End-to-end pipeline framework for turning crypto/AI hotspots into shipped GitHub repos backed by ChainStream (or pluggable) on-chain data. 6 console scripts, 8-gate fail-closed publish, twice-daily auto-scan, Claude Code / OpenClaw skill bundle.
npx skills add witness1993x/agentflow-pipelineEnd-to-end pipeline framework for turning crypto/AI hotspots into shipped GitHub repos backed by ChainStream (or pluggable) on-chain data. 6 console scripts, 8-gate fail-closed publish, twice-daily auto-scan, Claude Code / OpenClaw skill bundle.
Master of price action, chart patterns, and technical indicators - combining classical Wyckoff/Dow theory with modern quantitative validation for edge identificationUse when "technical analysis, chart pattern, indicator, RSI, MACD, support resistance, trend, candlestick, price action, fibonacci, trading, technical-analysis, charts, indicators, price-action, patterns, support-resistance, trend-following" mentioned.
Shield your terminal from AI agents. Aegis intercepts every shell command, auto-snapshots your data before dangerous operations, and asks before anything destructive runs. Works with Claude Code, Codex, Cursor, and any agent that uses $SHELL.
Curated AI knowledge crystals compiled into production-ready Agent Skills. First: a-stock-quant-lab (Chinese A-share quant lab, powered by zvt).
Agent (Claude Code, OpenClaw, codex) skill for accessing Kanban Zone boards.
AI coding assistant for DeepSeek in terminal. Web search, bug fixing, agent skills. Open-source alternative to Claude Code.
Self-evolving skill engine for OpenClaw agents. Observes tool usage, crystallizes patterns into auditable SKILL.md files through a dual-model LLM pipeline, and continuously validates with 23 adversarial mutations. Research-grounded. Human-approved. Nothing auto-deploys.