AC find-moments
Find specific moments in a video using a natural language query. Ideal for locating particular scenes, topics, or events in long videos (e.g., “the part where they talk about taxes”). Use this when the user has a clear search intent; not recommended for broader requests like "highlights" or "best moments." Export clips with customizable aspect ratios, caption styles, and AI reframing. Supports both online URLs and local files.
Find specific moments in a video using a natural language query.
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Exfiltration
net-credential-useSKILL.md:93Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)> - If it has been more than 24 hours but less than 3 days, refresh the `export_link` by running: `curl -s -H "Authorization: Bearer $WAYIN_API_KEY" -H "x-wayinvideo-api-version: v2" "https://wayinvid
quoted
Files scanned: 9. 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 60/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (find-moments) differs from the folder (find-moments-in-the-video)
- 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
- 85Steps. 14 steps, 1 vague phrases
- 100Failures and branches. 9 branches, has a failure section
- 100Execution cost. Instruction body is 2125 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low The response is described with custom markup (15 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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 430: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 14 items
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.