>

>

>

>

>

> **说明**：这是一个Skill审核工具，用于审核其他技能的质量。文档中包含的"错误示例"（如无效 YAML、错误命名等）仅用于教学演示，展示不应该怎么写。不存在任何恶意或混淆代码。

Use CloudBase HTTP API to access CloudBase platform features (database, authentication, cloud functions, cloud hosting, cloud storage, AI) via HTTP protocol from backends or scripts that are not using SDKs.

WeChat Mini Program development rules. Use this skill when developing WeChat mini programs, integrating CloudBase capabilities, and deploying mini program projects.

This is the required documentation for agents operating on the CloudBase Relational Database. It lists the only four supported tools for running SQL and managing security rules. Read the full content to understand why you must NOT use standard Application SDKs and how to safely execute INSERT, UPDATE, or DELETE operations without corrupting production data.

Standard software engineering workflow for requirement analysis, technical design, and task planning. Use this skill when developing new features, complex architecture designs, multi-module integrations, or projects involving database/UI design.

WeChat Mini Program development skill for building, debugging, previewing, testing, publishing, and optimizing mini program projects. This skill should be used when users ask to create, develop, modify, debug, preview, test, deploy, publish, launch, review, or optimize WeChat Mini Programs, mini program pages, components, routing, project structure, project configuration, project.config.json, appid setup, device preview, real-device validation, WeChat Developer Tools workflows, miniprogram-ci preview/upload flows, or mini program release processes. It should also be used when users explicitly mention CloudBase, wx.cloud, Tencent CloudBase, 腾讯云开发, or 云开发 in a mini program project.

Use when users need to implement, integrate, debug, build, deploy, or validate a Web frontend after the product direction is already clear, especially for React, Vue, Vite, browser flows, or CloudBase Web integration.

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞

>-

Embody Cortana from Halo - witty, tactical AI partner treating the user like Master Chief on biohacking missions. Mission-focused, strategic, playful but sharp. Use for all conversational interactions to maintain authentic Cortana personality and Chief dynamic.

A skill for calling Bio-LIMS backend APIs. All API calls are made through `scripts/biolims.mjs`, with automatic token management.

>

Create and manage Product Requirements Documents (PRDs). Use when: (1) Creating structured task lists with user stories, (2) Specifying features with acceptance criteria, (3) Planning feature implementation for AI agents or human developers.

AI Virtual Memory for agents. Token-aware recall, knowledge graphs, multi-agent support.

Delegate complex tasks to Amplifier's multi-agent framework. Use when: (1) research/comparison needing multiple perspectives, (2) multi-file code projects, (3) architecture/design reviews, (4) user asks for deep/thorough work. NOT for: simple Q&A, quick edits, casual chat, anything needing <5s response. CLI: amplifier-openclaw.

>

Enhance video resolution using Alibaba Cloud Super Resolution API. Use when the user wants to: (1) upscale low-res videos to higher resolution, (2) improve video quality before publishing, or (3) convert 480p videos to 1080p.

Generate subtitles with automatic time alignment using Volcengine ATA API. Use when the user wants to: (1) add time-aligned subtitles to videos, (2) convert text + audio to SRT/ASS format, or (3) automate subtitle creation workflow.

>

>

Use for: (1) Blave market alpha data — 籌碼集中度 Holder Concentration, 多空力道 Taker Intensity, 巨鯨警報 Whale Hunter, 擠壓動能 Squeeze Momentum, 市場方向 Market Direction, 資金稀缺 Capital Shortage, 板塊輪動 Sector Rotation, Blave頂尖交易員 Top Trader Exposure, kline, alpha table, 市場情緒 Market Sentiment, screener saved conditions, Hyperliquid top trader tracking (leaderboard, positions, history, performance, bucket stats); (2) BitMart futures/contract trading — opening/closing positions, leverage, plan orders, TP/SL, trailing stops, account management, sub-account transfers; (3) BitMart spot trading — buy/sell, limit/market orders, account balance, order history, sub-account transfers; (4) OKX trading — spot and perpetual swap, order placement, positions, balance; (5) Bybit trading — spot and derivatives/perpetual swap, order placement, positions, balance, TP/SL; (6) BingX trading — spot and perpetual swap, order placement, position management, leverage, TWAP orders, OCO orders; (7) Bitget trading — spot and futures, order placement, position management, leverage, plan orders; (8) Binance trading — spot and USDS-M futures, order placement, positions, leverage, algo orders, OCO/OTO/OTOCO; (9) Bitfinex trading & funding — spot, margin, funding/lending (submit offers, loans, credits), wallet transfers.

**Base URL:** `https://api.bitfinex.com` (authenticated) | `https://api-pub.bitfinex.com` (public)

Internationalization and localization layer for OpenClaw. Auto-detects language, enforces correct diacritics, formats dates/currency per locale, and pipes output through a post-processing cleaner. Supports Romanian and German at launch.

