AB first-line
「开口第一句」— 帮不擅长社交破冰的人，基于小红书公开内容找到共同兴趣、理解对方风格、生成自然不尬的第一句话。适合想扩展社交圈但不知道怎么自然开口的人。Use when: (1) user shares a xiaohongshu.com or xhslink.com URL and wants help crafting a first message, (2) user asks to analyze someone's Xiaohongshu content to find conversation angles, (3) user wants to browse Xiaohongshu by keyword to discover people with shared interests, (4) user asks for help with social icebreakers or first messages. Trigger phrases: xiaohongshu, xhs, 小红书, 开口第一句, 破冰, 第一句话, 不知道怎么开口, 怎么聊, 社交, 扩列, 交朋友, 分析主页, 搜博主, conversation starter, icebreaker, first message.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice
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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: bashallowed-tools: browser bash message
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 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (first-line) differs from the folder (xiaohongshu-first-line)
- 55Failures and branches. 1 branches
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 27 steps
- 100Execution cost. Instruction body is 1773 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +1No license
- +2Single-language instructions
- +3Description length 563: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 27 items
- +3Output format is stated explicitly
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.