SKILLEMALL.ai
GitHub ↗ RU Sign in

CB orca-lp

Full-stack Orca Whirlpool agent — read-only pool analytics (discovery, ranking, 6-month stability, range sizing, Monte Carlo projection, retrospective yield, rebalance planning, exit planning) plus on-chain liquidity management (open, increase, decrease, collect fees, close, swap). Wallet only required for intentional writes.

ClawHub Agent Skills author: orca v1.0.5 MIT-0 18 files body ≈ 13 790 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 66/100 · Nearly there — weak spots: result and completion, consistency, execution cost

GeneratorData and analyticsInfrastructureAI 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
C
70/100
safety, quality, tests
Safety 60%
74
Quality 40%
63
Run on models
none yet
Process rating
B
66/100
Nearly there
Result and completion w 14
0
Running it twice w 4
30
Consistency w 8
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 · 26

✓ No critical or high findings

Medium and low: 26
  • low Secrets in code secret-high-entropy-token examples/lp-range-analysis.md:11
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    npx tsx lp-range-analysis.ts Czfq…4zE
    fixture
  • low Secrets in code secret-high-entropy-token examples/lp-range-analysis.md:205
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    Analyzing SOL/USDC (0.04% fee, tickSpacing=4) — Czfq…4zE
    fixture
  • low Secrets in code secret-high-entropy-token examples/monitor-pool.md:11
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    npx tsx monitor-pool.ts Czfq…4zE 15 40
    fixture
  • low Secrets in code secret-high-entropy-token examples/monitor-pool.md:152
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    Monitoring pool Czfq…4zE
    fixture
  • low Secrets in code secret-high-entropy-token examples/open-position.md:31
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const SOL_USDC_POOL = new PublicKey("Czfq…4zE");
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/open-position.md:201
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    Pool: Czfq…4zE
    fixture
  • low Secrets in code secret-high-entropy-token examples/pair-discovery.md:199
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const BONK_MINT = "DezX…263";
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/pool-detail.md:11
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    npx tsx pool-detail.ts Czfq…4zE
    fixture
  • low Secrets in code secret-high-entropy-token examples/pool-detail.md:128
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    Address:        Czfq…4zE
    fixture
  • low Secrets in code secret-high-entropy-token examples/price-range-history.md:192
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    Address: Czfq…4zE
    fixture
  • low Secrets in code secret-high-entropy-token examples/quote.md:24
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    SOL:     { address: "So11…112", decimals: 9 },
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/quote.md:25
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    USDC:    { address: "EPjF…t1v", decimals: 6 },
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/quote.md:26
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    USDT:    { address: "Es9v…NYB", decimals: 6 },
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/quote.md:27
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    ORCA:    { address: "orca…tZE", decimals: 6 },
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/quote.md:28
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    BONK:    { address: "DezX…263", decimals: 5 },
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/range-projection.md:171
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    Address: Czfq…4zE
    fixture
  • low Secrets in code secret-high-entropy-token examples/swap.md:37
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const SOL_USDC_POOL = new PublicKey("Czfq…4zE");
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/swap.md:38
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const SOL_MINT = new PublicKey("So11…112");
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/swap.md:98
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    const usdcMint = new PublicKey("EPjF…t1v");
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/swap.md:123
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    Wallet: 69Hb…X4v
    fixture
  • low Secrets in code secret-high-entropy-token examples/yield-projection.md:238
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    SOL/USDC (0.04% fee) — Czfq…4zE
    fixture
  • low Secrets in code secret-high-entropy-token SKILL.md:350
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const SOL_MINT = new PublicKey("So11…112");
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:633
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    **Whirlpool program ID**: `whir…yCc` (same on mainnet + devnet).
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:793
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | SOL/USDC | 0.04% | `Czfq…4zE` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:794
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | USDC/USDT | 0.01% | `4fuU…4T4` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:795
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | SOL/JitoSOL | 0.01% | `Hp53…QKp` |
    table

Files scanned: 18. 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 ≈ 13790 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 66/100

  • 0Result and completion. Does not say what the result is
  • 30Running it twice. 21 mutating operations with no state check
  • 40Consistency. Frontmatter name (orca-lp) differs from the folder (orca-lp-analytics)
  • 40Execution cost. Instruction body is 13790 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 192 steps
  • 100Failures and branches. 9 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 19 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (10 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
  • +2Single-language instructions
  • +3Description length 327: enough signal without eating the budget
  • +4Structure: 57 headings
  • +3Step-by-step instructions: 192 items
  • +4Has examples (21 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.

External checks

ClawHub: clean
This Orca LP skill is a transparent DeFi assistant that can analyze pools safely by default and can sign real Solana transactions only when the user supplies a wallet key and confirms execution.
LLM: benign (high) · VirusTotal: · 29 May 2026