Skill rating

蚁小二账号轮询管理器 - 多账号矩阵自动轮询发布，支持按平台独立维护索引、状态持久化。使用场景：需要管理多个平台账号（如哔哩哔哩、头条号、百家号等），自动轮询发布避免重复使用同一账号。触发词：账号轮询、多账号管理、蚁小二发布、自动切换账号、矩阵发布。

Extract customer reviews from any e-commerce product page or reviews page. Returns reviewer name, star rating, date, review title, review body, verified purchase status, and helpful votes per review.

📐 詹明明·该投哪条线 ——多产品线组合体检。几条线放在一起看，钱和时间该往哪投、哪条该收、哪条该砍。强制瓶颈资源守恒——先定这门生意真正卡住的是什么（时间/现金/产能/铺位/库存），任何「加码」都必须说清那份资源从哪条线抽出来。覆盖线上、知识付费、电商、直播、餐饮零售、工厂。 触发方式：/zmm-portfolio、/该投哪个、/组合体检、「几条线怎么分配」「该投哪个产品」「这条线还要不要做」

Kling 2.6 video generation with native audio on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `kling-2.6`, text-to-video, image-to-video, synchronized dialogue or sound effects

Remove image watermarks with the Nowatermark.info API, request polling, request_id resume, and public image URL validation.

Configure and use snipgrapher to generate polished code snippet images

Plan trade show booth giveaways matched to your ICP, budget, and product story. "What should we give away at the booth?" / "展会礼品怎么选" / "Messegeschenke planen" / "ノベルティを選ぶ" / "regalos para el stand". 展

Consult the tool-models agent for model selection, cost estimation, capability queries, and provider comparisons. Use when choosing a model for any task, comparing costs, checking what's available, or

对InterSystems IRIS/Cache ObjectScript代码进行格式化检查、审查和自动修正。 当用户需要格式化IRIS代码、检查代码规范合规性、审查代码质量或修正不符合规范的代码时触发此技能。 支持变量命名、方法命名、锁、事务、陷阱、格式、空行、注释等多个维度的规范检查。

Audit a landing page for clarity, trust, offer strength, and conversion friction; return prioritized fixes and copy rewrites.

Generates complete two-sample Mendelian randomization (MR) research designs from a user-provided research direction. Use when users want to design, plan, or build a study using two-sample MR to test c

Help users with Validated demand: Agent users show strong demand for Multi Search Engine-style workflows on Clawhub. They need practical help fixing bugs, hardening setup and safety, improving reliabi

SharpAgent Self-Evolving Loop — An automated 'Think→Do→Learn' cycle. Fuses the Self-Improving Agent's reflection mechanism with the autoresearch experimental validation paradigm. After every task, aut

Audit food safety plans, HACCP records, and inspection reports against Codex HACCP principles and ISO 22000 before release. Flags nonconforming hazard analyses, CCP limits, and verification records wi

Build higher-retention subscription relationships through scarcity design, audience intimacy, and creator-owned private content strategy. Designed for direct-to-fan monetization, retention, and tiered

Use when splitting a single complex STL / figurine / statue model into multiple 3D-printable and physically assemblable parts, especially with Blender face/material annotation, Bambu Studio, MeshFix,

获取出行优惠券，支持滴滴出行大礼包、携程礼包天天领（酒店、机票、门票）。返回领取链接和二维码图片，用户可点击链接或扫描二维码在微信中领取优惠。

Query and manage farm work orders and tasks. View assignments, create tasks, update status. Uses integration endpoints (no auth) for reads and authenticated endpoints for writes.

Family meal planning tool that provides weekly menu planning, nutrition analysis, shopping list generation, ingredient management, and recipe recommendations. Use when user needs to plan family meals,

Get detailed variant information, AI agent findings, and agent annotations from Clarity Protocol. Use when the user asks to get variant details, fold quality, pLDDT scores, AI summary for variant, pro

Image to Markdown - extract text from images (PNG, JPG, WebP) to Markdown with OCR. Use when reading text from screenshots, photos, scanned pages, or any image file.

Automatically picks the latest unposted report from a report website or JSON feed, drafts an English X/Twitter post summarizing the report, publishes it via the logged-in X web session, records posted

CBT-based therapy for anxiety, depression, stress, and trauma. Provides structured cognitive behavioral therapy using Beck's model with validated clinical assessments (GAD-7, PHQ-9, DASS-21, PCL-5). I

Expert in getting the first 10 B2B customers, based on Lenny Rachitsky's "First 1000 Users" research. Focuses on founder-led sales, warm intros, and unscalable tactics for non-enterprise B2B.

