AF tencentcloud-lighthouse-skill
Load when: user mentions Lighthouse, 轻量应用服务器, 轻量服务器, or asks to check/create/manage/deploy Lighthouse instances, deploy applications to Lighthouse, manage Lighthouse firewall rules, reset Lighthouse password, view Lighthouse snapshots/images/traffic, monitor Lighthouse metrics, run commands on Lighthouse via TAT, or asks to get/identify the current instance ID. Trigger phrases: "查看轻量服务器", "Lighthouse实例", "轻量应用服务器", "部署应用", "部署程序", "部署到Lighthouse", "管理防火墙规则", "重置密码", "查看快照", "查看流量包", "获取实例ID", "查看实例ID", "当前实例", "实例IP", "check Lighthouse", "create Lighthouse", "deploy app", "deploy application", "Lighthouse firewall", "Lighthouse snapshot", "instance ID", "whoami". NOT for CVM, CBS, VPC, or other non-Lighthouse products.
As a process F 60/100 · Will not run — References files that are not bundled: url
How to improve
- 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 · 4
✓ No critical or high findings
Medium and low: 4
✓ Guard found no suspicious behaviour. 4 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: url
Process rating: all ten parameters 60/100
- 0Tools and files. 1 referenced file(s) missing: url
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 10 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 29 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1797 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 15 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 728: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.