SKILLEMALL.ai
RU Sign in

BF trip-scout

个人/家庭机酒搜索和自驾游行程规划助手。双场景驱动：场景一（机酒搜索）飞猪+携程双平台搜索， 智能酒店筛选（品牌信任梯度、加盟/直营识别、差评分析、多维度评价分析、黑榜），自进化学习； 机票价格监控（携程API抓取+价格历史+入手区间分析+降价预测+flyai交叉验证）； 场景二（自驾游行程规划）小红书路线推荐→酒店联动调整→地图渲染（H5行程页+高德专属地图双轨）→飞书攻略生成； 租车网点查询（神州租车API+一嗨租车页面解析，查城市取还车网点）。 触发词：搜机票、搜酒店、找酒店、订机票、机酒搜索、监控机票、机票价格、入手时机、自驾游、行程规划、路线推荐、 租车网点、租车门店、取车点、还车点、car rental stores、road trip、trip plan、travel search、flight search、hotel search。

ClawHub Agent Skills author: Hengshan Cui v1.0.0 MIT-0 48 files body ≈ 5 014 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

个人/家庭机酒搜索和自驾游行程规划助手。双场景驱动：场景一（机酒搜索）飞猪+携程双平台搜索， 智能酒店筛选（品牌信任梯度、加盟/直营识别、差评分析、多维度评价分析、黑榜），自进化学习； 机票价格监控（携程API抓取+价格历史+入手区间分析+降价预测+flyai交叉验证）；…

As a process F 31/100 · Will not run — References files that are not bundled: {图片URL}, {高德地图URL}

ProcedurePlaywrightAI and agentsSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
78/100
safety, quality, tests
Safety 60%
91
Quality 40%
59
Run on models
none yet
Process rating
F
31/100
Will not run
References files that are not bundled: {图片URL}, {高德地图URL}
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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 · 5

✓ No critical or high findings

Medium and low: 5
  • medium Broad scope meta-agent-memory-dump templates/MEMORY.md
    Agent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokens
    templates/MEMORY.md
  • low Obfuscation obf-base64-blob vendor/xhs_api/static/xhs_main_260411.js:96
    Long base64-looking blob (quoted — discussed, not commanded)
    "b1": "I38r…gIC+oIEL…fIi/eWc6…6QL+5Ii6…BIx+PGDi/sVtk…VTI
    quoted
  • low Obfuscation obf-base64-blob vendor/xhs_api/static/xhs_main_260411.js:400
    Long base64-looking blob (quoted — discussed, not commanded)
    var fff = "I38r…gIC+oIEL…fIi/eWc6…6QL+5Ii6…BIx+PGDi/sVtk…V0I
    quoted
  • low Obfuscation obf-base64-blob vendor/xhs_api/static/xhs_rap.js:420
    Long base64-looking blob (detector / deny-list definition)
    })();(self.webpackChunkxhs_pc_web=self.webpackChunkxhs_pc_web||[]).push([["4630"],{9116…ion(){(function Sanji(){var B=true,Q=false;return function(A,E,C){var g=[],H=[],I={},c=[],J={_gar…2:A}
    detector
  • low Secrets in code secret-high-entropy-token vendor/xhs_api/static/xhs_rap.js:420
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    })();(self.webpackChunkxhs_pc_web=self.webpackChunkxhs_pc_web||[]).push([["4630"],{9116…ion(){(function Sanji(){var B=true,Q=false;return function(A,E,C){var g=[],H=[],I={},c=[],J={_gar…2:A}
    detector

Files scanned: 48. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 5014 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: {图片URL}
  • warning missing-ref reference to a missing file: {高德地图URL}

Process rating: all ten parameters 31/100

Will not run. References files that are not bundled: {图片URL}, {高德地图URL}
  • 0Tools and files. 2 referenced file(s) missing: {图片URL}, {高德地图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
  • 30Running it twice. 1 mutating operations with no state check
  • 70Execution cost. Instruction body is 5014 tokens
  • 100Steps. 122 steps
  • 100Consistency. Name and required fields are in place
  • low The response is described with custom markup (5 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
  • -222 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +3Description length 380: enough signal without eating the budget
  • +4Structure: 26 headings
  • +3Step-by-step instructions: 122 items
  • +4Has examples (20 code blocks)
  • +4Reference files are cited in the instructions (11 of 11)
  • +3All 6 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.

External checks

ClawHub: suspicious
This travel-planning skill has a coherent purpose, but it needs Review because it handles account cookies, uses reverse-engineered anti-detection platform access, and includes under-scoped executable code paths.
LLM: suspicious (high) · 7 Sept 2026