BA alibabacloud-emr-starrocks-assistant
Alibaba Cloud EMR Serverless StarRocks development & operations assistant. Covers five scenarios: cluster connection, schema design, data ingestion, SQL development & tuning, and cluster health diagnostics. Use this Skill when users ask about StarRocks table design, writing SQL, choosing an ingestion method, query execution plans, materialized views, cluster health checks, FE/BE/CN node status, tablet health, or compaction. Typical scenarios: table design, Stream Load / Routine Load / Broker Load selection, SQL optimization, window functions, CTEs, JOIN tuning, materialized view design, cluster health inspection, node-down diagnosis. Not applicable for: StarRocks instance lifecycle management (create / scale / restart / config change / version upgrade — these are control-plane operations, please use the EMR Serverless console or the corresponding OpenAPI), or other Alibaba Cloud products (EMR Cluster, Spark, Milvus, ClickHouse, Doris, RDS, ECS).
As a process A 81/100 · Runs to the end — weak spots: running it twice
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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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.
- 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
-
high Obfuscation
uni-zero-widthreferences/sql.md:103Zero-width / invisible characters (possible hidden text) (4 occurrences)␀```sql
Medium and low: 2
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostreferences/connect.md:43Pipe-to-shell installer from a well-known host (still executes remote code)curl -LsSf https://astral.sh/uv/install.sh | sh
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read
Files scanned: 37. 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 81/100
- 30Running it twice. 20 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4953 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 67 steps
- 100Failures and branches. 7 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 959: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 20 headings
- +3Step-by-step instructions: 67 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.