AD csv-tools
CSV 工具集 v1.1.0 — 子命令+安全增强。 预览、筛选、排序、合并、分割、去重、验证、统计、 列操作(重命名/选择/计算列)、类型检测、数据画像、抽样。 纯Python标准库(csv模块)，无外部依赖。 Use when: - 需要快速处理CSV文件（预览/筛选/排序/统计） - 合并多个CSV文件或分割大CSV文件 - CSV数据去重、列操作、类型检测、数据画像 Do NOT use when: - 非CSV格式数据（JSON/YAML/Excel/数据库） - 需要写回原始输入文件 - 简单的数据查看（推荐用 cat/head 等系统命令） 🎉 v1.1.0 新增子命令: - stats — 列统计(sum/avg/min/max/std/中位数) - columns — 列操作(重命名/选择/添加计算列) - detect — 数据类型自动检测 - profile — 数据画像(缺失率条形图/唯一值/分布) - sample — 随机抽样(head/tail/random/systematic) v1.0.0 子命令: - preview / filter / sort / merge / split / dedup / validate 触发关键词：CSV文件操作、CSV格式转换、CSV数据清洗、CSV合并拆分、CSV验证统计 Do not trigger for: 非CSV格式数据处理、数据库操作、JSON/YAML/XML处理、图片处理 适用范围：CSV / TSV 格式数据文件 运行模式：纯本地，无网络请求 ❎ 外部依赖：Python标准库（无需额外安装）
CSV 工具集 v1.1.0 — 子命令+安全增强。 预览、筛选、排序、合并、分割、去重、验证、统计、 列操作(重命名/选择/计算列)、类型检测、数据画像、抽样。 纯Python标准库(csv模块)，无外部依赖。 Use when: - 需要快速处理CSV文件（预览/筛选/排序/统计） -…
As a process D 47/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 47/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 20 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 905 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 707: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.