Todays Orders

v1.0.0

Use this skill when the user wants a single approved onchain order for a Solana wallet, one explicit forbidden order, a quote-backed execution preview, or a...

0· 131·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for richard7463/todays-orders.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Todays Orders" (richard7463/todays-orders) from ClawHub.
Skill page: https://clawhub.ai/richard7463/todays-orders
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install todays-orders

ClawHub CLI

Package manager switcher

npx clawhub@latest install todays-orders
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
Purpose & Capability
The name/description and instructions consistently target producing one approved onchain order for a Solana wallet using OKX OnchainOS (wallet, market, trade, broadcast). That is coherent. However, the skill references an external service (OKX OnchainOS) as its factual layer but does not declare any required credentials or environment variables or explain how the agent will access that service; this is a functional gap (not necessarily malicious) that may lead to hallucinated quotes/routes if connectivity is absent.
Instruction Scope
SKILL.md is explicit and scoped: extract a Solana address, fetch wallet posture, fetch market context for relevant holdings, produce one approved order and one forbidden order, produce quote/route previews, and only broadcast after explicit approval. The instructions do not ask the agent to read unrelated files, secrets, or system paths.
Install Mechanism
Instruction-only skill with no install spec and no code files — minimal footprint. Nothing is downloaded or written to disk by the skill itself.
Credentials
The skill requests no environment variables or credentials in metadata, yet runtime instructions require access to OKX OnchainOS (wallet, market, trade, broadcast). Either the platform provides that integration implicitly, or the skill should have declared required credentials. The absence of declared credentials is a proportionality/clarity issue: ensure the execution environment supplies the necessary API access, and be cautious about possible hallucinated data if it does not.
Persistence & Privilege
No special persistence privileges requested. always is false. The agents/openai.yaml includes allow_implicit_invocation: true which permits implicit invocation; this is expected for a user-invocable skill and is not by itself a security concern.
Assessment
This skill is internally consistent as an instruction-only workflow, but before installing or using it you should: 1) Confirm your OpenClaw/runtime environment provides an OKX OnchainOS connector or the necessary API keys — the skill does not declare credentials. 2) Understand that execution (broadcasting a transaction) should only happen after explicit user approval; test the preview path first. 3) If your runtime lacks the OKX connector, expect the agent might hallucinate quotes/routes; do not rely on previewed execution values until they come from a trusted API. 4) If you plan to allow broadcasting, restrict the skill’s access to only the wallet(s) you control and require manual confirmation for any signed transaction.

Like a lobster shell, security has layers — review code before you run it.

latestvk97fxy1mznetagp9wtqhb7b1rx83g4vc
131downloads
0stars
1versions
Updated 1mo ago
v1.0.0
MIT-0

Today's Orders

Use this skill to run the Today's Orders / 今日军令 workflow inside OpenClaw. The job is not to produce many ideas. The job is to compress one wallet into:

  • 今日军情
  • 今日军令
  • 今日禁令
  • 执行推演
  • 夜间战报

This skill is designed for OpenClaw x OKX OnchainOS.

When to use it

  • The user wants a daily onchain plan for one Solana wallet.
  • The user asks what to do today with an existing wallet.
  • The user wants one approved action instead of many trade ideas.
  • The user wants one forbidden action written explicitly.
  • The user wants a quote-backed preview before execution.
  • The user wants to execute after approval and then summarize the result with a receipt-backed debrief.

Core law

Every response must obey this rule:

Approve at most one order for today. Suppress the rest.

Required capabilities

Use OKX OnchainOS as the factual layer:

  • Wallet / Portfolio for balances, holdings, stablecoin reserve, concentration, and idle capital
  • Market for price, 24h move, and token context
  • Trade for quote, route comparison, and execution preview
  • Broadcast / Status for signature, confirmation, and receipt

Do not invent holdings, quotes, routes, or receipts.

Workflow

  1. Extract one Solana wallet address. If none is provided, ask for it.
  2. Read the wallet posture first:
    • total wallet value
    • top holdings
    • stablecoin reserve
    • concentration
    • idle capital
  3. Pull market context only for the few holdings that matter most today.
  4. Decide one of four daily stances:
    • deploy
    • defend
    • observe
    • watch-only
  5. Approve at most one order. Prefer:
    • small deployment from stablecoins into a major asset
    • partial trim from an over-concentrated bag into a stable reserve
    • no action if the setup is not clean
  6. Write one forbidden order that is specific to the current wallet posture.
  7. If execution is requested, use Trade to produce:
    • quote
    • route
    • slippage context
    • expected output
  8. Only if the user approves, continue to Broadcast / Status and return the receipt.
  9. Close with a daily debrief based on the actual state:
    • preview debrief if not executed
    • receipt-backed debrief if executed

Fixed output

Always return the result in this order:

  1. 今日军情
    • one-line stance
    • wallet summary
    • 2-3 evidence bullets
  2. 今日军令
    • exactly one approved action, or explicitly say no action is approved
  3. 今日禁令
    • one action that should not be taken today
  4. 执行推演
    • quote, route, slippage, expected output
    • label clearly as preview until executed
  5. 夜间战报
    • preview debrief if not executed
    • receipt-backed debrief if executed

Output guidance

  • Keep the tone disciplined and procedural.
  • Use the military shell only as product language, not as roleplay spam.
  • If no clean setup exists, return watch-only and explain why.
  • Never approve more than one order.
  • Do not treat simulation as execution.
  • If the user asks to execute, ask for final approval before broadcast.

Comments

Loading comments...