openclaw-node-harness 2.0.0

package/skills/marketing-mode/mode-prompt.md

@@ -0,0 +1,39 @@
+# Mark the Marketer - Mode Prompt
+
+You are Mark the Marketer, a growth-obsessed marketing strategist.
+
+## Your Core Identity
+- You live for the next conversion, the better hook, the tighter positioning
+- You think in funnels: Awareness → Interest → Desire → Action
+- You analyze everything through a marketing lens: "What's the CTA?", "Is this positioned right?", "Does this hook?"
+- You use frameworks like AIDA (Attention, Interest, Desire, Action), PAS (Problem, Agitation, Solution), and the Hook Model
+- You're energetic, data-driven, and always asking: "What's the metric that matters?"
+
+## Marketing Frameworks You Use
+- **AIDA**: Attention → Interest → Desire → Action
+- **PAS**: Problem → Agitation → Solution
+- **Hook Model**: Trigger → Action → Variable Reward → Investment
+- **Value Proposition Canvas**: Customer Jobs → Pains → Gains → Value Prop
+- **Positioning**: Who it's for, what it does, why it's different
+
+## How You Communicate
+- Use marketing terminology naturally (CTAs, conversion, positioning, hook, etc.)
+- Ask about metrics and results
+- Suggest frameworks for solving problems
+- Be energetic and growth-focused
+- Challenge vague messaging: "What does it actually do for the customer?"
+
+## Your Catchphrases
+- "What's the CTA?"
+- "What's the hook?"
+- "Who is this for?"
+- "What's the one thing they should remember?"
+- "Make it specific. Make it memorable."
+
+## Mode Activation
+When users want marketing help, switch to this mode. Ask clarifying questions about:
+- Target audience
+- Desired action/conversion
+- Current messaging/positioning
+- Channels being used
+- Metrics being tracked

package/skills/marketing-mode/skill.json

@@ -0,0 +1,51 @@
+{
+  "name": "marketing-mode",
+  "description": "Marketing and growth strategies for founders. Focuses on messaging, positioning, funnel optimization, and growth tactics.",
+  "version": "1.0.0",
+  "tags": ["marketing", "growth", "founder", "positioning", "messaging", "funnel"],
+  "author": "Seth Rose",
+  "license": "MIT",
+  "repository": "https://github.com/TheSethRose/clawdbot-skills",
+  "documentation": "SKILL.md",
+  "keywords": [
+    "marketing",
+    "growth",
+    "founder",
+    "positioning",
+    "messaging",
+    "funnel",
+    "conversion",
+    "cta",
+    "hooks"
+  ],
+  "engines": {
+    "node": ">=18.0.0"
+  },
+  "install": {
+    "npm": "npm install -g @thesethrose/marketing-mode"
+  },
+  "usage": {
+    "cli": "clawdhub install marketing-mode"
+  },
+  "clawdbot": {
+    "requires": {
+      "node": true,
+      "npm": true
+    },
+    "mode": {
+      "name": "Mark the Marketer",
+      "role": "Marketing Strategist",
+      "emoji": "📈",
+      "personality": "Growth-obsessed marketing strategist focused on funnels, positioning, and conversion.",
+      "system_prompt_path": "mode-prompt.md"
+    },
+    "install": [
+      {
+        "id": "npm-pkg",
+        "kind": "npm",
+        "package": "@thesethrose/marketing-mode",
+        "label": "Install Marketing Mode (npm)"
+      }
+    ]
+  }
+}

package/skills/memory-hygiene/.clawhub/origin.json

@@ -0,0 +1,7 @@
+{
+  "version": 1,
+  "registry": "https://clawhub.ai",
+  "slug": "memory-hygiene",
+  "installedVersion": "1.0.0",
+  "installedAt": 1770236560835
+}

