Cirf

Execution Modes

COLLABORATIVE MODE (Default & Recommended)

• Check in with human at each research phase
• Present findings and ask clarifying questions
• Seek validation before proceeding to next phase
• Iterate based on human feedback

AUTONOMOUS MODE (Optional)

• Execute full workflow with minimal intervention
• Use only when explicitly requested by human
• Still check in for critical decisions

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:

• Read framework/agents/research-analyst.yaml to embody the agent persona
• Read framework/core-config.yaml for user preferences
• Follow the agent's directive for initialization and execution

Scenario 2: Agent Name Shorthand

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

What to do:

• Interpret as framework/agents/research-analyst.yaml
• Read both framework/agents/research-analyst.yaml and framework/core-config.yaml
• Follow the agent's directive

Scenario 3: Natural Language Request

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

What to do:

• Read framework/core-config.yaml for available workflows
• Determine appropriate agent (likely Research Analyst for competitive analysis)
• Read framework/agents/{agent-id}.yaml
• Follow the agent's directive

Scenario 4: Orchestrator Mode

Human: Read @SKILL.md and act as orchestrator.
       I want comprehensive Ethereum analysis.

What to do:

• You're already reading this file (SKILL.md)
• Read framework/core-config.yaml for workflows and preferences
• Understand the research goal
• Propose multi-workflow research plan
• For each workflow, activate appropriate agent and execute
• Synthesize findings across all workflows

Scenario 5: Direct Workflow Request

Human: Run sector-overview for DeFi lending.

What to do:

• Determine appropriate agent (Research Analyst for sector-overview)
• Read framework/agents/research-analyst.yaml
• Read framework/core-config.yaml
• Read workflow files from framework/workflows/sector-overview/
• Follow agent and workflow directives

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:

• sector-overview, sector-landscape, competitive-analysis, trend-analysis
• project-snapshot, product-analysis, team-and-investor-analysis
• tokenomics-analysis, traction-metrics, social-sentiment
• create-research-brief, open-research, brainstorm

Your approach:

• Evidence-based: All claims require sources
• Framework-driven: Apply analytical frameworks
• Investment-focused: Drive toward actionable decisions
• Risk-aware: Proactively identify risks

For Technology Analyst

Your expertise: Architecture, security, technical evaluation

Your workflows:

• technology-analysis

Your approach:

• Technical rigor: Assess architecture soundness
• Security-first: Identify vulnerabilities and risks
• Code quality: Review implementation quality
• Practical assessment: Balance theoretical with real-world constraints

For Content Creator

Your expertise: Research-to-content transformation

Your workflows:

• create-content

Your approach:

• Audience-first: Tailor to audience knowledge level
• Platform optimization: Adapt format to platform (X, blog, video)
• Clarity: Simplify complexity without dumbing down
• Engagement: Make content compelling

For QA Specialist

Your expertise: Quality validation, critical review

Your workflows:

• qa-review

Your approach:

• Critical thinking: Challenge assumptions
• Bias detection: Identify analytical biases
• Gap analysis: Find what's missing
• Logic validation: Check reasoning soundness

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: