BF xiaohongshu-ops
小红书端到端运营：账号定位、选题研究、内容生产、发布执行、数据复盘。 Use when: (1) 用户要写小红书笔记/帖子, (2) 用户说"发小红书"/"写个种草文"/"出一篇小红书", (3) 用户讨论小红书选题/热点/爆款分析/竞品对标, (4) 用户提到账号定位/人设/内容方向规划, (5) 用户要求生成小红书风格的配图/封面/标题, (6) 用户讨论小红书数据（点赞/收藏/评论/流量）, (7) 用户提到"种草"/"拔草"/"测评"/"好物分享"等小红书典型内容形式。 即使用户没有明确说"小红书"，只要涉及生活方式类短图文内容创作、 种草测评类写作、或社交电商内容运营，都应使用此技能。 支持多垂类复用，内置陪你看剧案例模板。 NOT for: 公众号文章发布（用 wemp-ops）、纯内部文档（用 internal-comms）、 图片生成本身（用 Gemini 生图 或 Seedream）。
小红书端到端运营：账号定位、选题研究、内容生产、发布执行、数据复盘。 Use when: (1) 用户要写小红书笔记/帖子, (2) 用户说"发小红书"/"写个种草文"/"出一篇小红书", (3) 用户讨论小红书选题/热点/爆款分析/竞品对标, (4) 用户提到账号定位/人设/内容方向规划, (5)…
As a process F 31/100 · No process to follow — References files that are not bundled: references/xhs-knowledge-base.md, examples/<vertical>/<vertical>.md, examples/<vertical>/README.md
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/xhs-knowledge-base.md - warning
missing-refreference to a missing file: examples/<vertical>/<vertical>.md - warning
missing-refreference to a missing file: examples/<vertical>/README.md - warning
missing-refreference to a missing file: examples/lifestyle/ - warning
missing-refreference to a missing file: examples/cosmetics/ - warning
missing-refreference to a missing file: examples/fitness/
Process rating: all ten parameters 31/100
- 0Tools and files. 6 referenced file(s) missing: references/xhs-knowledge-base.md, examples/<vertical>/<vertical>.md, examples/<vertical>/README.md
- 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
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (xiaohongshu-ops) differs from the folder (xhs-ops)
- 50When it triggers. No condition that starts the skill
- 100Steps. 110 steps
- 100Execution cost. Instruction body is 2144 tokens
- low 23 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 tags): a typed call is more reliable
- medium 2 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
- +3Output format is not stated: the model decides each time
- -216 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 407: enough signal without eating the budget
- +4Structure: 36 headings
- +3Step-by-step instructions: 110 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (12 of 15)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.