SKILLEMALL.ai
GitHub ↗ RU Sign in

CD ETHSKILLS — The missing knowledge between AI agents and production Ethereum.

For individual topics, fetch any of these directly:

modbender/skill-library-mcp Agent Skills author: modbender MIT 1 file body ≈ 33 750 tokens Open the sourcegithub.com↗ analyzed 3 d ago

For individual topics, fetch any of these directly:

As a process D 48/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, consistency

ProcedureGitHubAI and agentsInfrastructuretype 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%
95
Quality 40%
42
Run on models
none yet
Process rating
D
48/100
Unfinished process
Inputs and preconditions w 11
0
Execution cost w 6
10
Running it twice w 4
30
the three weakest of ten parameters · all ten

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
  • low Secrets in code secret-high-entropy-token SKILL.md:85
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **IdentityRegistry:** `0x80…432`
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:86
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **ReputationRegistry:** `0x80…b63`
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:266
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    **Account abstraction status:** ERC-4337 is growing but still early (Feb 2026). Major implementations: Kernel (ZeroDev), Biconomy, Alchemy Account Kit, Pimlico. EntryPoint v0.7: `0x00…2E5
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:295
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | Safe Singleton | `0x41…61a` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:296
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | Safe Proxy Factory | `0x4e…c67` |
    table

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

Against the Agent Skills spec

  • error name-long name is longer than 64 chars
  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning body-long SKILL.md body ≈ 33750 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 48/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 10Execution cost. Instruction body is 33750 tokens: crowds the task out of the window
  • 30Running it twice. 133 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 40Consistency. Frontmatter name (ETHSKILLS — The missing knowledge between AI agents and production Ethereum.) differs from the folder (eth-dev)
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web, git, python, node) that frontmatter does not declare
  • 60Steps. 409 steps, 6 vague phrases
  • 100Failures and branches. 2 branches, has a failure section
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 116 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (3 tags): a typed call is more reliable

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)
  • +3Description length 51: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • -2localhost URLs: will not work for another user
  • -2171 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Structure: 270 headings
  • +3Step-by-step instructions: 409 items
  • +4Has examples (93 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 42.