SKILLEMALL.ai
GitHub ↗ RU Sign in

BC switchboard-data-operator

Autonomous operator for Switchboard on-demand feeds, Surge streaming, and randomness. Designs jobs, simulates via Crossbar, and deploys/updates/reads feeds across Solana/SVM, EVM, Sui, and other Switchboard-supported chains—with user-controlled security, spend limits, and allow/deny lists.

modbender/skill-library-mcp Agent Skills author: modbender MIT 1 file body ≈ 14 772 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Autonomous operator for Switchboard on-demand feeds, Surge streaming, and randomness.

As a process C 64/100 · Has gaps — weak spots: execution cost, running it twice, progress reporting

ProcedureGitHubInfrastructuretype 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
79/100
safety, quality, tests
Safety 60%
93
Quality 40%
58
Run on models
none yet
Process rating
C
64/100
Has gaps
Progress reporting w 2
0
Running it twice w 4
30
Execution cost w 6
40
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 · 7

✓ No critical or high findings

Medium and low: 7
  • low Secrets in code secret-high-entropy-token SKILL.md:258
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)
    | Surge Program ID | `orac…Abz`             |
    detectortable
  • 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)
    | Monad Mainnet       | 143      | `0xB7…E67` |
    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)
    | Monad Testnet       | 10143    | `0xD3…A33` |
    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)
    | Hyperliquid Mainnet | 999      | `0xcD…347` |
    table
  • low Exfiltration exfil-secret-in-url SKILL.md:517
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    { httpTask: { url: "https://api.polygon.io/v2/last/trade/AAPL?apiKey=…" } },
    placeholder
  • low Exfiltration exfil-secret-in-url SKILL.md:575
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    { httpTask: { url: "https://api.example.com/data?key=…", method: "GET" } },
    placeholder
  • low Secrets in code secret-high-entropy-token SKILL.md:816
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    `orac…Abz`
    quoted

Files scanned: 1. 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 ≈ 14772 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 64/100

  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 40 mutating operations with no state check
  • 40Execution cost. Instruction body is 14772 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
  • 60Steps. 321 steps, 8 vague phrases
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 1 branches, has a failure section
  • 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 11 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)
  • -5TODO / placeholder text left in the skill
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 290: enough signal without eating the budget
  • +4Structure: 121 headings
  • +3Step-by-step instructions: 321 items
  • +3Output format is stated explicitly
  • +4Has examples (35 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.