SKILLEMALL.ai
GitHub ↗ RU Sign in

BC kaggle

Unified Kaggle skill. Use when the user mentions kaggle, kaggle.com, Kaggle competitions, datasets, models, notebooks, GPUs, TPUs, badges, or anything Kaggle-related. Handles account setup, competition reports, dataset/model downloads, notebook execution, competition submissions, badge collection, and general Kaggle questions.

modbender/skill-library-mcp Agent Skills author: modbender MIT 44 files · 8 scripts body ≈ 2 630 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Unified Kaggle skill.

As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

ProcedurePlaywrightData and analyticstype 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
79/100
safety, quality, tests
Safety 60%
76
Quality 40%
84
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
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.

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

    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 · 8

    ✓ No critical or high findings

    Medium and low: 8
    • medium Dangerous commands cmd-persistence modules/badge-collector/scripts/phase_5_streaks.py:67
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
      print(f"  1. Create a plist at ~/Library/LaunchAgents/com.kaggle.streak.plist")
      code literal
    • medium Dangerous commands cmd-persistence modules/badge-collector/scripts/phase_5_streaks.py:70
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
      print(f"  2. Load it: launchctl load ~/Library/LaunchAgents/com.kaggle.streak.plist")
      code literal
    • medium Dangerous commands cmd-persistence modules/badge-collector/scripts/phase_5_streaks.py:71
      Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
      print(f"  3. To stop: launchctl unload ~/Library/LaunchAgents/com.kaggle.streak.plist")
      code literal
    • medium Broad scope meta-broad-allowed-tools SKILL.md:1
      Broad tool permissions pre-approved: Bash
      allowed-tools: Bash Read WebFetch
    • low Dangerous commands cmd-cron-mention modules/badge-collector/scripts/phase_5_streaks.py:74
      Mentions editing / listing crontab (string literal in code, not executed)
      print(f"  1. Open crontab: crontab -e")
      code literal
    • low Dangerous commands cmd-cron-mention modules/badge-collector/scripts/phase_5_streaks.py:77
      Mentions editing / listing crontab (string literal in code, not executed)
      print(f"  3. Save and exit. Verify with: crontab -l")
      code literal
    • low Exfiltration read-dotenv modules/kllm/scripts/setup_env.sh:20
      Reads a .env file
      source .env
    • low Exfiltration read-dotenv modules/registration/scripts/setup_env.sh:17
      Reads a .env file
      source .env

    Files scanned: 44. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 56/100

    • 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
    • 30Running it twice. 15 mutating operations with no state check
    • 70When it triggers. States when to use, but not when not to
    • 85Steps. 63 steps, 3 vague phrases
    • 100Tools and files. Tools declared in frontmatter
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2630 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • 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
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +3Description length 328: enough signal without eating the budget
    • +4Structure: 17 headings
    • +3Step-by-step instructions: 63 items
    • +4Has examples (5 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.