SKILLEMALL.ai
GitHub ↗ RU Sign in

CF typhoon-tracker

台风实时追踪与影响研判（Typhoon Tracker），经多台风全周期实战验证。当用户询问台风路径/登陆预测/强度、风雨影响、出行安全、交通停运、活动/演唱会/漫展可行性时加载；当用户询问航班/高铁/交通出行与行程规划时**必须加载**——即使未明确提及台风，也要排查台风及其残余环流、冷空气等系统性天气背景对交通的影响（避免仅看当日天气导致误判，如残涡'回马枪'）；当询问停编台风的残涡去向/残余影响/降雨成因时**必须加载**（残涡可停编后重组二次增强）；当近海存在未编号扰动/热带低压/弱台风逼近重点城市时**必须加载**（距重点城市<500km 的系统优先级≥远洋强台风）。覆盖数据源体系与冲突仲裁、预测变化规律、影响/降雨/交通评估模型、三模式自动切换（台风/残涡/空窗期）、报告与PDF生成、决策框架。核心优势：真实台风实测反推规律（巴威/白海豚/浪卡/简拉维/沙德尔等）、交通停运[官方]与[预测]严格分级、残涡与近海系统动态跟踪、持续迭代越用越准。适用于西北太平洋台风逼近华东沿海及残涡滞留/重组/出境、近海弱系统快速升级的完整生命周期场景。

Not recommendedcritical or high security findings
ClawHub Agent Skills author: FireflJay v1.2.0 MIT-0 21 files body ≈ 10 367 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

台风实时追踪与影响研判（Typhoon…

As a process F 29/100 · Will not run — References files that are not bundled: references/[typhoon_name]_[编号]_case_data.md

ProcedureData and analyticsInfrastructuretype 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
C
73/100
safety, quality, tests
Safety 60%
82
Quality 40%
59
Run on models
none yet
Process rating
F
29/100
Will not run
References files that are not bundled: references/[typhoon_name]_[编号]_case_data.md
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

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

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.

For the author

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

  1. 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.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  4. 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 · 1

  • high Dangerous commands cmd-pipe-to-shell PUBLISH_GUIDE.md:64
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://skillhub.cn/install/install.sh | bash

Files scanned: 21. 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 ≈ 10367 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/[typhoon_name]_[编号]_case_data.md
  • note frontmatter-key unknown frontmatter key "source"
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "trigger"
  • note frontmatter-key unknown frontmatter key "agent_created"

Process rating: all ten parameters 29/100

Will not run. References files that are not bundled: references/[typhoon_name]_[编号]_case_data.md
  • 0Tools and files. 1 referenced file(s) missing: references/[typhoon_name]_[编号]_case_data.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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 40Execution cost. Instruction body is 10367 tokens: crowds the task out of the window
  • 100Steps. 203 steps
  • 100Consistency. Name and required fields are in place
  • low 23 top-level sections: this looks like several domains in one skill

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
  • -2105 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +3Description length 480: enough signal without eating the budget
  • +4Structure: 102 headings
  • +3Step-by-step instructions: 203 items
  • +4Has examples (6 code blocks)
  • +4Reference files are cited in the instructions (11 of 11)
  • +3All 1 scripts are documented
  • +1License stated

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

External checks

ClawHub: suspicious
This is a coherent typhoon and weather-tracking skill, but it should be reviewed because it automatically writes reports and updates skill data without clear user opt-in or containment.
LLM: suspicious (high) · 26 Aug 2026