AF multi-source-data-cleaner
EN: Production-grade data cleaning across heterogeneous sources (CSV/Excel/JSON/Parquet/SQL dumps/log files). Profiles schemas, detects encoding/delimiter, normalizes types, handles missing values, deduplicates fuzzy records, reconciles schema across sources, and outputs a clean unified dataset plus a full data-quality report. Use when user provides one or more dirty datasets and asks "清洗数据 / 合并数据 / 去重 / 缺失值处理 / data cleaning / dedup / schema reconcile". 中文：跨异构来源（CSV/Excel/JSON/Parquet/SQL 导出/日志文件）的工业级数据清洗。剖析 schema、自动识别编码与分隔符、归一化类型、处理缺失值、模糊去重、跨源字段对齐，输出统一的干净数据集与完整数据质量报告。当用户提供脏数据并要求"清洗/合并/去重/缺失值处理"时触发。
EN: Production-grade data cleaning across heterogeneous sources (CSV/Excel/JSON/Parquet/SQL dumps/log files).
As a process F 40/100 · Will not run — References files that are not bundled: templates/missing_strategy.json, scripts/reconcile_schema.py
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: templates/missing_strategy.json - warning
missing-refreference to a missing file: scripts/reconcile_schema.py
Process rating: all ten parameters 40/100
- 0Tools and files. 2 referenced file(s) missing: templates/missing_strategy.json, scripts/reconcile_schema.py
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 8 mutating operations with no state check
- 40Consistency. Frontmatter name (multi-source-data-cleaner) differs from the folder (multi-source-data-cleaner-pro)
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 50 steps, 1 vague phrases
- 100Execution cost. Instruction body is 1754 tokens
- 100Progress reporting. Reports progress
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 608: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 50 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.