Policy-gated execution + tamper-evident audit trail for VAIBot/OpenClaw operations. Use to precheck/deny/require-approval before shell execution, and to prod...
Deterministic model routing for OpenClaw with prefix routing (@codex/@mini), timezone-aware schedule switching, verify-after-switch, rollback, lock protectio...
智能模型路由系统，根据任务复杂度自动切换 AI 模型（fast/thinking）。 当需要： - 自动选择最优 AI 模型（简单任务用 k2p5，复杂任务用 thinking） - 根据
Auto-escalating multi-tier memory search that cascades from in-memory cache through SQLite, grep, and LanceDB vector search to find the best answer with mini...
自动生成并在指定时间通过飞书推送每日研究进展报告，内容涵盖今日进展、延续项目、明日计划及系统状态，字数不超1000字。
--- name: org-learning-ops-skill description: 全量会话分析 + 每日技能盘点分配 + CEO学习日报与热门skills雷达联动输出。 version: 1.0.0 --- # Org Learning Ops Skill ## 目
Track detailed AI agent expenses, revenues, budgets, and ROI with per-agent attribution and alerts for efficient micro-budget financial management.
Powerful web scraping, crawling, and data extraction with stealth anti-bot bypass (Cloudflare Turnstile, CAPTCHAs). Use when: (1) scraping websites that bloc...
Curated skill bundle for fintech startups, neobanks, payment processors and wealth-management platforms. Activates the firm pyramid with Finance, Legal, Engi...
Use this skill when users need to search for datasets, download data files, or explore data repositories. Triggers include: requests to "find datasets", "search for data", "download dataset from Kaggl
Post-processing skill for firm-orchestration: converts the structured JSON output of a multi-agent workflow run into real deliverables — GitHub Pull Requests...
Connect OpenClaw-style runs to VizClaw live rooms from a ClawHub-installable skill. Use when you need quick room creation, JSONL/websocket bridging, trigger and agent event streaming, or safe overview
Expert skill for OpenClaw (formerly Clawdbot/MoltBot) — the self-hosted AI agent framework. ALWAYS use when user mentions OpenClaw, Clawdbot, MoltBot, opencl...
Git-backed issue tracker for AI agents. Use when managing tasks, dependencies, or multi-step work. Triggers on task tracking, issue management, dependency graphs, ready work queues, or mentions of "be
Human-in-the-loop security layer. Intercepts high-risk commands and requires push notification approval.
Lightweight operational audit logging for AI assistants, agent workspaces, and personal automation systems. Use when you need a structured way to record high...
Bidirectional sync between Obsidian PKM (human-friendly notes) and structured ontology (machine-queryable graph). Automatically extracts entities and relatio...
--- name: queue-task description: Durable queue-task helper for resumable, idempotent batch jobs in task-father task folders. --- # queue-task Use this skill for durable long-running queue jobs with
Generate narrative chronicles of developer work from git history, session transcripts, and memory files. Use when the user asks "what did I do today/this wee...
Run QCut's native TypeScript pipeline CLI for AI content generation, video analysis, transcription, YAML pipelines, ViMax agentic video production, and proje...
Privacy-first UX research ethnography for OpenClaw. Use when asked to observe OpenClaw usage over time, extract local session data and conversations, analyze...
AI runtime security monitoring — context graph analysis, runtime audit log correlation with CVE findings, and vulnerability analytics queries. Use when the u...
自动增量提取对话中的结构化知识，智能过滤无用信息，动态聚类主题，支持状态追踪和长期价值沉淀。
Automatic conversation backup system for Obsidian with incremental snapshots, hourly breakdowns, and formatted chat-style markdown. Use when setting up conversation archival, preventing data loss from