CF metric-attribution
对指标波动进行综合归因诊断，定位导致指标变化的关键因子、维度和外部事件。当用户需要分析指标波动原因、定位指标变化的根因、做因子拆解归因（如 GMV = UV × 转化率 × 客单价）、或理解指标为什么涨跌时，必须使用此 Skill。 触发场景包括但不限于：用户提到"归因""归因分析""波动分析""波动归因""根因分析""根因""下钻分析""下钻归因""为什么涨了""为什么跌了""为什么下降""为什么增长""什么原因""哪个维度导致""贡献度分析""贡献度""因子拆解""因子分解""驱动因素""影响因素""变化原因""差异分析"，或用户对某个指标的变化表达了疑问、希望了解变化背后的原因时，都应使用此 Skill。 即使用户没有直接说"归因"二字，只要其意图是理解指标变化的原因或定位问题维度，也应触发此 Skill。 **重要：本 Skill 通过组合调用 Gateway API 获取指标数据，在本地进行归因计算，结合外部事件检索，最终输出综合归因诊断报告。构建查询前，必须先通过 Gateway API 检索相关指标和维度信息，禁止凭记忆猜测指标名或维度名。**
As a process F 34/100 · Will not run — References files that are not bundled: {waterfall_chart_path}
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Exfiltration
net-credential-useSKILL.md:76Credential used in a network call (verify the destination is the intended service)> curl -H "X-API-Key: $CAN_API_KEY" "https://gateway.can.aloudata.com/api/metrics/search?pageSize=5" --data-urlencode "keyword=销售额" -G
-
medium Exfiltration
net-credential-useSKILL.md:77Credential used in a network call (verify the destination is the intended service)> curl -H "X-API-Key: $CAN_API_KEY" "https://gateway.can.aloudata.com/api/metrics/retail_amt/dimensions"
-
medium Exfiltration
net-credential-useSKILL.md:79Credential used in a network call (verify the destination is the intended service)> curl -H "X-API-Key: $CAN_API_KEY" "https://gateway.can.aloudata.com/api/metrics/retail_amt/dimensions" --data-urlencode "keyword=渠道,地区,品牌" -G
-
medium Exfiltration
net-credential-useSKILL.md:121Credential used in a network call (verify the destination is the intended service)curl -H "X-API-Key: $CAN_API_KEY" "https://gateway.can.aloudata.com/api/metrics/search?pageSize=5" --data-urlencode "keyword=销售额" -G
-
medium Exfiltration
net-credential-useSKILL.md:177Credential used in a network call (verify the destination is the intended service)curl -H "X-API-Key: $CAN_API_KEY" "https://gateway.can.aloudata.com/api/metrics/search?pageSize=10" --data-urlencode "keyword=UV,转化率,客单价,购买人数" -G
Files scanned: 3. 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
missing-refreference to a missing file: {waterfall_chart_path} - note
frontmatter-keyunknown frontmatter key "permissions" - note
frontmatter-keyunknown frontmatter key "env_vars" - note
frontmatter-keyunknown frontmatter key "domain_whitelist" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "metadata.openclaw"
Process rating: all ten parameters 34/100
- 0Tools and files. 1 referenced file(s) missing: {waterfall_chart_path}
- 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
- 20When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 4159 tokens
- 100Steps. 50 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -229 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 486: enough signal without eating the budget
- +4Structure: 40 headings
- +3Step-by-step instructions: 50 items
- +4Has examples (17 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.