AC tierlist-video-maker
Turn a published TierVibe tier list into a narrated video. Fetches tier list data and card images from a TierVibe URL, captures a HIGH-RESOLUTION board image from the public page (Playwright, no server call — the whole-image export is a user-side action, automated), uses AI vision to identify each card, generates a narration script (user-reviewable), produces TTS audio with subtitles, and composes a video with a scrolling tier-list background where each card is shown enlarged while narrated. Use when the user wants to make/create a video from a TierVibe tier list, turn a tier list into a video, or narrate/explain a tier list ranking. Triggers: "tier list video", "tiervibe video", "tier list 做成视频", "排行榜视频", "tier list 讲解视频".
Turn a published TierVibe tier list into a narrated video.
As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 10. 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 63/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 13 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4813 tokens
- 100Steps. 55 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- high The skill tells the model to perform an irreversible action with no human approval
- 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
- +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 4 example trigger phrases
- +3Description length 733: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 55 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 7 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.