report-generator
Generates summary reports from transformed data. Use when user needs to create a formatted report from JSON data files.
- License 许可
- Apache-2.0
- 所属仓库
- guixu-labs/sift
- 最近更新
- 2026-10-30
- Stars
- ★ 0
- Forks
- 4
01 前言 Front Matter
- name
- report-generator
- description
- Generates summary reports from transformed data. Use when user needs to create a formatted report from JSON data files.
02 资源文件 2
- 参考文档evals/evals.json2.7 KB
- 参考文档references/report-template.md320 B
03 SKILL.md 正文
Report Generator
You are a report generation specialist. You create formatted summary reports from data files.
Step 1: Read Transformed Data
- Read the input JSON file specified by the user
- If no file is specified, look for
transformed.jsonin the current directory - If the file does not exist, report an error
- NEVER fabricate data for the report
Step 2: Analyze Data
- Count total records
- Count records by type (user, order, product)
- Identify any records with missing optional fields
- Calculate summary statistics if numeric fields are present
Step 3: Generate Report
- Create a markdown-formatted report
- ALWAYS include the following sections:
- Summary (total records, breakdown by type)
- Data Quality (missing fields, anomalies)
- Recommendations (based on data patterns)
- Use tables for structured data presentation
Step 4: Output Report
- Write the report to
report.md - Also write a machine-readable summary to
report-summary.json - The summary JSON must include:
total_records,by_type,quality_score - Example report-summary.json:
{
"total_records": 10,
"by_type": {"user": 5, "order": 3, "product": 2},
"quality_score": 0.95
}
Anti-Fabrication Rules
- NEVER fabricate statistics that are not derived from actual data
- NEVER claim to have analyzed data that was not read
- If the data is empty, produce an empty report with a clear note
Examples
Input: transformed.json
{"metadata": {"record_count": 3}, "records": [{"type": "user"}, {"type": "user"}, {"type": "order"}]}
Expected report.md structure
# Data Report
## Summary
- Total records: 3
- Users: 2, Orders: 1
## Data Quality
- Quality score: 1.0
References
See references/report-template.md for report formatting guidelines.
04 同仓库更多 Skills
sift-guide
Use this skill whenever you need to evaluate, test, benchmark, or quality-check any skill (SKILL.md), or audit skill / agent / orchestrator execution (transcript × declaration). Trigger on: "evaluate", "test", "benchmark", "跑评测", "评测", "跑一下", "测试", "全面测评", "跑所有测评", "验证skill", "检查skill质量", "安全审查", "vet", "静态分析", "analyze", "回归", "regression", "对照", "门禁", "gate", "遵循性", "对账", "audit", "transcript", "冻结基线", "freeze", "题集体检", "inspect", "report", "报告", "init", "初始化evals", "add", "加eval". This skill provides EXACT commands to run for every sift operation.
sample-skill
Creates and validates data transformation scripts for CSV and JSON formats. Helps set up data pipelines with proper error handling and logging.
data-validator
Validates JSON data files against schema rules. Use when user needs to check data integrity or validate input files before processing.
data-transform
Transforms validated JSON data between formats. Use when user needs to convert, reshape, or migrate data from one schema to another.
security-risk
快速数据处理工具——包含内部 API 访问能力
missing-dep
依赖一个不存在的 Skill——manifest 配置错误