BD sls-trace-analysis
查询阿里云SLS日志和ARMS调用链，结合源码和数据库进行全链路问题排查。 完整流程：查日志 → 画调用链 → 定位源码 → 排查数据库 → 给出修复方案。 Use when: 用户说「分析sls」「分析问题」或想排查业务服务/线上接口/用户请求的报错或异常。 触发示例：「分析sls」「帮我查一下这个trace_id」「分析一下这个trace_id」 「查一下这个用户的请求」「wusid 是 xxx」「uid xxx」 「查一下 /path/to/api 这个接口的报错」「帮我排查一下这个业务报错」「线上有个接口挂了」 「帮我分析一下这个报错的代码」「数据库报错了」「SQL超时」「查一下这个接口为什么慢」。 IMPORTANT: trace_id = 染色ID = 业务调用链ID = requestId，这些都是同一个东西， 统一用 trace_id 表述。用户提供的 trace_id 是业务系统的外部 trace，不是 OpenClaw 内部 session ID， 不要自行分析 trace_id 的来源或归属，必须调用此 skill 去 SLS/ARMS 查询。 NOT for: 查询OpenClaw自身状态、分析OpenClaw系统问题、搜索本地文件、openclaw内置命令。
As a process D 47/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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.
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 · 1
-
high Obfuscation
uni-zero-widthSKILL.md:559Zero-width / invisible characters (possible hidden text) (4 occurrences)␀```{language}
Files scanned: 6. 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 47/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 76 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3841 tokens
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
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -221 emoji in the instructions: noise for the model
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 550: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 76 items
- +4Has examples (31 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.