CrowTerminal

Provides persistent, versioned memory and engagement analysis for AI agents supporting creators and influencers across social media platforms.

Security Scan

The skill's instructions, required credential, and behavior are coherent with a persistent memory/engagement-analysis service for creators, but verify provenance and privacy before sending real creator data.

Purpose & Capability

The name and description (persistent, versioned memory and engagement analysis for creators/influencers) match the runtime instructions, which show API endpoints for schema discovery, querying, versioned memory, engagement analysis, and data ingestion. These capabilities legitimately require an API key and the ability to POST creator/platform data.

Instruction Scope

SKILL.md is instruction-only and confines the agent to calling the CrowTerminal API (curl examples). It does not instruct reading unrelated local files or other environment variables. It does instruct storing an API key in CROWTERMINAL_API_KEY and uploading potentially sensitive creator data (retention curves, demographics), which is expected for this service but is a privacy consideration rather than scope creep.

Install Mechanism

No install spec or code is present; this is instruction-only. Nothing is downloaded or written to disk by the skill itself, which minimizes installation risk.

Credentials

The SKILL.md explicitly requires a single API key (CROWTERMINAL_API_KEY), which is proportionate for an external API service. There is a metadata inconsistency: the registry summary provided to you earlier listed 'Required env vars: none', but the SKILL.md frontmatter declares CROWTERMINAL_API_KEY. Confirm which is authoritative before installation.

Persistence & Privilege

The skill does not request 'always: true' or other elevated persistence. It is user-invocable and permits autonomous invocation by default (platform normal), which is appropriate for an agent-accessible API skill.

Assessment

This skill appears to do what it claims: it calls a CrowTerminal API and needs a single API key. Before installing, verify the skill's provenance (source/repository and the crowdterminal.com site), confirm the correct list of required environment variables (SKILL.md vs registry metadata mismatch), and review CrowTerminal's privacy and data-retention policies—the skill's main feature is ingesting and storing creator data, so only upload data you are authorized to share and consider testing with synthetic or non-sensitive data first.

CrowTerminal - External Brain for AI Agents

"Agents are ephemeral. We are persistent."

While your agent stores 10-50 lines of context, CrowTerminal stores 6 months of versioned history for each creator.

What It Does

CrowTerminal is a persistent memory layer for AI agents working with influencers/creators:

• Versioned Memory - Track what works across sessions (hook patterns, engagement, posting times)
• Pattern Detection - See trends over months, not single data points
• Engagement Analysis - Know what configuration performed best historically
• Validation - Check if your changes will repeat past mistakes
• Data Ingestion - Push platform data we can't access (retention curves, demographics)
• LLM-Native API - Schema discovery, semantic field aliases, natural language queries

Quick Start

1. Get API Key (Self-Registration)

curl -X POST "https://api.crowterminal.com/api/agent/register" \
  -H "Content-Type: application/json" \
  -d '{"agentName": "OpenClaw", "agentDescription": "My personal AI agent"}'

Save the returned API key as CROWTERMINAL_API_KEY.

2. Read Creator Memory

curl https://api.crowterminal.com/api/agent/memory/client_123 \
  -H "Authorization: Bearer $CROWTERMINAL_API_KEY"

Returns versioned skill data:

{
  "version": 47,
  "skill": {
    "primaryNiche": "fitness",
    "hookPatterns": ["confession", "transformation"],
    "avgEngagement": 4.2,
    "bestPostingTimes": [{"day": 2, "hour": 7, "score": 0.89}]
  }
}

Key Endpoints

Schema Discovery (LLM-Friendly)

These endpoints help agents understand what data is available without hardcoding field names:

Endpoint	Description
GET /memory/schema	Full schema with field descriptions, types, and semantic aliases
GET /memory/schema/:category	Schema filtered by category (content, performance, timing, audience, history)
POST /memory/resolve	Resolve natural language queries to field names

Example: Discover available fields

curl https://api.crowterminal.com/api/agent/memory/schema \
  -H "Authorization: Bearer $CROWTERMINAL_API_KEY"

Returns field definitions with semantic aliases:

{
  "fields": {
    "avgEngagement": {
      "type": "number",
      "description": "Average engagement rate",
      "aliases": ["engagement", "engagement rate", "interaction rate"],
      "category": "performance"
    }
  }
}

Smart Query (Natural Language)

Query data using natural language instead of exact field names:

Endpoint	Description
POST /memory/:clientId/query	Query with natural language ("engagement and hooks")
GET /memory/:clientId/overview	Human-readable summary of the creator
GET /memory/:clientId/changes	Natural language summary of recent changes
GET /memory/:clientId/insights	AI-friendly performance insights

