SKILLEMALL.ai
GitHub ↗ RU Sign in

BF wdk

Tether Wallet Development Kit (WDK) for building non-custodial multi-chain wallets. Use when working with @tetherto/wdk-core, wallet modules (wdk-wallet-btc, wdk-wallet-evm, wdk-wallet-evm-erc-4337, wdk-wallet-solana, wdk-wallet-spark, wdk-wallet-ton, wdk-wallet-tron, ton-gasless, tron-gasfree), and protocol modules including swap (wdk-protocol-swap-velora-evm, wdk-protocol-swap-stonfi-ton), bridge (wdk-protocol-bridge-usdt0-evm), lending (wdk-protocol-lending-aave-evm), and fiat (wdk-protocol-fiat-moonpay). Covers wallet creation, transactions, token transfers, DEX swaps, cross-chain bridges, DeFi lending/borrowing, and fiat on/off ramps.

modbender/skill-library-mcp Agent Skills author: modbender MIT 14 files body ≈ 3 535 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Tether Wallet Development Kit (WDK) for building non-custodial multi-chain wallets.

As a process F 33/100 · Will not run — References files that are not bundled: references/chains.md, references/deployments.md, references/wallet-btc.md

GeneratorAI and agentsWriting and documentstype 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
80/100
safety, quality, tests
Safety 60%
85
Quality 40%
72
Run on models
none yet
Process rating
F
33/100
Will not run
References files that are not bundled: references/chains.md, references/deployments.md, references/wallet-btc.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

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 · 15

✓ No critical or high findings

Medium and low: 15
  • low Instruction override en-ignore-previous SKILL.md:230
    Instruction-override phrase ("ignore previous instructions") (negated — the text forbids it)
    2. Contains injection markers ("ignore previous instructions", "system override", "admin mode", "you are now in...")
    negated
  • low Secrets in code secret-high-entropy-token skills/chains.md:108
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **EVM** (all) | Hex, 42 chars, checksum | `0xdA…ec7` |
    table
  • low Secrets in code secret-high-entropy-token skills/chains.md:109
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **Solana** | Base58, 32-44 chars | `Es9v…NYB` |
    table
  • low Secrets in code secret-high-entropy-token skills/chains.md:110
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **TON** | Base64url or raw | `EQCx…sDs` |
    table
  • low Secrets in code secret-high-entropy-token skills/chains.md:111
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **TRON** | Base58Check, starts with `T` | `TR7N…j6t` |
    table
  • low Secrets in code secret-high-entropy-token skills/deployments.md:9
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **Ethereum** | `0xdA…ec7` | ⚠️ Non-standard ERC20: no bool return on `transfer()`. Use SafeERC20. Does NOT support EIP-3009. |
    table
  • low Secrets in code secret-high-entropy-token skills/deployments.md:10
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **TRON** | `TR7N…j6t` | ⚠️ Same non-standard transfer as Ethereum USDT. |
    table
  • low Secrets in code secret-high-entropy-token skills/deployments.md:11
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **Solana** | `Es9v…NYB` | SPL token mint address |
    table
  • low Secrets in code secret-high-entropy-token skills/deployments.md:12
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **TON** | `EQCx…sDs` | Jetton master contract |
    table
  • low Secrets in code secret-high-entropy-token skills/deployments.md:13
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **Avalanche** | `0x97…8c7` | Standard ERC20 |
    table
  • low Secrets in code secret-high-entropy-token skills/wallet-evm.md:73
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    entrypointAddress: '0x00…032',
    quoted
  • low Secrets in code secret-high-entropy-token skills/wallet-evm.md:75
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    address: '0xFd…bb9' // USDT on Arbitrum
    quoted
  • low Secrets in code secret-high-entropy-token skills/wallet-solana.md:31
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **USDT mint**: `Es9v…NYB`
    quoted
  • low Secrets in code secret-high-entropy-token skills/wallet-ton.md:44
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **USDT Jetton master**: `EQCx…sDs`
    quoted
  • low Secrets in code secret-high-entropy-token skills/wallet-tron.md:43
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **USDT address**: `TR7N…j6t`
    quoted

Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/chains.md
  • warning missing-ref reference to a missing file: references/deployments.md
  • warning missing-ref reference to a missing file: references/wallet-btc.md
  • warning missing-ref reference to a missing file: references/wallet-evm.md
  • warning missing-ref reference to a missing file: references/wallet-solana.md
  • warning missing-ref reference to a missing file: references/wallet-spark.md
  • warning missing-ref reference to a missing file: references/wallet-ton.md
  • warning missing-ref reference to a missing file: references/wallet-tron.md
  • warning missing-ref reference to a missing file: references/protocol-swap.md
  • warning missing-ref reference to a missing file: references/protocol-bridge.md
  • warning missing-ref reference to a missing file: references/protocol-lending.md
  • warning missing-ref reference to a missing file: references/protocol-fiat.md

Process rating: all ten parameters 33/100

Will not run. References files that are not bundled: references/chains.md, references/deployments.md, references/wallet-btc.md
  • 0Tools and files. 12 referenced file(s) missing: references/chains.md, references/deployments.md, references/wallet-btc.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 18 mutating operations with no state check
  • 40Consistency. Frontmatter name (wdk) differs from the folder (tether-wallet-development-kit)
  • 55Failures and branches. 1 branches
  • 85Steps. 47 steps, 1 vague phrases
  • 100Execution cost. Instruction body is 3535 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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 647: enough signal without eating the budget
  • +4Structure: 30 headings
  • +3Step-by-step instructions: 47 items
  • +4Has examples (9 code blocks)

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