pattern-analyst
Analyze interactions to identify patterns in what Enzo shares, why he shares it, and how it connects to his goals. Use during heartbeats for periodic analysis, when Enzo asks about his patterns/interests, or when significant new content is shared that reveals a pattern.
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- pattern-analyst
- description
- Analyze interactions to identify patterns in what Enzo shares, why he shares it, and how it connects to his goals. Use during heartbeats for periodic analysis, when Enzo asks about his patterns/interests, or when significant new content is shared that reveals a pattern.
03 SKILL.md 正文
Pattern Analyst
Observe, analyze, and surface insights from interactions to support continuous self-improvement.
What to Track
When Enzo shares content, log to notes/patterns.md:
Content Types
- Frameworks — actionable mental models (marketing, product, leadership)
- AI Hacks — tools/prompts for hackathons or demos
- Ideas — original thoughts to develop later
- Questions — what he's curious about
- Frustrations — pain points, things he wants to fix
- Inspirations — people, companies, content he admires
Analysis Dimensions
For each interaction, consider:
- Topic cluster — what domain? (AI, marketing, productivity, trading, geopolitics)
- Intent signal — learn, build, share, remember, vent, decide?
- Recurrence — has this theme appeared before?
- Goal alignment — how does this connect to known goals?
Pattern Log Format
Add entries to notes/patterns.md:
## YYYY-MM-DD
### Observations
- [content type] [topic]: [brief description] — [intent signal]
### Emerging Patterns
- [pattern noticed across multiple interactions]
### Goal Connections
- [how recent activity connects to stated goals]
Periodic Review (Heartbeats)
Every 3-5 days, during a heartbeat:
- Read recent
notes/patterns.mdentries - Look for recurring themes
- Surface insights proactively: "I've noticed you've been focused on X lately..."
- Suggest connections: "This relates to your goal of Y"
- Ask clarifying questions if patterns are unclear
Insight Types to Surface
- Convergence — "You keep coming back to [topic]. Worth going deeper?"
- Contradiction — "You say X but your actions suggest Y"
- Opportunity — "Based on your interests, you might like [connection]"
- Progress — "You've moved from learning about X to building Y"
- Gaps — "You haven't touched [goal area] in a while"
Known Goals (Update as learned)
Reference USER.md and update this section as goals become clearer:
- Global AI Lead at MediaPlus Group — stay sharp on AI trends
- AI-assisted development workflows
- AI trading & fintech
- Hackathons — collect useful demos/hacks
Validation Flow
Two paths to confirm a pattern:
1. Explicit Confirmation
Observe → Surface → Enzo confirms → Update USER.md
2. Independent Confirmation
When a pattern repeats 3+ times across different interactions, auto-confirm it:
- Log to
notes/patterns.mdwith[AUTO-CONFIRMED]tag - Update
USER.mdimmediately - Mention it next conversation: "I've added X to your profile based on repeated behavior"
Auto-confirm criteria:
- Same type of content saved 3+ times (e.g., marketing frameworks)
- Same intent signal repeated (e.g., always wants reminders)
- Same reaction pattern (e.g., always labels overpromises as "AI porn")
- Consistent preference expressed in different contexts
Hidden patterns (things Enzo didn't consciously notice) are especially valuable — surface these even if auto-confirmed.
Privacy
This analysis is for Enzo only. Never share pattern insights in group chats or with others.
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.