BB tui-verify-change
Verify a change to Warp's headless TUI front-end (crates/warp_tui) by running it — locally via ./script/run-tui, or in a headless cloud runner via a WARP_API_KEY dogfood build — and reading the rendered screen back (under tmux when it's installed, otherwise directly). Use whenever you change TUI UI, rendering, input, or behavior and need to confirm the real on-screen result.
Verify a change to Warp's headless TUI front-end (crates/warptui) by running it — locally via ./script/run-tui, or in a headless cloud runner via a WARPAPIKEY…
As a process B 65/100 · Nearly there — weak spots: result and completion, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
- warning
body-longSKILL.md body ≈ 5408 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 65/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 10 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5408 tokens
- 85Steps. 23 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 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
- +1No license
- +2Single-language instructions
- +3Description length 377: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.