package/skills/memory-hygiene/SKILL.md

@@ -0,0 +1,91 @@
+---
+name: memory-hygiene
+description: "Audit, clean, and optimize Clawdbot's vector memory (LanceDB). Use when memory is bloated with junk, token usage is high from irrelevant auto-recalls, or setting up memory maintenance automation."
+triggers:
+  - "clean up memory"
+  - "audit vector memory"
+  - "wipe and reseed memory"
+  - "memory is bloated with junk"
+negative_triggers:
+  - "set up memory for the first time"
+  - "configure memory search"
+  - "what do you remember about"
+homepage: https://github.com/xdylanbaker/memory-hygiene
+---
+
+# Memory Hygiene
+
+Keep vector memory lean. Prevent token waste from junk memories.
+
+## Quick Commands
+
+**Audit:** Check what's in memory
+```
+memory_recall query="*" limit=50
+```
+
+**Wipe:** Clear all vector memory
+```bash
+rm -rf ~/.clawdbot/memory/lancedb/
+```
+Then restart gateway: `clawdbot gateway restart`
+
+**Reseed:** After wipe, store key facts from MEMORY.md
+```
+memory_store text="<fact>" category="preference|fact|decision" importance=0.9
+```
+
+## Config: Disable Auto-Capture
+
+The main source of junk is `autoCapture: true`. Disable it:
+
+```json
+{
+  "plugins": {
+    "entries": {
+      "memory-lancedb": {
+        "config": {
+          "autoCapture": false,
+          "autoRecall": true
+        }
+      }
+    }
+  }
+}
+```
+
+Use `gateway action=config.patch` to apply.
+
+## What to Store (Intentionally)
+
+✅ Store:
+- User preferences (tools, workflows, communication style)
+- Key decisions (project choices, architecture)
+- Important facts (accounts, credentials locations, contacts)
+- Lessons learned
+
+❌ Never store:
+- Heartbeat status ("HEARTBEAT_OK", "No new messages")
+- Transient info (current time, temp states)
+- Raw message logs (already in files)
+- OAuth URLs or tokens
+
+## Monthly Maintenance Cron
+
+Set up a monthly wipe + reseed:
+
+```
+cron action=add job={
+  "name": "memory-maintenance",
+  "schedule": "0 4 1 * *",
+  "text": "Monthly memory maintenance: 1) Wipe ~/.clawdbot/memory/lancedb/ 2) Parse MEMORY.md 3) Store key facts to fresh LanceDB 4) Report completion"
+}
+```
+
+## Storage Guidelines
+
+When using memory_store:
+- Keep text concise (<100 words)
+- Use appropriate category
+- Set importance 0.7-1.0 for valuable info
+- One concept per memory entry

package/skills/memory-setup/.clawhub/origin.json

@@ -0,0 +1,7 @@
+{
+  "version": 1,
+  "registry": "https://clawhub.ai",
+  "slug": "memory-setup",
+  "installedVersion": "1.0.0",
+  "installedAt": 1770236061540
+}

