BC alibabacloud-db-cost-diagnosis
Read-only cost diagnostics and audits for Alibaba Cloud database products (RDS, Redis, MongoDB, PolarDB, DTS, DBS, CDT): explain a high or spiking DB bill with billing-item breakdowns and month-over-month anomaly attribution, and run proactive audits of renewal/expiry risk, idle instances, and optional paid features — never modifying any resource. Triggers: "why is my database bill so high", "DB cost spike", "database cost anomaly", "database bill surged", "unexpected database charges", "unexplained database charge", "don't know what feature is charging me", "RDS bill breakdown", "billing item breakdown", "charged after instance deleted", "released instance still billed", "monthly DB cost trend", "cost increase root cause", "CDT bill", "cost audit", "database cost audit", "idle database instance", "idle instance still charging", "renewal lock", "about to expire", "unexpected auto-renewal charge", "DMS charges", "DAS billing".
Read-only cost diagnostics and audits for Alibaba Cloud database products (RDS, Redis, MongoDB, PolarDB, DTS, DBS, CDT): explain a high or spiking DB bill…
As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securityreferences/module1_cost_query.md:41Offensive-security / dual-use content (legitimate for authorised testing; review intended use)do not attempt any privilege escalation.
-
low Risky intent
intent-offensive-securityreferences/ram-policies.md:31Offensive-security / dual-use content (legitimate for authorised testing; review intended use)for rows 4-5; there is no privilege escalation because both resolve to the
Files scanned: 16. 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 ≈ 5714 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 30 mutating operations with no state check
- 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 5714 tokens
- 85Steps. 29 steps, 1 vague phrases
- 100Failures and branches. 2 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 (8 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)
- +3Description length 939: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -32 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 23 example trigger phrases
- +4Structure: 20 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.