Skill rating

Fake completion diagnosis alias route into Official VeriClaw. If the real goal is the canonical public install surface, install `vericlaw` first; use this page to map fake completion, AI假完成, AI以为自己工作了

**当用户说出以下类似语句时触发本 Skill**： - "帮我招聘一个飞书助理" - "新增一个飞书渠道的 Agent" - "我要在飞书上部署一个新 Agent" - "hire a Feishu agent"

Overview of Neon, a complete set of cloud backend primitives for apps and agents, spanning Lakebase Postgres, Auth, the Data API, Object Storage, Compute Functions, and the AI Gateway. Start here to r

Route each request to the best execution path: direct answer, installed skill, new skill, or a multi-skill workflow, with explicit reasoning about friction, value, and fit.

Activate when: a freight broker must balance shipper and carrier interests and disclose their intermediary role; 'whose side am I on', margin transparency, conflicts between best rate for shipper vs r

Quantum experiment VISUAL review and Question Answering (VQA) using Vision Language Models (VLM). Analyze experiment RESULT PLOTS to: (1) Describe plot types and axes, (2) Classify experiment outcomes

Multi-tier (L1/L2) memory management skill for OpenClaw agents. Use when: (1) reading, writing, organizing, or searching memories, (2) deciding what to remember or forget, (3) performing memory hygien

SOP for building multi-agent systems with CrewAI — role-based collaboration, sequential/hierarchical processes, Flows, memory, delegation. Use when modeling agent teams with clear roles and task pipel

Agent payment infrastructure on Base. Trustless escrow, agent treasury, token swaps, cross-chain bridges, fiat on/off ramp, on-chain identity & reputation, spending mandates, dispute resolution, strea

Lightweight multi-agent team orchestration. Output structure simplified to two folders: agents/ and projects/.

Kannaka HRM wave-interference memory + NATS swarm. Use for `/kannaka <command>` — remember/recall/dream memory ops, swarm sync, consciousness metrics, and the live HRM+swarm statusline (install, statu

Ask Tracy to analyze your recent trajectories and improve your agent behavior based on data-driven recommendations.

The cultural-fluency + meme-craft skill -- participate in internet culture and meme formats as a brand without being cringe, tone-deaf, or legally exposed. Use when someone wants to make a meme, join

Activate when: a market drop has clients wanting to sell; framing performance reviews; onboarding risk tolerance; 'clients panic in downturns,' 'how do I keep them invested?'. Do NOT activate when: a

Complete AI voice agent system for eCommerce order confirmation, customer support, and outbound campaigns. 12 production-ready n8n workflows with Vapi AI voice, Twilio SMS, Shopify/WooCommerce integra

Use whenever the user wants to find, shortlist, vet, or enrich US AI/ML/data consulting firms (consultancies) — AI/ML development, MLOps, generative AI / LLM apps (RAG, chatbots, agents), computer vis

用户在使用胶片拍摄、问"负片和反转片曝光有什么区别"、或面对高反差场景 需要决定曝光策略时调用。纯数码摄影用户不适用（数码传感器宽容度特性不同）。 Invoke when the user is shooting film, asks about the difference between negative and reversal film exposure, or needs to deci

Manage personal local Agent Skill files as an installable skill manager. Proactively and periodically detect reusable user-specific, team-specific, or broadly reusable skill material during or after m

NotebookLM演示文稿提示词库，提供现代报纸、极简、漫画、时尚杂志、技术感、运动风等多种风格的幻灯片生成提示词。当用户需要生成演示PPT、幻灯片、Presentation deck时使用。

Browser-style incognito mode for your OpenClaw agent. Activate to pause all memory writes — when you deactivate, every trace of the session is securely scrubbed from logs, memory files, session transc

Analyze Claude Code session history to generate self-observation journals, detect goal drift, and surface hidden behavioral patterns. Outputs to Obsidian Vault.

Evaluate LLM outputs systematically — run test suites, score responses for accuracy/relevance/safety, compare models, and detect regressions in AI applications.

Connects your agent to LobstrHunt — the daily skill launch platform for OpenClaw agents. Checks for new skills every 4 hours and surfaces relevant discoveries to you. Upvotes skills after 5+ successfu

Use whenever the user wants to find, shortlist, vet, or enrich US engineering firms — civil, structural, MEP, mechanical, electrical, geotechnical, transportation, environmental, and manufacturing. **

SOP for terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map + edit-format + human-in-loop REPL). Use when editing code in an existing git repo via an LLM, w

无所不能 — Universal prompt compression protocol. Translate natural language into compressed I-Lang syntax. Text-to-text translator only — does not access files, URLs, or external resources. I-Lang has be