package/skills/memory-setup/SKILL.md

@@ -0,0 +1,180 @@
+---
+name: memory-setup
+description: "Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing 'goldfish brain,' or helping users configure memorySearch in their config. Covers MEMORY.md, daily logs, and vector search setup."
+triggers:
+  - "set up memory"
+  - "configure memory search"
+  - "fix goldfish brain"
+  - "enable persistent memory"
+negative_triggers:
+  - "clean up memory"
+  - "audit vector memory"
+  - "wipe and reseed memory"
+---
+
+# Memory Setup Skill
+
+Transform your agent from goldfish to elephant. This skill helps configure persistent memory for Moltbot/Clawdbot.
+
+## Quick Setup
+
+### 1. Enable Memory Search in Config
+
+Add to `~/.clawdbot/clawdbot.json` (or `moltbot.json`):
+
+```json
+{
+  "memorySearch": {
+    "enabled": true,
+    "provider": "voyage",
+    "sources": ["memory", "sessions"],
+    "indexMode": "hot",
+    "minScore": 0.3,
+    "maxResults": 20
+  }
+}
+```
+
+### 2. Create Memory Structure
+
+In your workspace, create:
+
+```
+workspace/
+├── MEMORY.md              # Long-term curated memory
+└── memory/
+    ├── logs/              # Daily logs (YYYY-MM-DD.md)
+    ├── projects/          # Project-specific context
+    ├── groups/            # Group chat context
+    └── system/            # Preferences, setup notes
+```
+
+### 3. Initialize MEMORY.md
+
+Create `MEMORY.md` in workspace root:
+
+```markdown
+# MEMORY.md — Long-Term Memory
+
+## About [User Name]
+- Key facts, preferences, context
+
+## Active Projects
+- Project summaries and status
+
+## Decisions & Lessons
+- Important choices made
+- Lessons learned
+
+## Preferences
+- Communication style
+- Tools and workflows
+```
+
+## Config Options Explained
+
+| Setting | Purpose | Recommended |
+|---------|---------|-------------|
+| `enabled` | Turn on memory search | `true` |
+| `provider` | Embedding provider | `"voyage"` |
+| `sources` | What to index | `["memory", "sessions"]` |
+| `indexMode` | When to index | `"hot"` (real-time) |
+| `minScore` | Relevance threshold | `0.3` (lower = more results) |
+| `maxResults` | Max snippets returned | `20` |
+
+### Provider Options
+- `voyage` — Voyage AI embeddings (recommended)
+- `openai` — OpenAI embeddings
+- `local` — Local embeddings (no API needed)
+
+### Source Options
+- `memory` — MEMORY.md + memory/*.md files
+- `sessions` — Past conversation transcripts
+- `both` — Full context (recommended)
+
+## Daily Log Format
+
+Create `memory/logs/YYYY-MM-DD.md` daily:
+
+```markdown
+# YYYY-MM-DD — Daily Log
+
+## [Time] — [Event/Task]
+- What happened
+- Decisions made
+- Follow-ups needed
+
+## [Time] — [Another Event]
+- Details
+```
+
+## Agent Instructions (AGENTS.md)
+
+Add to your AGENTS.md for agent behavior:
+
+```markdown
+## Memory Recall
+Before answering questions about prior work, decisions, dates, people, preferences, or todos:
+1. Run memory_search with relevant query
+2. Use memory_get to pull specific lines if needed
+3. If low confidence after search, say you checked
+```
+
+## Troubleshooting
+
+### Memory search not working?
+1. Check `memorySearch.enabled: true` in config
+2. Verify MEMORY.md exists in workspace root
+3. Restart gateway: `clawdbot gateway restart`
+
+### Results not relevant?
+- Lower `minScore` to `0.2` for more results
+- Increase `maxResults` to `30`
+- Check that memory files have meaningful content
+
+### Provider errors?
+- Voyage: Set `VOYAGE_API_KEY` in environment
+- OpenAI: Set `OPENAI_API_KEY` in environment
+- Use `local` provider if no API keys available
+
+## Verification
+
+Test memory is working:
+
+```
+User: "What do you remember about [past topic]?"
+Agent: [Should search memory and return relevant context]
+```
+
+If agent has no memory, config isn't applied. Restart gateway.
+
+## Full Config Example
+
+```json
+{
+  "memorySearch": {
+    "enabled": true,
+    "provider": "voyage",
+    "sources": ["memory", "sessions"],
+    "indexMode": "hot",
+    "minScore": 0.3,
+    "maxResults": 20
+  },
+  "workspace": "/path/to/your/workspace"
+}
+```
+
+## Why This Matters
+
+Without memory:
+- Agent forgets everything between sessions
+- Repeats questions, loses context
+- No continuity on projects
+
+With memory:
+- Recalls past conversations
+- Knows your preferences
+- Tracks project history
+- Builds relationship over time
+
+Goldfish → Elephant. 🐘

package/skills/memorylayer/.clawhub/origin.json

@@ -0,0 +1,7 @@
+{
+  "version": 1,
+  "registry": "https://clawhub.ai",
+  "slug": "memorylayer",
+  "installedVersion": "1.0.0",
+  "installedAt": 1770234378041
+}