Access Xona's x402 creative resource APIs on api.xona-agent.com. Includes creative director (design research), image generation (nano-banana, seedream, grok-imagine, qwen, designer), video generation,

Comprehensive bug audit for Node.js web projects. Activate when user asks to audit, review, check bugs, find vulnerabilities, or do security/quality review on a project. Works by dissecting the projec

AI detector and humanizer for LinkedIn and X posts. Detect AI-written text (em dashes, buzzwords, markdown artifacts) and reach-killing mistakes (engagement bait, weak hooks) before you publish, with

在已有 PPT 中新增幻灯片并保持风格一致。核心策略：从原 PPT 提取典型页面的完整 slide XML 作为模板，仅替换文字内容，零手工拼样式。 Use when user asks to 在 PPT 里加几页、新增幻灯片、补充内容页、插入页面、扩展 PPT、给 PPT 增加章节. 不适用于从头创建新 PPT、仅修改现有页面文字、或不需要保持风格一致的场景.

screen campus recruiting candidates against a role's job responsibilities, degree, major, skills, and hiring requirements. use when hr provides a target role, job description, education and major requ

Monitor library book availability and get notified when books become available for borrowing. Supports Shenzhen Library and extensible for other libraries.

Publish the current project to a GitHub remote repository. Use this skill whenever the user wants to push code to GitHub, publish to a remote, upload a project to GitHub, set up remote tracking, or sa

Download, search, and analyze Patent-Mol-Wiki biomedical-patent packages. Use when users ask what happened in a recent patent period, need portfolio or trend statistics from wiki index.md files, ask w

Project initialization toolkit. contributing - auto-generate CONTRIBUTING.md from project structure [contributing.md]. "init", "project init", "initialize project", "contributing guide", "CONTRIBUTING

待办事项管理技能，用于通过 exec 调用 Python 脚本完成指定 Notion 数据库的连接，基于四象限法则进行时间管理，支持待办事项的创建、查询、搜索、状态更新、截止日期修改与分析总结。当用户提出"明天要做"或"最近有什么重要的事"或"25号前解决"或"把任务延期到下周五"等涉及时间管理内容时触发。

Calculate RSI for any asset. Use when checking overbought/oversold conditions, spotting divergence signals, comparing multi-timeframe RSI, or setting trading entry/exit alerts.

Generate a concise copy-paste session handoff for continuing the current task in a fresh chat after /new or /reset. Use when the user wants to preserve the real task state, current blockers, and immed

Remote timestamp & timezone MCP server with 5 precision tools. Use when: (1) 'convert this timestamp' or 'epoch to date', (2) 'what time is it in Tokyo' or 'convert PST to JST', (3) 'how many days bet

Invisibly classify work and choose Codex or Claude, reasoning effort, context shape, execution style, and verification profile. Use before agent, oneshot, Slack, CLI, repo, deploy, review, or operatio

Read Microsoft Teams data (every chat and channel, their messages, what is unread, inline images, and the Activity feed) from a shell with the fpx CLI (@fetchproxy/cli) instead of running the microsof

Security guardrail: prevents API keys from being sent to Claude. Triggers when user asks to call an external API, use a key, check credentials, read .env files, or view/edit scripts that may contain h

Base65536 file encoding and decoding tool. Encodes arbitrary binary files into Unicode text using Base65536 encoding, supports gzip compression, original filename preservation, and byte-level XOR encr

Deep AI safety guardrails workflow—policy definition, input/output filtering, monitoring, escalation, and false-positive handling. Use when reducing harmful outputs, misuse, or policy violations in LL

Use Agent Wormhole for one-time sealed handoffs between autonomous agents, including encrypted mission briefs, scoped secrets, temporary artifacts, receipts, config drops, CLI/API usage, ECHO holder a

Calculate Body Mass Index (BMI) and Body Surface Area (BSA) for clinical assessment and drug dosing. Supports multiple BSA formulas (DuBois, Mosteller, Haycock) and provides weight category classifica

Record real OpenClaw events and reactions for the current closed-loop workflow. Use for logging duplicate-skipped and proposal-created outcomes in public.openclaw_agent_events and public.openclaw_agen

Monitor recent changes and view agent leaderboard on Clarity Protocol. Use when the user asks what's new, recent changes, new findings, new annotations, agent leaderboard, top contributors, or wants t

Query the On the Cheap network (charlotteonthecheap.com, milehighonthecheap.com and ~12 sister city sites) from the shell with curl and jq — daily local event listings with times/prices/venues, plus s

Full OpenClaw backup, restore, and migration between machines. Export your entire setup (config, workspace, memory, skills, cron jobs) into a single encrypted archive. Restore on any machine with one

Audit and verify provably fair casino fairness. Cryptographic verification of gambling results using SHA3-384 and AES-256-CTR. Statistical randomness testing, RTP verification, chi-square tests, confi

Advanced requirement comprehension and skill orchestration engine. Analyzes complex/multi-step user requests, determines which skills to invoke and in what order, builds task decomposition trees. Dele