DC alibabacloud-lakehouse-migration
Unified dispatch entry point for the LHM (Lakehouse Migration Center) skill, coordinating the three core capabilities of SQL conversion, data validation, and big-data workflow migration. Use when the user raises a lakehouse migration requirement, such as SQL dialect conversion (e.g., "presto to spark", "hive to maxcompute", "转换 SQL", "SQL 转换", "方言转换"), pre/post-migration data validation / data consistency comparison ("数据校验", "数据比对", "一致性检查", "跑校验", "数据量校验", "指标校验"), migration of scheduled workflows such as DataWorks/DolphinScheduler/Airflow ("工作流迁移", "调度任务迁移", "建数据源", "创建数据源", "把 X 迁移到 Y"), or when the user is unsure which sub-skill to use or needs cross-skill collaboration.
Unified dispatch entry point for the LHM (Lakehouse Migration Center) skill, coordinating the three core capabilities of SQL conversion, data validation, and…
As a process C 55/100 · Has gaps — References files that are not bundled: references/manifest.json, references/ram-policies.md, scripts/requirements.txt
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
-
high Concealment
en-hide-from-userSKILL.md:222Instruction to hide actions from the user- Installing or running any sub-skill CLI (`uv tool install`, `pip install`, `lhm-sch-ds`, `lhm-sch-env`, `lhm-sch-deploy`, `lhm-sch-read-exec`, the data-validation scripts, `lookup_rules.py`). **A su
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8291 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: references/manifest.json - warning
missing-refreference to a missing file: references/ram-policies.md - warning
missing-refreference to a missing file: scripts/requirements.txt - warning
missing-refreference to a missing file: scripts/install_lhm_plugin.sh
Process rating: all ten parameters 55/100
- 0Tools and files. 4 referenced file(s) missing: references/manifest.json, references/ram-policies.md, scripts/requirements.txt
- 0Result and completion. Does not say what the result is
- 40Execution cost. Instruction body is 8291 tokens: crowds the task out of the window
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 88 steps, 1 vague phrases
- 100Failures and branches. 7 branches, has a failure section
- 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 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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)
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 683: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 88 items
- +4Has examples (18 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.