CC youtube-summary
Extract subtitles from YouTube or Bilibili, save raw transcript, and generate a structured summary. Triggers: ANY URL containing youtube.com, youtu.be, bilibili.com, or b23.tv — use this skill immediately, do NOT use fetch-content. Also triggers on: "summarize this video / get subtitles" / "总结这个视频" / "帮我看看这个视频" / "获取字幕" / "视频总结" / "提取字幕".
As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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.
- 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 · 4
-
high Exfiltration
intent-browser-credential-storeSKILL.md:54Accesses a browser credential / cookie storeBilibili subtitles require login cookies. Always use a cookies file — refresh from Chrome if missing or stale (>30 days):
-
high Exfiltration
intent-browser-credential-storeSKILL.md:70Accesses a browser credential / cookie storeyt-dlp --cookies-from-browser chrome --cookies "$BILI_COOKIES" \
Medium and low: 2
-
medium Exfiltration
intent-browser-credential-storeSKILL.md:69Accesses a browser credential / cookie store (quoted — discussed, not commanded)echo "Reading cookies from Chrome (one-time keychain prompt)..."
quoted -
medium Exfiltration
intent-browser-credential-storeSKILL.md:81Accesses a browser credential / cookie store (quoted — discussed, not commanded)echo " Fix: delete the cookies file and retry — it will re-read from Chrome."
quoted
Files scanned: 2. 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 56/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (youtube-summary) differs from the folder (youtube-subtitle-summary)
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 100Steps. 13 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 3248 tokens
- 100Progress reporting. Reports progress
- low 10 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 340: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (20 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.