CB modelselector-openclaw
Use when the OpenClaw Control UI chat model picker is one long flat provider-grouped list and picking a model is slow, when you have many providers each with many models, when the user wants a two-column provider/model picker (left = provider navigation, right = only that provider's models), when the per-chat account row (e.g. deepseek:default) should be hidden, or when a previously installed picker enhancement disappeared after an upgrade. Installs, repairs, verifies or uninstalls a browser-side enhancement injected into the Control UI's index.html.
Use when the OpenClaw Control UI chat model picker is one long flat provider-grouped list and picking a model is slow, when you have many providers each with…
As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, consistency
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 12
✓ No critical or high findings
Medium and low: 12
-
medium Dangerous commands
cmd-execpolicy-bypassREADME.md:77Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File scripts/pcl-…ps1
-
medium Dangerous commands
cmd-execpolicy-bypassREADME.md:103Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File scripts/pcl-…ps1 -Remove
-
medium Dangerous commands
cmd-execpolicy-bypassREADME.md:204Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File scripts/pcl-…ps1
-
medium Dangerous commands
cmd-execpolicy-bypassREADME.md:226Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File scripts/pcl-…ps1 -Remove
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read Write
-
medium Dangerous commands
cmd-execpolicy-bypassSKILL.md:85Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File scripts/pcl-…ps1
-
medium Dangerous commands
cmd-execpolicy-bypassSKILL.md:125Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File scripts/pcl-…ps1 -Remove
-
medium Dangerous commands
cmd-execpolicy-bypass说明.md:53Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File scripts\pcl-…ps1
-
medium Dangerous commands
cmd-execpolicy-bypass说明.md:87Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File scripts\pcl-…ps1 -Remove
-
low Dangerous commands
cmd-execpolicy-bypassscripts/pcl-patch.ps1:8Runs PowerShell with execution policy bypassed (code comment)# powershell -ExecutionPolicy Bypass -File pcl-…ps1 # 安装/修复
comment -
low Dangerous commands
cmd-execpolicy-bypassscripts/pcl-patch.ps1:9Runs PowerShell with execution policy bypassed (code comment)# powershell -ExecutionPolicy Bypass -File pcl-…ps1 -Remove # 卸载
comment -
low Dangerous commands
cmd-execpolicy-bypassscripts/pcl-patch.ps1:10Runs PowerShell with execution policy bypassed (code comment)# powershell -ExecutionPolicy Bypass -File pcl-…ps1 -Dist "<...>\dist\control-ui"
comment
Files scanned: 12. 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 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (modelselector-openclaw) differs from the folder (modelselectoropenclaw)
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 44 steps
- 100Execution cost. Instruction body is 3243 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (7 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
- +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
- -31 of 4 scripts are never mentioned in SKILL.md
- +3Description length 556: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 44 items
- +4Has examples (4 code blocks)
- +1License stated
- +2Bilingual instructions (RU + EN)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.