BF umeng-cli-uapp-retention
友盟 U-App 留存率查询技能，支持通过 umeng-cli call 调用友盟 OpenAPI（gateway.open.umeng.com）的 1 个只读留存接口，覆盖新增/活跃用户的次日/3日/7日/14日/30日留存率查询、版本与渠道维度的留存对比分析。当用户需要查询应用留存率、次日留存、7日留存、版本/渠道留存对比时使用。
As a process F 29/100 · Will not run — References files that are not bundled: ../../../umeng-cli/SKILL.md, ../../../umeng-cli/reference/openapi/uapp.md, ../umeng-cli-uapp-channel-version/SKILL.md
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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:53Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/umeng/umeng-cli/main/scripts/install.sh | sh
Files scanned: 2. 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: ../../../umeng-cli/SKILL.md - warning
missing-refreference to a missing file: ../../../umeng-cli/reference/openapi/uapp.md - warning
missing-refreference to a missing file: ../umeng-cli-uapp-channel-version/SKILL.md - warning
missing-refreference to a missing file: ../umeng-cli-uapp-core-index/SKILL.md - warning
missing-refreference to a missing file: ../umeng-cli-uapp-event/SKILL.md
Process rating: all ten parameters 29/100
- 0Tools and files. 5 referenced file(s) missing: ../../../umeng-cli/SKILL.md, ../../../umeng-cli/reference/openapi/uapp.md, ../umeng-cli-uapp-channel-version/SKILL.md
- 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
- 40Consistency. Frontmatter name (umeng-cli-uapp-retention) differs from the folder (uapp-retention)
- 70Execution cost. Instruction body is 4135 tokens
- 100Steps. 58 steps
- 100Running it twice. No mutating operations
- low 13 top-level sections: this looks like several domains in one skill
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
- +1No license
- +2Single-language instructions
- +3Description length 168: enough signal without eating the budget
- +4Structure: 35 headings
- +3Step-by-step instructions: 58 items
- +4Has examples (14 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.