BC panel
Open the read-only Ralphy side panel in the agent host's built-in browser, next to the chat: live job activity (running, failed, queued, done) and trend references to copy (picks with evidence, rising signals, top videos, formats and hooks per niche). USE WHEN the user asks to see what Ralphy is doing, wants a panel / dashboard / side view of jobs or renders, wants to browse trends or references visually, or asks to open Ralphy in the browser next to the chat. TRIGGER (EN): "open the panel", "show me what ralphy is doing", "open ralphy on the right", "show trends in the browser", "trend dashboard", "where is my render". DO NOT FIRE for a one-off answer the CLI gives directly (one job's status, one niche report) unless the user wants to watch it.
The skill promises to open a read-only Ralphy panel in the agent's browser—showing live job status (running, failed, queued, done) and trend references with sources. One file, no lint errors, quality score 86. Process score sits at 61, though, which signals trigger logic may not fire reliably. Triggers are documented ("open the panel", "show trends in the browser"), but the actual panel-opening mechanism isn't spelled out in the files. No model runs, no sandbox tests. Platform coverage is broad: Claude through OpenClaw.
Useful if you're tired of checking Ralphy's status in the CLI. The low process score means it won't always catch your requests—test it on your own prompts before relying on it in production.
Open the read-only Ralphy side panel in the agent host's built-in browser, next to the chat: live job activity (running, failed, queued, done) and trend…
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "namespace"
Process rating: all ten parameters 61/100
- 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
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 833 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low The response is described with custom markup (9 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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 755: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.