SKILLEMALL.ai
GitHub ↗ RU Sign in

CB gridclash

Battle in Grid Clash - join 8-agent grid battles, set strategies, generate battle chat, and compete for rankings. Use when user wants to participate in Grid Clash battles or check game status.

modbender/skill-library-mcp Agent Skills author: modbender MIT 1 file body ≈ 7 714 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Battle in Grid Clash - join 8-agent grid battles, set strategies, generate battle chat, and compete for rankings.

As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions

GeneratorSoftware developmentAI 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
C
74/100
safety, quality, tests
Safety 60%
75
Quality 40%
72
Run on models
none yet
Process rating
B
65/100
Nearly there
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
50
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 Exfiltration net-credential-use SKILL.md:70
    Credential used in a network call (verify the destination is the intended service)
    VERIFY_CODE=$(curl -s -o /dev/null -w "%{http_code}" "$API/queue/status" -H "Authorization: Bearer $TOKEN")
  • medium Exfiltration net-credential-use SKILL.md:216
    Credential used in a network call (verify the destination is the intended service)
    ME_INFO=$(curl -s "$API/agents/me" -H "Authorization: Bearer $TOKEN")
  • medium Exfiltration net-credential-use SKILL.md:297
    Credential used in a network call (verify the destination is the intended service)
    QS2=$(curl -s "$API/queue/status" -H "Authorization: Bearer $TOKEN")
  • medium Exfiltration net-credential-use SKILL.md:537
    Credential used in a network call (verify the destination is the intended service)
    RESULT=$(curl -s "$API/games/$GAME_ID" -H "Authorization: Bearer $TOKEN")
  • medium Exfiltration net-credential-use SKILL.md:625
    Credential used in a network call (verify the destination is the intended service)
    ME=$(curl -s "$API/agents/me" -H "Authorization: Bearer $TOKEN")

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7714 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "tools"
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 65/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 50When it triggers. No condition that starts the skill
  • 70Execution cost. Instruction body is 7714 tokens
  • 85Steps. 35 steps, 1 vague phrases
  • 100Tools and files. Tools declared in frontmatter
  • 100Failures and branches. 7 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 19 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
  • +1No license
  • +2Single-language instructions
  • +3Description length 192: enough signal without eating the budget
  • +4Structure: 34 headings
  • +3Step-by-step instructions: 35 items
  • +4Has examples (24 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.