BF video-viral-pipeline
把一条外语长视频一键做成中文字幕成片，并自动切成多条"独立成爆款"的 9:16 竖屏短片（带钩子标题+gpt-image 封面），可选一键发布到微信视频号 / 抖音 / 小红书 / 公众号四个平台。当用户说"翻译视频并切片""做爆款切片""视频号一条龙""发抖音小红书""把这个 YouTube 链接做成短视频矩阵"时使用。
把一条外语长视频一键做成中文字幕成片，并自动切成多条"独立成爆款"的 9:16 竖屏短片（带钩子标题+gpt-image 封面），可选一键发布到微信视频号 / 抖音 / 小红书 / 公众号四个平台。当用户说"翻译视频并切片""做爆款切片""视频号一条龙""发抖音小红书""把这个 YouTube…
As a process F 33/100 · Will not run — References files that are not bundled: examples/get_<平台>_cookie.py
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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 · 3
-
high Exfiltration
intent-browser-credential-storeSKILL.md:35Accesses a browser credential / cookie storeyt-dlp --cookies-from-browser chrome -f "bv*[height<=1080]+ba/b[height<=1080]" \
Medium and low: 2
-
medium Exfiltration
intent-browser-credential-storeSKILL.md:38Accesses a browser credential / cookie store (quoted — discussed, not commanded)- YouTube 报"Sign in to confirm you're not a bot"→ 加 `--cookies-from-browser chrome`。
quoted -
low Dangerous commands
cmd-shell-rcscripts/setup.sh:11Writes to a shell startup file (string literal in code, not executed)echo " 提示：把 ffmpeg-full 放进 PATH 前面：echo 'export PATH=\"/usr/local/opt/ffmpeg-full/bin:\$PATH\"' >> ~/.zshrc"
code literal
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: examples/get_<平台>_cookie.py
Process rating: all ten parameters 33/100
- 0Tools and files. 1 referenced file(s) missing: examples/get_<平台>_cookie.py
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 100Steps. 37 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1229 tokens
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
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 162: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (6 code blocks)
- +3All 8 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.