AC video-download
使用 yt-dlp 与 FFmpeg 下载、保存、检查或提取公开视频、独立音频、最佳原语言字幕及最高质量原始封面，并为后续字幕翻译准备确定性的隐藏输入。Use when Codex is asked to inspect formats, download permitted media with its best source thumbnail, audio, and source subtitle when available, or prepare deterministic inputs for the video translation workflow; confirm quality, path, and filename before downloading.
As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Obfuscation
obf-hex-escape-chainskill-card.md:33Escaped/char-code string obfuscation- [Video translation workflow documentation](https://github.com/aiaaaa4/ai-landing-skills/blob/main/docs/video-translate/%E8%A7%86%E9%A2%91%E7%BF%BB%E8%AF%91%E5%B7%A5%E4%BD%9C%E6%B5%81%E8%AF%B4%E6%98%
-
low Obfuscation
obf-hex-escape-chainscripts/preflight.py:18Escaped/char-code string obfuscation (quoted — discussed, not commanded)必读：翻译流程会自动提取音频并上传到 OkFile，生成供 Fun-ASR 调用的临时公开链接，以获得词级时间戳，并支持后续 AI 语义划分、修正和质检。ASR 固定使用阿里百炼 Fun-ASR；翻译可选择通过 API 调用阿里百炼旗舰翻译模型 `qwen-mt-plus`，或直接使用当前 Agent 的模型额度。若当前环境支持，推荐在 Codex 中使用 GPT-5.6 以追求更高质量。更多信息
quoted
Files scanned: 4. 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 50/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 9 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Failures and branches. 4 branches
- 100Steps. 31 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2502 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 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 343: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (11 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.