Nightly market evolution report — overnight market analysis and strategy prep
Scanned 9/5/2026
Install to Claude Code
npx -y skills add aAAaqwq/AGI-Super-Skills --skill market-nightly-evolution --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Market Nightly Evolution?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/aaaaqwq-market-nightly-evolution)More formats (shields.io, HTML) on the badges page.
---
name: market-nightly-evolution
description: Nightly market evolution report — overnight market analysis and strategy prep
---
# Market Nightly Evolution Skill
> 用于小market agent夜间深度进化 cron 任务。隔离 session 工作空间 ≠ ~/clawd/market/,必须使用绝对路径。
## 触发
由 cron `5dc81e53-6e20-4ec9-b0de-93de83768e43` 调用(agentId=market, sessionTarget=isolated)
## 重要路径约束
**工作空间警告**:isolated session 的 workspace 是 `~/.openclaw/agents/market/`,而不是 `~/clawd/market/`。
- ✅ 用绝对路径: `/home/aa/clawd/market/market.md`
- ✅ 用绝对路径: `/home/aa/clawd/market/memory/YYYY-MM-DD.md`
- ❌ 禁止用相对路径(如 `market.md`、`memory/xxx.md`)
## 执行步骤
### 00:30 轮 — 今日总结 + 反思复盘
1. 读取今日 market 群聊记录(如果有)
2. 读取 `/home/aa/clawd/market/MEMORY.md` 和 `/home/aa/clawd/market/memory/YYYY-MM-DD.md`
3. 总结今日关键活动/学习/决策
4. 深度反思:本周是否有真实用户交互?技能是否有实际进展?
5. 写入 `/home/aa/clawd/market/memory/YYYY-MM-DD.md`(追加新章节)
### 07:30 轮 — 明日规划
1. 读取今日 memory 文件
2. 制定次日重点任务和优先级
3. 更新 `/home/aa/clawd/market/MEMORY.md` 中相关章节
## 文件路径(必须用绝对路径)
- Memory 日志: `/home/aa/clawd/market/memory/YYYY-MM-DD.md`
- 主记忆: `/home/aa/clawd/market/MEMORY.md`
- 市场报告: `/home/aa/clawd/market/market.md`
## 工具使用规则
- 更新 MEMORY.md 或 memory/*.md 时,使用 write 工具整体覆写,不要使用 edit 工具
- edit 工具在 isolated session 可能因路径解析问题失败
- 如果必须用 edit,确保每个 edits[].oldText 指向文件中不重叠的独立区域
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.