BB alibabacloud-migration-lhm-migrate-hive-to-paimon
Hive 到阿里云 DLF Paimon 数据迁移工具，覆盖存量迁移与增量迁移全流程。存量迁移：Hive DDL 自动转换为 Paimon DDL 与 format-table 外表、rclone 同步 HDFS 到 OSS、Spark Thrift Server 执行 INSERT OVERWRITE，支持 orc/parquet/csv/json/text；提供 --auto-create-db、--force、--max-parallel 并行、--verify 行数校验、--direct-read 直读模式（OSS-HDFS/DLS 场景跳过 rclone）、迁移报告自动生成。增量迁移：三阶段流水线（DDL → rclone → INSERT）执行 hive-exploration 增量探查结果。内置独立 ddl_converter 支持 Hive DDL 快速转换为 DLF Paimon/FORMAT 外表 DDL。使用场景：用户提到"存量迁移"、"增量迁移"、"增量同步"、"Hive Paimon 迁移"、"Paimon 建表"、"Hive 数据湖迁移"、"format-table"、"direct-read"、"hive-to-paimon"、"migration-lhm-migrate-hive-to-paimon"、"转换 Hive DDL"、"建 DLF 表"、"生成 Paimon/外表 DDL"、"表记录数统计SQL"时调用此 skill。
Hive 到阿里云 DLF Paimon 数据迁移工具，覆盖存量迁移与增量迁移全流程。存量迁移：Hive DDL 自动转换为 Paimon DDL 与 format-table 外表、rclone 同步 HDFS 到 OSS、Spark Thrift Server 执行 INSERT OVERWRITE，支持…
As a process B 65/100 · Nearly there — weak spots: when it triggers
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:264Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)# Generic: curl https://rclone.org/install.sh | bash
vendor-host -
low Dangerous commands
cmd-pipe-to-shellscripts/common.py:1190Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; the skill's own vendor host)'curl -s https://rclone.org/install.sh | bash',
code literalvendor-host -
low Dangerous commands
cmd-pipe-to-shellscripts/common.py:1201Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; the skill's own vendor host)print(" 通用: curl https://rclone.org/install.sh | bash")code literalvendor-host
Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5097 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 65/100
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5097 tokens
- 85Steps. 51 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 21 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
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)
- -32 of 9 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +3Description length 641: enough signal without eating the budget
- +4Structure: 43 headings
- +3Step-by-step instructions: 51 items
- +3Output format is stated explicitly
- +4Has examples (20 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.