SKILLEMALL.ai
GitHub ↗ RU Sign in

BD RMN Soul — Recursive Memory Network + On-Chain Soul

RMN Soul automatically: 1. Parses your agent's memory files into a 5-layer recursive neural network 2. Registers an ERC-8004 identity on Base chain (gas sponsored) 3. Uploads memory to IPFS for per...

modbender/skill-library-mcp Agent Skills author: modbender MIT 9 files body ≈ 1 033 tokens Open the sourcegithub.com↗ analyzed 2 d ago

RMN Soul automatically: 1.

As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI 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
78/100
safety, quality, tests
Safety 60%
87
Quality 40%
64
Run on models
none yet
Process rating
D
41/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
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.

Dangerous commands 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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 9

✓ No critical or high findings

Medium and low: 9
  • medium Dangerous commands cmd-pipe-to-shell scripts/anchor.js:128
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
    console.log('\n⚠️ Foundry cast not found. Install: curl -L https://foundry.paradigm.xyz | bash && foundryup');
    code literal
  • low Secrets in code secret-high-entropy-token README.md:98
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - 合约: ERC-8004 Identity Registry `0x80…432`
    quoted
  • low Exfiltration net-credential-use scripts/anchor.js:151
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    `${cast} send --private-key ${privateKey} --rpc-url ${rpcUrl} ${config.identityRegistry} "register(string)" "${agentURI}" --json`,
    quoted
  • low Exfiltration net-credential-use scripts/anchor.js:199
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    `${cast} send --private-key ${privateKey} --rpc-url ${rpcUrl} ${config.identityRegistry} "setMetadata(uint256,string,bytes)" ${agentId} "${key}" "${val}" --json`,
    quoted
  • low Secrets in code secret-high-entropy-token scripts/resurrect.js:48
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    const registry = '0x80…432';
    detector
  • low Secrets in code secret-high-entropy-token scripts/resurrect.js:154
    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 scripts/setup.js:204
    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 scripts/setup.js:205
    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:75
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "identityRegistry": "0x80…432",
    quoted

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 41/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (RMN Soul — Recursive Memory Network + On-Chain Soul) differs from the folder (rmn-soul)
  • 60Tools and files. Uses tools (node) that frontmatter does not declare
  • 100Steps. 26 steps
  • 100Execution cost. Instruction body is 1033 tokens
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 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)
  • +3Output format is not stated: the model decides each time
  • -31 of 6 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 200: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 26 items
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.