SKILLEMALL.ai
GitHub ↗ RU Sign in

BC Superior Trade

Backtest and deploy trading strategies on Superior Trade's managed cloud.

ClawHub Agent Skills author: Superior-AI v4.5.0 MIT-0 22 files body ≈ 15 567 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Backtest and deploy trading strategies on Superior Trade's managed cloud.

As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

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
75/100
safety, quality, tests
Safety 60%
91
Quality 40%
51
Run on models
none yet
Process rating
C
57/100
Has gaps
Inputs and preconditions w 11
0
Result and completion w 14
40
Consistency w 8
40
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: Superior Trade (ClawHub)

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 · 9

✓ No critical or high findings

Medium and low: 9
  • low Secrets in code secret-high-entropy-token exchanges/aerodrome.md:66
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | `AERO/USDC` | `0x94…631` | 18 | `0x83…913` | 6 | `0x6c…71d` | false |
    table
  • low Secrets in code secret-high-entropy-token exchanges/aerodrome.md:67
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | `CHECK/USDC` | `0x91…6Eb` | 18 | `0x83…913` | 6 | `0x6a…E0f` | false |
    table
  • low Secrets in code secret-high-entropy-token exchanges/aerodrome.md:86
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "baseAddress": "0x94…631",
    quoted
  • low Secrets in code secret-high-entropy-token exchanges/aerodrome.md:95
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "baseAddress": "0x91…6Eb",
    quoted
  • low Secrets in code secret-high-entropy-token exchanges/aerodrome.md:99
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "poolAddress": "0x6a…E0f",
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:501
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "0xf4…aF1",
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:684
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | Native Arbitrum USDC | `0xaf…831` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:693
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "asset_address": "0xaf…831",
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:702
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "asset_address": "0xaf…831",
    quoted

Files scanned: 22. 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")
  • warning body-long SKILL.md body ≈ 15567 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "updated"
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "source"
  • note frontmatter-key unknown frontmatter key "primaryEnv"
  • note frontmatter-key unknown frontmatter key "auth"
  • note frontmatter-key unknown frontmatter key "env"
  • note frontmatter-key unknown frontmatter key "externalEndpoints"
  • note edit-residue the text marks something as outdated (lines 188, 211, 313, 315): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 57/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Result and completion. Does not say what the result is
  • 40Consistency. Frontmatter name (Superior Trade) differs from the folder (superior-skills)
  • 40Execution cost. Instruction body is 15567 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
  • 85Steps. 140 steps, 2 vague phrases
  • 100Failures and branches. 6 branches, has a failure section
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 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)
  • +3Description length 73: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 80 headings
  • +3Step-by-step instructions: 140 items
  • +4Has examples (35 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 51.

External checks

ClawHub: clean
This is a disclosed trading automation skill that can trade real funds, but its financial authority is aligned with its stated purpose and includes user-confirmation safeguards.
LLM: benign (high) · VirusTotal: · 6 Jun 2026