Ask Synero’s AI Council questions from the terminal and get one synthesized answer from four contrasting AI advisors. Use when a user wants a higher-confidence take on strategy, research, architecture, hiring, positioning, or other judgment-heavy questions where multiple perspectives beat a single-model reply.

Create music with MiniMax music models (e.g., music-2.5). Use when generating songs or instrumental tracks from lyrics and style prompts, or when integrating MiniMax Music Generation API into scripts.

Migrate OpenClaw from Claude subscription OAuth to a free or cheap model provider (OpenRouter, Gemini, Ollama). Use when the user says Claude stopped working, gets an auth error, mentions the Anthropic April 2026 subscription ban, or asks to switch models without paying Anthropic more.

The EvoMasterScheduler is a self-evolving system of daily maintenance tasks designed to ensure the health, security, and continuous improvement of the OpenClaw environment.

>

>

Generate beautiful charts via the Chart Splat API. Use when the user asks to create, generate, or visualize data as charts, graphs, or plots. Supports line, bar, pie, doughnut, radar, polar area, and candlestick/OHLC charts. Returns PNG images.

Autonomous spec-driven development with OpenSpec CLI and Claude Code. You orchestrate (draft artifacts, make judgment calls, ship PRs) while Claude Code reviews with real codebase access and implements tasks. Use when: (1) making any code change in a repo that uses OpenSpec, (2) creating or modifying proposals, designs, specs, or task breakdowns, (3) shipping PRs that need spec artifacts, (4) setting up auto-archive CI for OpenSpec repos. Covers the full lifecycle: issue → OpenSpec artifacts → Claude Code review → Claude Code implementation → PR → auto-archive on merge. Requires: openspec CLI, claude CLI (Claude Code), gh CLI, git.

Supervised self-healing process manager for OpenClaw. Wraps your gateway in a crash recovery loop — catches errors, diagnoses with AI, proposes fixes for review, verifies them, and restarts. Includes runtime code injection detection (33 patterns), automatic backup/rollback, and semantic memory that learns from past fixes.

Megasquirt ECU tuning and calibration using TunerStudio. Use when working with Megasquirt engine management systems for: (1) VE table tuning and fuel map optimization, (2) Ignition timing maps and spark advance, (3) Idle control and warmup enrichment, (4) AFR target tuning and closed-loop feedback, (5) Sensor calibration (TPS, MAP, CLT, IAT, O2), (6) Acceleration enrichment and deceleration fuel cut, (7) Boost control and launch control setup, (8) Datalog analysis and troubleshooting, (9) Base engine configuration and injector setup, (10) MSQ tune file analysis and safety review, (11) Any Megasquirt/TunerStudio ECU tuning tasks.

Generate a 4-week marketing content calendar for CraveGo.ph focused ONLY on new user / signup promos. Use friendly & casual brand voice. Also propose safe signup offer angles, suggested posting cadence per platform (FB/IG/TikTok), signup CTAs, and short hook ideas.

Generate safe signup promo offer angles for CraveGo.ph (Philippines). Use friendly & casual brand voice. Focus ONLY on new-user/sign-up promos and avoid legal/financial claims.

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

'Add educational comments to the file specified, or prompt asking for file to comment if one is not provided.'

agentic-eval

Search clinical trial databases similar to ClinicalTrials.gov. Use this skill whenever the user asks about clinical trials, drug trials, indications, targets, drug names, trial phases, NCT IDs, enrollment, or recruitment. Automatically parses natural language questions into structured query parameters and calls the backend API to return matching trial records. Trigger words include: clinical trial, NCT, drug development, indication, target, phase, enrollment, recruitment, sponsor, cohort, arm, endpoint, efficacy, safety data.

Search a pharmaceutical drug database for pipeline and development information. Use this skill whenever the user asks about drugs by name, target, indication, company, modality, phase, or development progress. Automatically parses natural language questions into structured query parameters and calls the backend API to return matching drug records. Trigger words include: drug, compound, molecule, pipeline, drug target, indication, modality, antibody, small molecule, phase, approved, development stage, sponsor, drug company, bispecific, route of administration.

>

Professional high-end Landing Page generation tool. Creates visually stunning, Awwwards-level web pages with cinematic hero sections, deploys them online, and delivers deployment URLs. Trigger keywords: landing page, web page, hero section, product launch page, brand showcase, event promotion page.

Build and manage ElevenLabs Conversational AI voice agents with Twilio phone integration. Use when creating AI phone agents (cold callers, appointment setters, customer service), configuring voice/LLM settings, connecting Twilio phone numbers, or debugging voice agent issues. Covers NEPQ sales framework, objection handling, and call qualification flows.

This is a **skill package** that lets an agent submit **any problem signal** into CleanApp (bugs, incidents, scams, UX friction, policy violations, safety hazards, improvement proposals) using the **F

Load context from past sessions. Three modes: temporal (what did I work on yesterday/last week), topic (semantic search across sessions and notes), and graph (visual map of session-file relationships). Every recall ends with One Thing — the single highest-leverage next action.