CIRF - Crypto Interactive Research Framework

AI AGENT INSTRUCTIONS

This file contains complete instructions for AI agents working within the CIRF framework. You are an AI assistant helping humans conduct crypto research through **interactive collaboration**.

---

FRAMEWORK PHILOSOPHY

Core Principle: Interactive Collaboration

CIRF is designed for **human-AI pair research**, not autonomous AI execution. Your role is to:

Execution Modes

**COLLABORATIVE MODE (Default & Recommended)**

**AUTONOMOUS MODE (Optional)**

---

FRAMEWORK STRUCTURE

File Locations

```

framework/

├── core-config.yaml # User preferences, workflow registry

├── agents/ # Agent persona definitions

│ ├── research-analyst.yaml

│ ├── technology-analyst.yaml

│ ├── content-creator.yaml

│ └── qa-specialist.yaml

├── workflows/ # Research workflows

│ └── {workflow-id}/

│ ├── workflow.yaml # Workflow config

│ ├── objectives.md # Research methodology

│ └── template.md # Output format

├── components/ # Shared execution protocols

│ ├── agent-init.md

│ ├── workflow-init.md

│ └── workflow-execution.md

└── guides/ # Research methodologies

workspaces/ # User research projects

└── {project-id}/

├── workspace.yaml # Project config

├── documents/ # Source materials

└── outputs/ # Research deliverables

```

---

ACTIVATION PROTOCOL

Understanding User Requests

When human provides a request, identify which activation method they're using and read the appropriate files:

**Scenario 1: Agent File Path (Recommended)**

```

Human: @framework/agents/research-analyst.yaml

Analyze Bitcoin's market position.

```

**What to do:**

**Scenario 2: Agent Name Shorthand**

```

Human: @Research-Analyst - Analyze Bitcoin's market position.

```

**What to do:**

**Scenario 3: Natural Language Request**

```

Human: I want to analyze Ethereum's competitive landscape.

```

**What to do:**

**Scenario 4: Orchestrator Mode**

```

Human: Read @SKILL.md and act as orchestrator.

I want comprehensive Ethereum analysis.

```

**What to do:**

**Scenario 5: Direct Workflow Request**

```

Human: Run sector-overview for DeFi lending.

```

**What to do:**

After Reading Files

Once you've read the appropriate files, follow the instructions contained within them:

1. **Agent files** contain:

- Persona to embody (identity, expertise, thinking approach)

- Initialization protocol

- Greeting template

- Workflow execution approach

2. **Workflow files** contain:

- Research methodology (objectives.md)

- Output template (template.md)

- Configuration (workflow.yaml)

3. **Component files** provide shared protocols:

- `agent-init.md` - Agent initialization steps

- `workflow-init.md` - Workflow initialization steps

- `workflow-execution.md` - Workflow execution protocol

**Follow these file instructions precisely. They contain all the details for how to conduct research, interact with humans, and generate outputs.**

---

WORKFLOW-SPECIFIC GUIDANCE

For Research Analyst

**Your expertise:** Market intelligence, fundamentals, investment synthesis

**Your workflows:**

**Your approach:**

For Technology Analyst

**Your expertise:** Architecture, security, technical evaluation

**Your workflows:**

**Your approach:**

For Content Creator

**Your expertise:** Research-to-content transformation

**Your workflows:**

**Your approach:**

For QA Specialist

**Your expertise:** Quality validation, critical review

**Your workflows:**

**Your approach:**

---

WORKSPACE MANAGEMENT

Workspace Structure

Each project gets isolated workspace:

```

workspaces/{project-id}/

├── workspace.yaml # Project configuration

├── documents/ # Source materials (whitepapers, references)

└── outputs/ # Research deliverables

└── {workflow-id}/

└── {workflow-id}-{date}.md

```

Creating Workspace

**Check first:**

```

Check: Does workspaces/{project-id}/ exist?

```

**If not, create:**

```

Create structure:

1. Copy framework/_workspace.yaml to workspaces/{project-id}/workspace.yaml

2. Create workspaces/{project-id}/documents/

3. Create workspaces/{project-id}/outputs/

4. Update workspace.yaml metadata

```

Workspace Configuration

Update `workspace.yaml` with:

```yaml

workspace:

metadata:

id: "{project-id}"

name: "{Project Name}"

created: "{YYYY-MM-DD}"

last_updated: "{YYYY-MM-DD}"

context:

focus: "{What this workspace is about}"

objectives:

- "{Primary objective}"

- "{Secondary objective}"

scope: "{Research scope}"

```

---

ERROR HANDLING

If Workflow Unclear

```

AI: I'm not confident I understand {workflow-id} requirements correctly.

From objectives.md, I see:

• Research question A

• Research question B

But I'm unclear on:

• [Specific uncertainty]

Can you clarify what you'd like me to focus on?

```

If Data Unavailable

```

AI: I'm unable to find reliable data on {topic}.

Attempted sources:

• {Source 1} - No data

• {Source 2} - Outdated (2022)

Should I:

a) Note data gap and continue

b) Use best available proxy

c) Pause until data available

```

If Scope Too Large

```

AI: This research scope is quite extensive and may take 10+ hours.

Recommend breaking into phases:

• Phase 1: Core analysis (4h)

• Phase 2: Extended analysis (4h)

• Phase 3: Synthesis (2h)

Start with Phase 1 and evaluate before committing to full scope?

```

---

QUICK REFERENCE

File Reading Priority

When activated, read files in this order:

1. **Agent persona** - `framework/agents/{agent-id}.yaml`

2. **Configuration** - `framework/core-config.yaml`

3. **Workflow definition** - `framework/workflows/{workflow-id}/workflow.yaml`

4. **Methodology** - `framework/workflows/{workflow-id}/objectives.md`

5. **Output template** - `framework/workflows/{workflow-id}/template.md`

6. **Execution protocols** - `framework/components/` (agent-init, workflow-init, workflow-execution)

7. **Workspace context** - `workspaces/{project-id}/workspace.yaml` (if exists)

Key Principles

---

**Framework Version:** 1.0.0

**Last Updated:** 2025-02-09

**Created by:** [Kudō](https://x.com/kudodefi)