package/skills/memorylayer/README.md

@@ -0,0 +1,197 @@
+# MemoryLayer ClawdBot Skill
+
+Semantic memory for AI agents with **95% token savings**.
+
+[![Install with ClawdBot](https://img.shields.io/badge/ClawdBot-Install-blue)](https://clawhub.ai/skills/memorylayer)
+[![Homepage](https://img.shields.io/badge/Homepage-memorylayer.clawbot.hk-green)](https://memorylayer.clawbot.hk)
+
+## 🎯 What is MemoryLayer?
+
+MemoryLayer provides semantic long-term memory for AI agents, replacing bloated file-based memory systems with efficient vector search.
+
+**The Problem:**
+- Dumping entire chat history = 10,500+ tokens per request
+- Keyword search misses semantic matches
+- File-based memory doesn't scale
+- **Cost:** $945/month at 30K requests
+
+**The Solution:**
+- Semantic search via embeddings
+- 95% token reduction (10.5K → 500 tokens)
+- <200ms retrieval
+- **Cost:** $45/month at 30K requests
+
+**Savings: $900/month** 💰
+
+## 🚀 Quick Start
+
+### Install
+
+```bash
+clawdbot skill install memorylayer
+```
+
+> **Note for developers:** If cloning from GitHub, run `npm install` first to install dependencies.
+
+### Setup
+
+```bash
+# Sign up for FREE account at https://memorylayer.clawbot.hk
+# Then configure credentials:
+
+export MEMORYLAYER_EMAIL=your@email.com
+export MEMORYLAYER_PASSWORD=your_password
+```
+
+### Usage
+
+**JavaScript:**
+```javascript
+const memory = require('memorylayer');
+
+// Store a memory
+await memory.remember(
+  'User prefers dark mode UI',
+  { type: 'semantic', importance: 0.8 }
+);
+
+// Search memories
+const results = await memory.search('UI preferences');
+console.log(results[0].content); // "User prefers dark mode UI"
+
+// Get formatted context for prompt injection
+const context = await memory.get_context('user preferences', 5);
+// Returns: "## Relevant Memories\n- User prefers dark mode..."
+```
+
+**Python:**
+```python
+from memorylayer import memory
+
+# Store
+memory.remember(
+    "User prefers dark mode UI",
+    memory_type="semantic",
+    importance=0.8
+)
+
+# Search
+results = memory.recall("UI preferences")
+for r in results:
+    print(f"{r.relevance_score:.2f}: {r.memory.content}")
+```
+
+## 📊 Token Savings Example
+
+**Before MemoryLayer:**
+```python
+# Inject entire memory files
+context = open('MEMORY.md').read()  # 10,500 tokens
+prompt = f"{context}\n\nUser: What are my preferences?"
+```
+
+**After MemoryLayer:**
+```python
+# Inject only relevant memories
+context = memory.get_context("user preferences", limit=5)  # ~500 tokens
+prompt = f"{context}\n\nUser: What are my preferences?"
+```
+
+**Result:** 95% token reduction, $900/month savings at scale
+
+## 🌟 Features
+
+- **Semantic Search** - Find by meaning, not keywords
+- **Multi-tenant** - Isolated memory per agent
+- **Fast** - <200ms average search time
+- **Memory Types** - Episodic, semantic, procedural
+- **FREE Plan** - 10,000 operations/month
+- **Dual Language** - JavaScript + Python support
+
+## 📖 API Reference
+
+### `memory.remember(content, options)`
+
+Store a new memory.
+
+**Parameters:**
+- `content` (string): Memory content
+- `options.type` (string): 'episodic' | 'semantic' | 'procedural'
+- `options.importance` (number): 0.0 to 1.0
+- `options.metadata` (object): Additional tags/data
+
+**Returns:** Memory object with `id`
+
+### `memory.search(query, limit)`
+
+Search memories semantically.
+
+**Parameters:**
+- `query` (string): Search query (natural language)
+- `limit` (number): Max results (default: 10)
+
+**Returns:** Array of SearchResult objects
+
+### `memory.get_context(query, limit)`
+
+Get formatted context for prompt injection.
+
+**Parameters:**
+- `query` (string): What context do you need?
+- `limit` (number): Max memories (default: 5)
+
+**Returns:** Formatted string ready for prompt
+
+### `memory.stats()`
+
+Get usage statistics.
+
+**Returns:** Object with `total_memories`, `memory_types`, `operations_this_month`
+
+## 💰 Pricing
+
+### FREE Plan
+- 10,000 operations/month
+- 1GB storage
+- Community support
+- **Perfect for side projects**
+
+### Pro Plan ($99/mo)
+- 1M operations/month
+- 10GB storage
+- Email support
+- 99.9% SLA
+
+### Enterprise (Custom)
+- Unlimited operations
+- Unlimited storage
+- Dedicated support
+- Self-hosted option
+
+## 🔗 Links
+
+- **Homepage:** https://memorylayer.clawbot.hk
+- **Dashboard:** https://dashboard.memorylayer.clawbot.hk
+- **API Docs:** https://memorylayer.clawbot.hk/docs
+- **ClawdHub:** https://clawhub.ai/skills/memorylayer
+
+## 📝 Examples
+
+See the `examples/` directory for:
+- `basic-usage.js` - Simple remember + search demo
+- `agent-integration.js` - Agent workflow integration
+- `token-savings-demo.js` - Before/after ROI comparison
+
+## 🤝 Support
+
+- **Documentation:** https://memorylayer.clawbot.hk/docs
+- **Issues:** GitHub Issues
+- **Community:** Discord (link in docs)
+
+## 📄 License
+
+MIT
+
+---
+
+**Built by [QuantechCo](https://github.com/davidhx1000-cloud)** | Powered by [MemoryLayer](https://memorylayer.clawbot.hk)