
  • 日時理:JSON 無原日型。恆文錄式(ISO 8601)與時區理
  • 譜演:加除欄可破消費。Protobuf 善理;JSON 需慎本
  • JSON 內二:Base64 編脹二 ~33%。二重載用二式
  • YAML 安:YAML 解器可執任碼經 !!python/object。恆用安載

  • design-serialization-schema
  • implement-pharma-serialisation
  • create-quarto-report

GitHub Repository

pjt222/agent-almanac
Path: i18n/wenyan-ultra/skills/serialize-data-formats
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

Related Skills

railway-docs

Documentation

This skill fetches current Railway documentation to answer questions about features, functionality, or specific docs URLs. It ensures developers receive accurate, up-to-date information directly from Railway's official sources. Use it when users ask how Railway works or reference Railway documentation.

View skill

n8n-code-python

Documentation

This Claude Skill provides expert guidance for writing Python code in n8n's Code nodes, specifically for using Python's standard library and working with n8n's special syntax like `_input`, `_json`, and `_node`. It helps developers understand Python's limitations within n8n and recommends using JavaScript for most workflows while offering Python solutions for specific data transformation needs.

View skill

archon

Documentation

The Archon skill provides RAG-powered semantic search and project management through a REST API. Use it for querying documentation, managing hierarchical projects/tasks, and performing knowledge retrieval with document upload capabilities. Always prioritize Archon first when searching external documentation before using other sources.

View skill

n8n-code-javascript

Documentation

This Claude Skill provides expert guidance for writing JavaScript code in n8n's Code nodes. It covers essential n8n-specific syntax like `$input`/`$json` variables, HTTP helpers, and DateTime handling, while troubleshooting common errors. Use it when developing n8n workflows that require custom JavaScript processing in Code nodes.

View skill