BF content-collector
个人内容收藏与知识管理系统。收藏、整理、检索、二创。 Use when: (1) 用户分享链接/文字/截图并要求保存或收藏, (2) 用户说"收藏这个"/"存一下"/"记录下来"/"save this"/"bookmark"/"clip this", (3) 用户要求按关键词/标签搜索之前收藏的内容, (4) 用户要求基于收藏内容生成小红书/社交媒体文案（二创/改写/洗稿）, (5) 用户发送 URL 并要求提取/总结/摘要内容, (6) 用户提到"之前看过一个..."/"上次收藏的..."等回忆性检索, (7) 用户转发或粘贴了一段内容（文章片段/推文/视频链接）并暗示想留存。 即使用户没有明确说"收藏"，只要涉及保存外部内容、整理知识、检索历史收藏、 或基于已收藏内容进行二次创作，都应使用此技能。 已支持来源：博客、X/Twitter、网页、B站视频。 内容类型：文字、长视频（B站可自动转录）、短视频。
个人内容收藏与知识管理系统。收藏、整理、检索、二创。 Use when: (1) 用户分享链接/文字/截图并要求保存或收藏, (2) 用户说"收藏这个"/"存一下"/"记录下来"/"save this"/"bookmark"/"clip this", (3) 用户要求按关键词/标签搜索之前收藏的内容, (4)…
As a process F 33/100 · Will not run — References files that are not bundled: images/{slug}/filename.png
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.
- The text references files that are not there: add them or drop the references.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
-
high Exfiltration
intent-browser-credential-storescripts/bilibili_transcribe.sh:29Accesses a browser credential / cookie storeyt-dlp --cookies-from-browser chrome \
Medium and low: 1
-
medium Exfiltration
intent-browser-credential-storescripts/bilibili_subtitle.py:113Accesses a browser credential / cookie store (quoted — discussed, not commanded)"~/Library/Application Support/Google/Chrome/Default/Cookies"
quoted
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: images/{slug}/filename.png
Process rating: all ten parameters 33/100
- 0Tools and files. 1 referenced file(s) missing: images/{slug}/filename.png
- 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. 1 mutating operations with no state check
- 100Steps. 117 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2395 tokens
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (21 tags): a typed call is more reliable
- medium 3 test cases, all positive: not one "should refuse" or "should ask first"
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
- -31 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 409: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 117 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.