SKILLEMALL.ai
RU Sign in

CF dlt-probability-analyzer

大乐透诚实理性助手 · 一份不忽悠的大乐透报告：随机性检验、选号法打假、胆拖优化、合买覆盖、诚实账本与预算守护、玩家防坑教育、网点雷达，只讲真话、只做伤害减损。当用户说"分析大乐透/大乐透预测/生成大乐透报告/大乐透中奖概率/彩票能不能预测/选号法有没有用/大乐透随机性检验/大乐透胆拖方案/大乐透合买/拼单/大乐透账本/预算/防坑/体彩网点/超级大乐透分析/大乐透开奖模式/大乐透历史统计"时使用。生成严谨分析报告，内置对"预测力"的统计证伪（前区熵效率/任一组合恒等概率/样本外回测/no_edge 结论）、22 项自检护栏。核心立场：数学上任何选号法都不优于随机、期望为负，本 skill 不承诺中奖或正收益，而是帮你用最低成本理性娱乐、看清概率、控制花费、避免被骗与沉迷。

ClawHub Agent Skills author: hmily741963 v1.0.0 MIT-0 65 files body ≈ 4 462 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

大乐透诚实理性助手 ·…

As a process F 34/100 · Will not run — References files that are not bundled: references/faq.md, scripts/run_dlt.py, scripts/lib/REPORT_PATH.txt

AnalyzerInfrastructuretype 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
72/100
safety, quality, tests
Safety 60%
85
Quality 40%
53
Run on models
none yet
Process rating
F
34/100
Will not run
References files that are not bundled: references/faq.md, scripts/run_dlt.py, scripts/lib/REPORT_PATH.txt
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.

Dangerous commands 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 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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. 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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Dangerous commands cmd-persistence dlt_restore.py:8
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    1. 还原 Windows 排程任务 DLT_…art (schtasks /create /xml, 需管理员)
    code literal
  • medium Dangerous commands cmd-persistence dlt_restore.py:71
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    print(f"    (dry) 将执行: schtasks /create /tn {TASK_NAME} /xml {xml} /f")
    code literal
  • medium Dangerous commands cmd-persistence operations.md:110
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    - 任务名 `DLT_…art`：`schtasks /create /tn DLT_…art /tr "绝对路径\dlt_…bat" /sc weekly /d MON,WED,SAT /st 20:10 /ru SYSTEM /rl highest`
    quoted

Files scanned: 65. 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 missing-ref reference to a missing file: references/faq.md
  • warning missing-ref reference to a missing file: scripts/run_dlt.py
  • warning missing-ref reference to a missing file: scripts/lib/REPORT_PATH.txt
  • warning missing-ref reference to a missing file: references/scripts.md
  • warning missing-ref reference to a missing file: references/methodology.md
  • warning missing-ref reference to a missing file: references/operations.md
  • warning missing-ref reference to a missing file: references/changelog.md
  • warning missing-ref reference to a missing file: scripts/lib/dlt_error_log.txt
  • warning missing-ref reference to a missing file: scripts/lib/
  • note frontmatter-key unknown frontmatter key "agent_created"

Process rating: all ten parameters 34/100

Will not run. References files that are not bundled: references/faq.md, scripts/run_dlt.py, scripts/lib/REPORT_PATH.txt
  • 0Tools and files. 9 referenced file(s) missing: references/faq.md, scripts/run_dlt.py, scripts/lib/REPORT_PATH.txt
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (dlt-probability-analyzer) differs from the folder (dlt-skill)
  • 50Failures and branches. 0 branches, has a failure section
  • 70Execution cost. Instruction body is 4462 tokens
  • 100Steps. 96 steps
  • 100Running it twice. No mutating operations
  • low 13 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
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -221 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 340: enough signal without eating the budget
  • +4Structure: 29 headings
  • +3Step-by-step instructions: 96 items
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.

External checks

ClawHub: suspicious
The skill is mostly a lottery report tool, but it also includes broad Windows scheduling, WorkBuddy, user-profile, and persistence-related behavior that users should review carefully before installing.
LLM: suspicious (high) · 24 Aug 2026