A battle-tested decision-making protocol for AI agents to handle high-stakes investments, tech selections, and major purchases with rigorous real-time data verification.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install build-protocol-decision
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install build-protocol-decision using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Build Protocol Decision?
The build-protocol-decision framework is an advanced extension of the core Openclaw Skills ecosystem designed for high-stakes, irreversible decision-making. Specifically engineered for situations committing over $1,000 or one day of effort, this protocol enforces absolute methodology transparency and real-time data verification over gut feeling. It helps AI agents systematically avoid confirmation bias and the Sycophancy of Precision, where overly precise figures mask underlying data inaccuracies.
By inheriting the eight iron rules of the parent build-protocol and adding three decision-specific guidelines (real-time verification, methodology enforcement, and stop-loss first planning), this skill guarantees that AI-generated decisions are robust, verifiable, and executable. Whether evaluating US equities, cryptocurrency, enterprise software, or vendor selection, it ensures your AI agent works with live data rather than static, stale documents.
Build Protocol Decision Use Cases
- When making a high-stakes investment or trading decision (stocks, forex, or cryptocurrency) committing significant capital.
- When selecting corporate technology stacks, software-as-a-service vendors, or outsourcing suppliers.
- When deciding between building an in-house solution or buying a commercial alternative (buy-vs-build).
- When planning major capital purchases or physical asset acquisitions requiring multi-year total cost of ownership (TCO) estimates.
- When an AI agent needs to resolve user prompts like 'should I buy X', 'compare options', or 'investing strategies'.
How Build Protocol Decision Works
- Option Gathering: The agent runs targeted web searches, scrapes product reviews, or queries market APIs to compile a non-biased list of all candidates.
- Constraint Enforcement: The system defines hard budget ceilings, timeline limits, non-negotiable disqualifiers, and risk tolerances.
- Real-Time Data Verification: Live price feeds are pulled from authoritative sources (such as Stooq or CoinGecko) to bypass stale document-cached data.
- Dimension Analysis: The options are scored across a multi-dimensional matrix, explicitly mapping out trade-offs.
- Methodology Execution: Financial or analytical models like Discounted Cash Flow (DCF), Price-to-Earnings (PE) comparisons, or Weighted Decision Matrices are run.
- Exit & Contingency Planning: Plan B paths, stop-loss triggers, and return/termination windows are established before any action.
- Documentation: The final choice is written down alongside a date-stamped 'Why This' and 'Why Not the Alternatives' rationale.
- Sized Execution: Execution begins with precise risk-adjusted position sizing or phased system rollouts.
- Daily Tracking: The agent maintains a daily profit and loss log or KPI scorecard to identify thesis-breaking events immediately.
- Postmortem Review: Weekly and monthly retrospectives are conducted to cut losing bets early and log lessons learned.
Build Protocol Decision Setup
Configure your AI environment to load the build-protocol-decision rule set alongside your standard Openclaw Skills library. Ensure your runtime environment has curl installed to execute live data-fetching commands.
For US Stock queries via Stooq, use:
curl "https://stooq.com/q/l/?s=SYMBOL.us&f=sd2t2ohlcv&h&e=csv"
For Cryptocurrency price verification via CoinGecko, execute:
curl "https://api.coingecko.com/api/v3/simple/price?ids=bitcoin&vs_currencies=usd"
Integrate this skill with your agent workspace by copying the markdown files to your local agent skills path (e.g., .claw/skills/build-protocol-decision.md).
Build Protocol Decision Data Schema & Taxonomy
The build-protocol-decision skill structures its decision files, evaluations, and metadata systematically. Decisions are logged alongside active tracking data and references:
Document Structure
| Component | Type | Description |
|---|---|---|
| Frontmatter | YAML | Metadata including name, version, and trigger rules |
| Comparison Matrix | Markdown Table | Scoring profiles across 4-8 dimensions with weighted percentages |
| Daily P/L Log | CSV / Markdown | Daily tracked record of entry price, current price, and unrealized yield |
| Audit Log | Bash Script / Log | Record of methodology audits and data freshness checks |
Schema References
references/decision-workflow.md: Detailed step-by-step audit checklists.references/investment-playbook-template.md: Structure for anonymous investment plays.references/audit-script-decision.sh: Script validating real-time data compliance.
Build Protocol Decision Advanced Features
- Anti-Sycophancy Protection: Forces AI models to round highly uncertain estimates to 2 significant figures and explicitly mark them with '(est.)' to counter false precision.
- Stop-Loss Priority Routing: Enforces a strict guardrail requiring maximum-drawdown and exit strategies to be defined prior to executing purchase transactions.
- Multi-Agent Research Governance: Limits execution to <= 2 parallel sub-agents for shared-state documents, preventing conflicts, while allowing up to <= 4 for isolated investigations.
- Direct API Integration: Integrates natively with live data sources like Stooq and Yahoo Finance over cached search results to protect against outdated decision-making.
- Integration with Openclaw Skills Ecosystem: Connects seamlessly with feishu-bitable for automated daily tracking and academic-research-hub for thorough scientific literature analysis.
SKILL.md
Loading
Related Openclaw Skills
TikTok Product Launch OS (TK实拍打品OS)
An end-to-end, data-driven operating system designed to transform e-commerce products into repeatable, high-converting TikTok video campaigns.
Owl Browser Agent
An AI-native browser skill that renders pages as compact, handle-addressable OwlMark text to let agents navigate, click, and type without relying on screenshots or coordinate guessing.
File Management
A robust, secure cloud file management tool for AI agents that handles uploads up to 100MB, download URLs, sharing, and meta-tagging.
Data Format Validation
A multi-domain data format validation tool for AI agents that ensures clean input processing for JSON, network configurations, financial identifiers, and general strings.
Build Protocol - Engineering
A rigorous, multi-step engineering protocol for AI agents to design, build, test, and safely deploy complex software systems.
Build Protocol
A rigorous 9-step workflow and quality gate system for managing multi-agent collaboration to produce high-quality, long-form knowledge products.
Featured*
