CC baoyu-skills
宝玉分享的 Claude Code 技能集，包含多个内容生成和处理子技能。 子技能列表 (skills/baoyu-*): - baoyu-article-illustrator: 文章插图生成 - baoyu-comic: 漫画生成 - baoyu-compress-image: 图片压缩 - baoyu-cover-image: 封面图生成 - baoyu-danger-gemini-web: Gemini网页抓取 - baoyu-danger-x-to-markdown: X帖子转Markdown - baoyu-format-markdown: Markdown格式化 - baoyu-image-gen: AI图片生成 - baoyu-infographic: 信息图生成 - baoyu-markdown-to-html: Markdown转HTML - baoyu-post-to-wechat: 发送微信文章 - baoyu-post-to-weibo: 发送微博 - baoyu-post-to-x: 发送X帖子 - baoyu-slide-deck: PPT/幻灯片生成 - baoyu-translate: 翻译 - baoyu-url-to-markdown: URL转Markdown - baoyu-xhs-images: 小红书图片处理 触发词示例： - "用baoyu生成一张图片" - "把XX网页转成markdown" - "生成XX的PPT"
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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.
- 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 · 9
-
high Exfiltration
intent-browser-credential-storeCLAUDE.md:35Accesses a browser credential / cookie store- **Gemini Web auth**: Browser cookies (first run opens Chrome for login, `--login` to refresh)
Medium and low: 8
-
medium Dangerous commands
cmd-pipe-to-shellCHANGELOG.md:276Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)- Remove `curl | bash` remote code execution pattern from all install instructions
quoted -
medium Dangerous commands
cmd-pipe-to-shellCHANGELOG.zh.md:276Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)- 移除所有安装说明中的 `curl | bash` 远程代码执行模式
quoted -
low Dangerous commands
cmd-pipe-to-shellCLAUDE.md:39Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)- **No piped shell installs**: Never `curl | bash`. Use `brew install` or `npm install -g`
negated -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:69High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…cAz+ivBu…Lvw==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:154High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…IxX/wd5n…MGF+pv6g…i2Z+Wnj9/KjGz…4Eg==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:188High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…BQM/qZ3R+9TEU…es4+qu1b…BFA==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:205High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha512-8mL/vh8q…uJP+ZcVY…AJW+m0Et…WzA==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:222High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…NES+HiD4…TOe+/2rdn…PWn/r/aAw==",
detector
Files scanned: 55. 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")
Process rating: all ten parameters 53/100
- 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
- 100Tools and files. No external tools needed
- 100Steps. 5 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 240 tokens
- 100Running it twice. No mutating operations
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
- -46 reference files, but SKILL.md never points to them: the model will not open them
- -35 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 645: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 5 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.