AB aws-fis-experiment-prepare
Use when the user wants to prepare, create, or generate an AWS FIS (Fault Injection Service) experiment configuration. Triggers on "prepare FIS experiment", "create FIS experiment for [scenario]", "generate chaos experiment config", "准备 FIS 实验", "生成 [scenario] 混沌实验配置", "create experiment template for AZ power interruption", "set up fault injection test". Covers Scenario Library pre-built scenarios (AZ Power Interruption, AZ Application Slowdown, Cross-AZ Traffic Slowdown, Cross-Region Connectivity), custom single FIS actions (aws:rds:failover-db-cluster, aws:ec2:stop-instances, etc.), and SSM Automation-based fault injection for Amazon MSK (broker reboot) and ElastiCache Redis/Valkey (primary node reboot, replication group failover).
As a process B 74/100 · Nearly there — weak spots: running it twice, progress reporting
How to improve
- 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
-
low Secrets in code
secret-high-entropy-tokenreferences/az-power-interruption-guide.md:255High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)| `AWSF…ess` | Stop/Start instances, KMS grants for encrypted EBS, SSM commands |
detectortable -
low Secrets in code
secret-high-entropy-tokenreferences/cfn-base-template.md:65High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)| `aws:…ces`, `aws:…ces`, `aws:…pi-*`, `aws:…sg-*` | `AWSF…ess` |
detectortable -
low Secrets in code
secret-high-entropy-tokenreferences/cfn-base-template.md:72High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)| `aws:ebs:*` | `AWSF…ess` (EBS actions are covered by the EC2 policy) |
detectortable
Files scanned: 14. 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 74/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 31 mutating operations with no state check
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4776 tokens
- 100Steps. 74 steps
- 100Failures and branches. 7 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
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)
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 743: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 74 items
- +3Output format is stated explicitly
- +4Has examples (13 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 99.