SKILLEMALL.ai
GitHub ↗ RU Sign in

BD clicks-protocol

Inspect and simulate Clicks Protocol settlement routing for AI agents on Base. Use read-only MCP calls for settlement state, split previews, optional yield routing, and attribution stats.

ClawHub Agent Skills author: Protogenosone v1.2.7 MIT-0 4 files · 1 script body ≈ 1 968 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI 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
B
87/100
safety, quality, tests
Safety 60%
85
Quality 40%
91
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    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 · 15

    ✓ No critical or high findings

    Medium and low: 15
    • low Secrets in code secret-high-entropy-token references/contracts.md:7
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | ClicksRegistry | `0x23…0a3` | [View](https://basescan.org/address/0x23…0a3) |
      table
    • low Secrets in code secret-high-entropy-token references/contracts.md:8
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)
      | ClicksFeeV2 | `0x8C…fb5` | [View](https://basescan.org/address/0x8C…fb5) |
      detectortable
    • low Secrets in code secret-high-entropy-token references/contracts.md:9
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)
      | ClicksYieldRouter | `0x05…ECD` | [View](https://basescan.org/address/0x05…ECD) |
      detectortable
    • low Secrets in code secret-high-entropy-token references/contracts.md:10
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)
      | Clic…rV4 | `0xB7…3C8` | [View](https://basescan.org/address/0xB7…3C8) |
      detectortable
    • low Secrets in code secret-high-entropy-token references/contracts.md:11
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)
      | ClicksReferral | `0x1E…ccC` | [View](https://basescan.org/address/0x1E…ccC) |
      detectortable
    • low Secrets in code secret-high-entropy-token scripts/clicks.sh:102
      High-entropy token-like string (may be an id, hash or a credential)
      - ClicksRegistry: 0x23…0a3
    • low Secrets in code secret-high-entropy-token scripts/clicks.sh:103
      High-entropy token-like string (may be an id, hash or a credential)
      - Clic…V4: 0xB7…3C8
    • low Secrets in code secret-high-entropy-token scripts/clicks.sh:104
      High-entropy token-like string (may be an id, hash or a credential)
      - ClicksYieldRouter: 0x05…ECD
    • low Secrets in code secret-high-entropy-token scripts/clicks.sh:105
      High-entropy token-like string (may be an id, hash or a credential)
      - Clic…V2: 0x8C…fb5
    • low Secrets in code secret-high-entropy-token scripts/clicks.sh:106
      High-entropy token-like string (may be an id, hash or a credential)
      - ClicksReferral: 0x1E…ccC
    • low Secrets in code secret-high-entropy-token SKILL.md:176
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - ClicksRegistry: `0x23…0a3`
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:177
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - Clic…V4: `0xB7…3C8`
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:178
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - Clic…V2: `0x8C…fb5`
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:179
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - ClicksYieldRouter: `0x05…ECD`
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:180
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - ClicksReferral: `0x1E…ccC`
      quoted

    Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 49/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 3 mutating operations with no state check
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 100Steps. 43 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1968 tokens
    • 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)
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +3Description length 187: enough signal without eating the budget
    • +4Structure: 20 headings
    • +3Step-by-step instructions: 43 items
    • +4Has examples (9 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)
    • +3All 1 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: clean
    This skill is a read-only Clicks Protocol inspection helper that discloses its network calls and does not handle keys, sign transactions, or persist data.
    LLM: benign (high) · VirusTotal: · 21 Jul 2026