BF culturetour-search
指导智能体检索文旅素材（数游神州 data0086.com）并走通「搜索 → 列表 → 预览(HLS/MP4) → 选择/购买 → Mock交易返回 → 视频下载到本地」。搜索请求默认 3条，最多 5 条（pageSize≤5），用户可要求更少；列表用表格展示（颜色徽章状态 + img + video），用户通过文本指令选择，支持多选与批量购买。用户可「购买 1,2」直接下单，无需二次确认；购买后 mock 交易响应（video_url 取自搜索结果的 fragmentUrl），自动下载视频到本地并输出文件路径。 **输出格式自动适配**：桌面端/Web 客户端（ArkClaw、OpenClaw 等）默认输出 HTML 表格；**IM 手机应用**（飞书、微信、钉钉等）则输出 **Markdown 表格**，避免手机端直接显示 HTML 源码。 所有嵌入媒体仅限 config.json 中 trusted_media_origins 声明的域名。环境变量 WENLV_API_ORIGIN、TRADE_API_BASE 可选覆盖 config.json 默认值（见 index.json env 声明）。
As a process F 29/100 · Will not run — References files that are not bundled: url, cover_url, preview_url
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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 · 0
✓ No critical or high findings
Files scanned: 8. 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") - warning
body-longSKILL.md body ≈ 7633 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: url - warning
missing-refreference to a missing file: cover_url - warning
missing-refreference to a missing file: preview_url - warning
missing-refreference to a missing file: {preview_url} - warning
missing-refreference to a missing file: video_url
Process rating: all ten parameters 29/100
- 0Tools and files. 5 referenced file(s) missing: url, cover_url, preview_url
- 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
- 40Consistency. Frontmatter name (culturetour-search) differs from the folder (culturetour-skill)
- 70Execution cost. Instruction body is 7633 tokens
- 100Steps. 34 steps
- 100Running it twice. No mutating operations
- low The response is described with custom markup (25 tags): a typed call is more reliable
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)
- +3Output format is not stated: the model decides each time
- -218 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 508: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (20 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.