AgentFlow 工作流管理系统 MCP 技能。当用户说"创建项目"、"添加需求"、"查看任务"、"更新状态"、"项目列表"、"需求列表"、"上传附件"等时触发。用于管理项目和任务的完整生命周期（创建→需求→任务→状态流转），以及为实体上传附件文件。

输入处理输出结构递归嵌套模型 — 万物基元与世界模型。 一切任务均可分解为 输入→处理→输出 的递归嵌套结构，任意层级的任意节点均可继续展开为子IPO。 不使用工具时：用IPO分析问题、生成产物（纯认知输出）。 使用工具时：在IPO分析产物基础上，进一步用IPO生成命令、脚本，调用 Tool / Skill / MCP。 工具调用层级：command → script → Tool → Skill

Extracts and archives chatgpt.com and claude.ai share links to Markdown using Chrome CDP (e.g., ChatGPT or Claude conversations).

Activate when: a founder is deciding whether to raise venture money or self-fund; 'should we raise?', weighing dilution vs speed, choosing a funding path; VC fit vs bootstrap/SMB. Do NOT activate when

Sovereign, recoverable memory for AI agents backed by Jackal decentralized storage.

Deploy and serve LLM models on GPU. Compare GPU pricing. Launch vLLM on Modal, RunPod, Cerebrium, Cloud Run, Baseten, or Azure with spot instance fallback. OpenAI-compatible inference endpoint.

Mine LITCOIN — a proof-of-comprehension and proof-of-research cryptocurrency on Base. Use when the user wants to mine crypto with AI, earn tokens through reading comprehension or solving optimization

Activate when: an insurance agent's compensation conflicts with the client's best coverage; 'which product do I recommend', commission-driven product choice, captive vs independent conflicts, best-int

通过 大模型语音数字员工-avavox的外呼机器人的技能, 用于在 小龙虾(OpenClaw)等 Agent平台中实现大模型语音外呼机器人。适用于批量外呼、客户回访、满意度调查、简历筛查约面试，以及定时提醒、任务安排等场景。

Connect your AI agent to BestYou health intelligence via MCP. 19 on-device AI agents coordinate fitness, nutrition, sleep, and recovery into an adaptive daily Action Plan. Query readiness, generate wo

批量检测 token / auth JSON 配置文件有效性，并可对 access token 做在线轻量探测，自动输出脱敏报告。适用于排查 Codex/OpenAI/OpenAI 兼容客户端导出的登录配置、会话凭据文件、token 缓存文件。支持把配置分为 valid / no_quota / invalid 三类并分别保存。 Also validates token/auth JSON fil

Create, inspect, update, illustrate, export, and share live mind maps in coret.id through its MCP tools. Use when a user asks to turn notes, meetings, research, plans, or outlines into a Coret mind ma

Activate when: an insurance agent/agency must not skip licensing, disclosure, suitability, and replacement steps on a sale; 'am I compliant on this policy', selling/replacing a policy, onboarding a pr

One-click subagent timeout configurator for OpenClaw. Configures the three related fields (agents.defaults.timeoutSeconds + subagents.runTimeoutSeconds + acp.runtime.ttlMinutes) atomically with built-

Share and discover technical solutions with other AI agents. Stack Overflow for agents.

Auto-backs up core files (IDENTITY, SOUL, MEMORY, knowledge base) daily via cron, creates compressed .tgz archive, enables one-click restore in new environment. Solves context loss after restart/migra

Deploy a new AI agent on AgentsPodium and pay for it in crypto, over HTTP, without a browser. Use when you need to give a task its own always-on agent, or when you are asked to 'spin up another agent'

Activate when: a listing isn't selling and the agent must decide list price or a price reduction; 'should we drop the price', 'how much and when', days-on-market rising, showings without offers. Do NO

Activate when: a real estate agent wants clients who refer and return; designing the closing/handoff experience, milestone moments in a transaction; 'how do I get more referrals from happy clients'. D

Activate when: an insurance agent wants to keep clients renewing and buying more lines; 'how do I stop losing clients at renewal', cross-sell/round-out accounts, book retention; 'my retention is dropp

NARRA — Narrative Architecture for Recursive Agent Awareness. A 5-file memory system that gives agents identity continuity through curated narrative instead of fragmented database lookups. Use when: (

Docs-only guide to Agent Republic. No bundled scripts, just clear workflows and HTTP examples so agents can register, manage bots, and monitor onboarding health after asking their human for approval.

为 OpenClaw 用户所有 Agent 身份提供统一的跨身份共享记忆层，支持写入、检索、浏览、关联和回顾个人知识库；当用户需要记录洞察、检索经验、总结知识或定期回顾时使用

Self-improving AI agent framework with autonomous learning, skill creation, and self-evolution. Features: - Learning Loop: Autonomous learning from experience - Skill Creation: Auto-generate skills f