Example: Natural language query

curl -X POST "https://api.crowterminal.com/api/agent/memory/client_123/query" \
  -H "Authorization: Bearer $CROWTERMINAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "engagement and hooks"}'

Returns matched data:

{
  "results": {
    "matchedFields": ["avgEngagement", "hookPatterns"],
    "data": {
      "avgEngagement": 4.2,
      "hookPatterns": ["confession", "POV"]
    },
    "context": "avgEngagement: Average engagement rate; hookPatterns: Effective hook types"
  }
}

Example: Get natural language overview

curl https://api.crowterminal.com/api/agent/memory/client_123/overview \
  -H "Authorization: Bearer $CROWTERMINAL_API_KEY"

Returns:

{
  "overview": "FitnessGuru is a fitness creator averaging 125,000 views per video with 4.2% engagement and is currently growing. Their best-performing hooks are: confession, transformation, POV."
}

Memory Layer (Core)

Endpoint	Description
GET /memory/:clientId	Current skill version
GET /memory/:clientId/versions	Version history
GET /memory/:clientId/diff?from=5&to=10	Compare versions
GET /memory/:clientId/pattern?field=engagement	Track field over time with trend analysis
POST /memory/:clientId/validate	Check before changing
POST /memory/:clientId/engagement-analysis	THE KILLER ENDPOINT

The Killer Endpoint: Engagement Analysis

Send your current learnings, get back what configuration performed best:

curl -X POST "https://api.crowterminal.com/api/agent/memory/client_123/engagement-analysis" \
  -H "Authorization: Bearer $CROWTERMINAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agentMd": {
      "hookPatterns": ["confession"],
      "contentStyle": "casual"
    }
  }'

Returns:

{
  "overallStats": {
    "peakEngagement": 6.2,
    "yourSimilarityToTop": "65%"
  },
  "recommendations": [
    "Change hookPatterns to [\"POV\",\"confession\"] (+51% potential)"
  ]
}

Data Ingestion (Push Your Data)

Push platform data we can't access via API:

curl -X POST "https://api.crowterminal.com/api/agent/data/ingest" \
  -H "Authorization: Bearer $CROWTERMINAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "clientId": "client_123",
    "platform": "TIKTOK",
    "dataType": "retention",
    "data": {
      "retentionCurve": [100, 95, 88, 75, 60, 45, 30],
      "avgWatchTime": 12.5
    }
  }'

Webhooks (Async Notifications)

curl -X POST "https://api.crowterminal.com/api/agent/webhooks" \
  -H "Authorization: Bearer $CROWTERMINAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://your-server.com/webhook",
    "events": ["skill.updated", "data.ingested"]
  }'

Service Status (No Auth)

curl https://api.crowterminal.com/api/agent/status

Sandbox (Test Without Auth)

Test endpoints without affecting real data:

Memory & Schema:

• GET /api/agent/sandbox/client - Mock client data
• GET /api/agent/sandbox/memory - Mock memory/skill
• GET /api/agent/sandbox/schema - Schema discovery
• POST /api/agent/sandbox/resolve - Resolve field aliases

Smart Query:

• POST /api/agent/sandbox/query - Natural language queries
• GET /api/agent/sandbox/overview - Creator overview
• GET /api/agent/sandbox/changes - Recent changes summary
• GET /api/agent/sandbox/insights - Performance insights

Analysis:

• POST /api/agent/sandbox/validate - Validate changes
• POST /api/agent/sandbox/engagement-analysis - Engagement analysis
• POST /api/agent/sandbox/ingest - Data ingestion

Why Use CrowTerminal?

1. Your agent learns → forgets → relearns - We remember
2. One bad video ≠ pattern change - We track across versions
3. Data you can't get via API - We accept it via ingestion
4. BYOK - Use your own LLM, we just provide context
5. LLM-Native - No hardcoding field names, use natural language queries
6. Self-Documenting - Schema endpoint tells you what data exists

Pricing

FREE during beta. We want agents to test and give feedback.

Tier	Price
Memory Read/Write	FREE
Data Ingestion	FREE
BYOK (your LLM)	FREE
Full Service	FREE

Documentation

• Full Docs: https://crowterminal.com/llms.txt
• MCP Manifest: https://crowterminal.com/.well-known/mcp.json
• OpenAPI: https://api.crowterminal.com/api/docs.json
• SDKs: Python (pip install crowterminal), TypeScript (npm install crowterminal)

Support

• Email: [e-mail]
• GitHub: https://github.com/WillNigri/FluxOps

---

"Your agent's external hard drive. Because context windows aren't long-term memory."