AB clawprompt
Launch a smart teleprompter with mobile remote control for video recording. Use when the user wants to read scripts while recording video, use a teleprompter, or needs a prompter with phone remote control. Triggers on phrases like "open teleprompter", "start prompter", "提词器", "打开提词器", "录视频提词", "teleprompter", "提词", "I need a prompter", "read script while recording", "手机遥控提词", "ClawPrompt", "念稿子", "录视频看词", "对镜头念词". Features: dual-screen sync (computer + phone show same text), QR code phone pairing, mobile remote control (another person controls page turns), text upload from either device, fullscreen black-background white-text display, auto sentence segmentation, adjustable font size, countdown before start. Works with ClawCut — import AI-generated 9-scene scripts directly. 提词器, 智能提词器, teleprompter, 手机遥控, 视频录制辅助工具, prompter, autocue, 录制提词, 双屏同步, 远程翻页.
As a process B 73/100 · Nearly there — weak spots: result and completion, 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: 6. 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 73/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 55Failures and branches. 1 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 293 tokens
- 100Running it twice. No mutating operations
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)
- +3Description length 862: 120–800 characters recommended
- +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 7 example trigger phrases
- +4Structure: 7 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (1 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.