DB huawei-cloud-rds-smart-service
Huawei Cloud RDS (Relational Database Service) full-scenario intelligent service covering all database engines (MySQL, PostgreSQL, SQL Server, MariaDB, GaussDB for MySQL, TaurusDB). Provides six capability domains: (1) Basic intelligent Q&A for RDS product features, best practices, and specifications; (2) SQL statement performance optimization with slow log analysis, top SQL, execution plan guidance, and index recommendations; (3) Database instance daily O&M including health inspection, restart, flavor resize, disk expansion, primary-standby switchover, and read replica management; (4) Online fault localization and troubleshooting via error logs, replication status, connection diagnostics, and recovery time window; (5) Parameter tuning with parameter group management, modification suggestions, and performance parameter adjustment guidance; (6) Backup and recovery guidance including backup policy management, manual backup creation, restore to new/existing instance, and point-in-time recovery. Uses CLI→SDK→API three-level fallback for maximum compatibility. All mutating operations require explicit user confirmation. Triggers include: "RDS","关系型数据库","数据库实例","慢SQL","SQL优化","数据库运维","数据库故障","故障排查","参数调优","备份恢复","数据库巡检","RDS诊断","数据库诊断","DBA","数据库性能","主从延迟","连接数","数据库备份","数据恢复","RDS智能服务","database instance","RDS troubleshooting","slow query","SQL performance","database backup","parameter tuning","RDS ops","database diagnose".
As a process B 70/100 · Nearly there — weak spots: when it triggers, 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 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
- 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.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Shorten the description to 1024 characters.
- 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
-
high Dangerous commands
cmd-pipe-to-shellreferences/cli-installation-guide.md:8Downloads and executes remote code from an unrecognised host (pipe to shell)curl -sSL https://obs.…com/hcloud_client/hcloud_install.sh | bash
-
high Dangerous commands
cmd-pipe-to-shellreferences/cli-installation-guide.md:14Downloads and executes remote code from an unrecognised host (pipe to shell)curl -sSL https://obs.…com/hcloud_client/hcloud_install.sh | bash
-
high Dangerous commands
cmd-pipe-to-shellreferences/cli-installation-guide.md:20Downloads and executes remote code from an unrecognised host (pipe to shell)curl -sSL https://obs.…com/hcloud_client/hcloud_install.sh | bash
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1442 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5511 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 70/100
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 12 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5511 tokens
- 100Steps. 47 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low 11 top-level sections: this looks like several domains in one skill
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)
- +3Description length 1441: 120–800 characters recommended
- -33 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Structure: 26 headings
- +3Step-by-step instructions: 47 items
- +3Output format is stated explicitly
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 43.