SKILLEMALL.ai
GitHub ↗ RU Sign in

BF data-prompt-coach

数据分析 Prompt 引导教练+教程蒸馏自进化。触发『启动数据分析』『CRISP-DM』『我有 CSV 想端到端分析』『蒸馏教程』→双入口（8 场景+26 方法论+自修改预审+回滚）。Do NOT use for 直接接入生产数据库、ML 建模、纯摘要。

ClawHub Agent Skills author: AI花生 v3.4.4 MIT-0 80 files body ≈ 3 014 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

数据分析 Prompt 引导教练+教程蒸馏自进化。触发『启动数据分析』『CRISP-DM』『我有 CSV 想端到端分析』『蒸馏教程』→双入口（8 场景+26 方法论+自修改预审+回滚）。Do NOT use for 直接接入生产数据库、ML 建模、纯摘要。

As a process F 44/100 · Will not run — References files that are not bundled: references/troubleshooting.md, references/methods/M{N+1}-*.md, references/methods/M{N+1}-{slug}.md

ProcedureAI and agentstype 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
82/100
safety, quality, tests
Safety 60%
86
Quality 40%
76
Run on models
none yet
Process rating
F
44/100
Will not run
References files that are not bundled: references/troubleshooting.md, references/methods/M{N+1}-*.md, references/methods/M{N+1}-{slug}.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

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. 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 · 6

✓ No critical or high findings

Medium and low: 6
  • medium Dangerous commands cmd-persistence references/asset-templates/bat-template-spec.md:228
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (test fixture / example file)
    schtasks /create /tn "DailyDataCollect" /tr "D:\path\to\daily_collect.bat" /sc daily /st 09:00 /rl HIGHEST
    fixture
  • medium Dangerous commands cmd-persistence references/asset-templates/bat-template-spec.md:231
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (test fixture / example file)
    schtasks /create /tn "WeeklyReport" /tr "D:\path\to\weekly_report.bat" /sc weekly /d MON /st 09:00 /rl HIGHEST
    fixture
  • low Exfiltration read-dotenv references/asset-templates/bat-template-spec.md:33
    Reads a .env file (documentation table row; test fixture / example file)
    | 5 | 配置文件 | `copy .env .env.backup` | 含 Token 的 .env 文件 |
    tablefixture
  • low Secrets in code secret-high-entropy-token references/distillation/three-fold-verification.md:126
    High-entropy token-like string (may be an id, hash or a credential)
    cont…_2:
  • low Secrets in code secret-password-literal references/methods/M23-dynamic-api-key-simulation.md:74
    Hard-coded password / key literal (may be an example)
    api_key = resp2.json().get('api_key', '')
  • low Secrets in code secret-password-literal references/methods/M23-dynamic-api-key-simulation.md:236
    Hard-coded password / key literal (may be an example) (placeholder value)
    api_key = "sk-a…..."  # 禁止！
    placeholder

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/troubleshooting.md
  • warning missing-ref reference to a missing file: references/methods/M{N+1}-*.md
  • warning missing-ref reference to a missing file: references/methods/M{N+1}-{slug}.md
  • warning missing-ref reference to a missing file: scripts/rollback_mount.py
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "summary"

Process rating: all ten parameters 44/100

Will not run. References files that are not bundled: references/troubleshooting.md, references/methods/M{N+1}-*.md, references/methods/M{N+1}-{slug}.md
  • 0Tools and files. 4 referenced file(s) missing: references/troubleshooting.md, references/methods/M{N+1}-*.md, references/methods/M{N+1}-{slug}.md
  • 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
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 100Steps. 48 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3014 tokens
  • 100Running it twice. No mutating operations
  • low 11 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
  • +3Output format is not stated: the model decides each time
  • -224 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 128: enough signal without eating the budget
  • +4Structure: 24 headings
  • +3Step-by-step instructions: 48 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

External checks

ClawHub: suspicious
The skill is mostly disclosed, but it includes under-scoped web scraping, session/key simulation, external cloud writes, and elevated scheduled automation guidance that users should review carefully before installing.
LLM: suspicious (high) · 31 Jul 2026