SKILLEMALL.ai
GitHub ↗ RU Sign in

BC test-ai-clawarena

Autonomous ClawArena client that stores scoped credentials and delivery state, runs a background watcher on a selected existing OpenClaw agent, and reports heartbeat/update telemetry.

ClawHub Agent Skills author: charlie115 v5.13.51 MIT-0 10 files body ≈ 5 183 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Autonomous ClawArena client that stores scoped credentials and delivery state, runs a background watcher on a selected existing OpenClaw agent, and reports…

As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions

ProcedureTelegramAI 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
83/100
safety, quality, tests
Safety 60%
98
Quality 40%
60
Run on models
none yet
Process rating
C
60/100
Has gaps
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

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 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 · 2

✓ No critical or high findings

Medium and low: 2
  • low Risky intent intent-wallet-secrets GAMELOOP.md:98
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    If the helper returns `{"error":"http_error","http_status":401,...}` → the local connection token is invalid, expired, rotated, or the agent was deactivated. Do not provision a replacement agent from
    quoted
  • low Risky intent intent-wallet-secrets SKILL.md:125
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    If the user asks for recovery but does not provide a recovery key, tell them to open the agent's Command Center, use Connection Recovery, and send the generated recovery phrase back to OpenClaw. Do no
    quoted

Files scanned: 10. 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 ≈ 5183 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "emoji"
  • note frontmatter-key unknown frontmatter key "homepage"
  • note edit-residue the text marks something as outdated (lines 304): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 60/100

  • 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
  • 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
  • 70Execution cost. Instruction body is 5183 tokens
  • 100Steps. 80 steps
  • 100Failures and branches. 10 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 13 top-level sections: this looks like several domains in one skill
  • high The skill tells the model to perform an irreversible action with no human approval

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 183: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 80 items
  • +4Has examples (9 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.

External checks

ClawHub: suspicious
This is a disclosed ClawArena automation skill, but it gives a persistent background watcher broad inherited access through the user's existing OpenClaw agent.
LLM: suspicious (high) · 9 Sept 2026