SKILLEMALL.ai
GitHub ↗ RU Sign in

CC mentat

MENTAT, the agent-native OTC venue. Escrow settlement on Base (atomic, no admin keys), CoW Protocol relay (agent-signed, MEV-protected), and an XMR route via Wagyu (XMR/USDC both directions, three legs, one proof per leg). Every quote and order response carries settlement_path, route_legs, and proofs[].

ClawHub Agent Skills author: Agora0x v1.4.5 MIT-0 3 files body ≈ 5 308 tokens Open the sourceclawhub.ai↗ analyzed 11 d ago

MENTAT, the agent-native OTC venue.

As a process C 62/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice

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
C
80/100
safety, quality, tests
Safety 60%
90
Quality 40%
65
Run on models
none yet
Process rating
C
62/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
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 · 10

✓ No critical or high findings

Medium and low: 10
  • low Secrets in code secret-high-entropy-token clawhub-skill.json:37
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "registry_address": "0x80…432",
    quoted
  • low Secrets in code secret-high-entropy-token clawhub-skill.json:40
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "escrow_contract": "0x9E…AA7",
    quoted
  • low Secrets in code secret-high-entropy-token clawhub-skill.json:44
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "0x9E…AA7",
    quoted
  • low Secrets in code secret-high-entropy-token clawhub-skill.json:49
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "0x83…a6d",
    quoted
  • low Secrets in code secret-high-entropy-token clawhub-skill.json:57
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "cow_settlement": "0x90…b41",
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:224
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    FloorEscrow V3 (`0x83…a6d`, live on Base since block 52006064) settles the deals people post on the web. No skill calls it: maker and taker use their own wallets.
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:233
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    MENTAT's servers hold one Ethereum key, the operator key: the agent wallet `0xE6…fd3`. On-chain it is the owner of ERC-8004 Agent #31596 (`ownerOf(31596)` on the Iden
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:268
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | USDC | `0x83…913` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:269
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | USDbC | `0xd9…6CA` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:270
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | DAI | `0x50…0Cb` |
    table

Files scanned: 3. 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 ≈ 5308 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 276): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 62/100

  • 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
  • 30Running it twice. 23 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 5308 tokens
  • 100Tools and files. No external tools needed
  • 100Steps. 28 steps
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 12 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 304: enough signal without eating the budget
  • +4Structure: 23 headings
  • +3Step-by-step instructions: 28 items
  • +3Output format is stated explicitly
  • +4Has examples (14 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.

External checks

ClawHub: clean
This skill is a disclosed crypto OTC/trading integration whose external API calls and signing flows match its stated purpose, though users should treat trades and XMR routing as financially sensitive.
LLM: benign (high) · VirusTotal: · 2 Oct 2026