AC agent-tab-title
Patch a locally installed OpenClaw Control UI so the browser tab title shows the active agent name (e.g. "Milly · OpenClaw") instead of the static "OpenClaw Control". Use when the user wants to disambiguate multiple OpenClaw Control UI browser tabs / Cmd-` switcher entries for multi-agent setups, asks how to make Control UI tab title dynamic, asks to install / apply / remove / re-apply this tab-title local patch, or to restore the patch after `openclaw update` overwrote dist files. Mirrors upstream PR openclaw/openclaw#80944 as a zero-build local override that survives by re-running apply.sh after each upgrade.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
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 · 0
✓ No critical or high findings
Files scanned: 3. 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 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 16 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 730 tokens
- 100Running it twice. Mutating operations check current state
- low The response is described with custom markup (3 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
- +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
- +5Description quotes 2 example trigger phrases
- +3Description length 618: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.