BC video-content-operator
Use when a user wants help deciding what video/social content to make, how to package it for different platforms, which source materials or ideas are worth using, or what the next content move should be. This skill is for creator operating decisions above editing execution. It should be used for requests like: plan this week's content, decide which clips are worth turning into posts, package an idea for Xiaohongshu/Shorts/YouTube, generate draft content directions, compare angles, recommend the next post, or analyze a creator's current content situation. Before giving recommendations, first understand the user's current state: who they are, which platforms they are already using, what kinds of content they usually publish, and what problem they are trying to solve. In OpenClaw main sessions, proactively use memory files to understand the user before making recommendations. Do NOT use this skill for pure execution when the user already knows exactly what to edit; defer actual editing to sparki-video-editor or other execution tools.
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Shorten the description to 1024 characters.
- 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
- error
description-longdescription is 1046 chars, limit 1024 - warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Use when a user wants help deciding what video/social content to m… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Failures and branches. 9 branches
- 100Steps. 105 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1907 tokens
- low 12 top-level sections: this looks like several domains in one skill
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
- +3Description length 1046: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 24 headings
- +3Step-by-step instructions: 105 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.