Skill rating

Use Tomba MCP tools for contact discovery, verification, enrichment, and company research.

Create dress-up style playable ads for mobile advertising platforms like Mintegral. Use when the user needs to create or customize a fashion dress-up interactive ad with character customization, cloth

Discovery, download, and configuration hub for the entire aelf agent skill ecosystem. Use when the user wants to: (1) explore or list available aelf skills, (2) install/bootstrap aelf skills into Curs

Teaches AI agents how to learn better by enforcing deep correction, transfer learning, and proactive pattern recognition. Use when an error occurs and needs deep analysis (not surface patch), before s

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code

Recover conversation context when a message arrives with unclear meaning. Use when a user's message lacks context (e.g. "I logged in" with no prior mention of logging in), when resuming after compacti

Explain cron expressions in plain English and calculate next run times. Use when asked to decode a crontab entry, understand a cron schedule, check when a cron job will next run, or translate between

Generate release notes from git commit history using Conventional Commits convention. Categorizes commits into Features, Bug Fixes, Performance, Refactoring, Docs, Tests, Build, CI, and more. Use when

register a new omnimemory saas account when needed, verify otp, create a first-party api key, optionally bind a third-party llm key, then install, configure, repair, and verify the @omni-pt/omnimemory

Design, structure, review, and generate B2B CRM or admin pages using an Ant Design-style system with page taxonomy, reusable layout rules, token guidance, component mapping, and AI-generation constrai

Use when OpenClaw needs to access AICFO through one bearer API key. Covers agent-session introspection, company selection, app-level MCP usage, connector actions, Company-DB entity/file reads, and the

When the user wants to run paid ads within directories or marketplaces. Also use when the user mentions "Taaft ads," "Shopify App Store ads," "G2 sponsored," "Capterra ads," "directory ads," "marketpl

Use this skill when a software architect, tech lead, or staff engineer needs to capture an in-flight architectural decision as a structured ADR. Enumerates alternatives with honest trade-offs and prod

Manage Hong Kong IPO user preferences and watchlists, including risk profile, default output, budget, financing preference, and tracked symbols. Use when the user wants personalized HK IPO settings or

BTC mining farm management via natural language. Activate when user mentions mining farm, miners, hashrate, BTC mining, miner reboot, mining revenue, Nonce mining, 矿场, 矿机, 算力, BTC挖矿, 矿机重启, 挖矿收益, 矿场管理.

Generate WeryAI images from text prompts or reference images through the WeryAI image APIs. Use when the user needs text-to-image, image-to-image, async image task submission with bounded polling to f

Stage 2 of FDE Delivery Loop. Turn a validated customer problem-discovery package into a POC engagement charter that defines the business outcome to test, proof criteria, scope, mutual commitments, ti

Diagnose conversion bottlenecks in product pages and checkout flows, then prescribe specific, data-driven fixes prioritized by expected revenue impact. Use when add-to-cart rates lag benchmarks, check

Turn Weixin/Wechat replies into readable image cards by rendering HTML into long PNG screenshots. Use when a Weixin direct-chat reply would exceed 150 Chinese characters, when the user asks for a card

Multi-agent auto-evolution system — orchestrate review-execute-audit loops with 4 roles (Coordinator, Reviewer, Executor, Auditor). A single coordinator agent drives the loop by spawning sub-agents fo

Local skill for capturing learnings, errors, corrections, and patterns to enable continuous agent improvement. Processes events locally in your OpenClaw agent without external API calls. Returns struc

Execute booking/search flows via browser automation with verification artifacts. Use for reservation forms, availability checks, and capture of proof (screenshots/confirmation IDs).

Use when users need to query daily currency exchange rates between two currencies.

Analyze industry competitive dynamics using Porter's Five Forces framework. Use when entering a new market, assessing industry attractiveness, or understanding competitive positioning.

Generate test summary reports, quality metrics, and test execution analysis. Aggregate test results into structured reports with pass/fail rates, coverage, trends, and recommendations. Use when: (1) s

Resilient multi-layer web scraper with automatic failover. Use when scraping web content that may be JS-rendered, behind bot protection, or on sites that block standard HTTP requests. Supports three-t

A comprehensive Git command assistant and workflow guide. Trigger whenever the user asks how to perform a specific Git operation, wants to know what a Git command does, needs help fixing a Git mistake

Use when user requests deep analysis, thorough thinking, or detailed breakdown of a problem. Triggered by phrases like: 帮我深入思考, 请仔细分析, 帮我详细拆解, 请梳理一下思路, 仔细考虑, 深入理解, 详细分析, or similar expressions indicat

Generates ICS calendar files with structured CRM data for B2B sales follow-ups. Creates importable .ics reminders with customer details, deal status, priority, and next steps — works with Apple Calend

Hreflang and international SEO audit, validation, and generation. Detects common mistakes, validates language/region codes, and generates correct hreflang implementations. Use when user says "hreflang

Stage 1 of FDE Delivery Loop. Turn customer interviews, frontline observations, tickets, meeting notes, and business data into an evidence-backed customer problem-discovery package. Use to uncover cus

Turn a real win into a set of designed, on-brand image assets for social media, email and a profile, in every size those channels need, built around a verified screenshot as proof. Use whenever someon

Writes publication-ready longform blog posts with strong structure, accurate definitions, and balanced critique. Use when user asks to draft an article/newsletter/essay, or wants a deep, polished blog

Wrap sending a Telegram message to a fixed topic into one script call. Use when user wants to quickly send notifications/messages to a specific Telegram topic by running a script.

Build, check, and submit R packages to CRAN or Bioconductor. Use when creating a new R package from scratch, fixing R CMD check errors/warnings, preparing for CRAN or Bioconductor submission, setting

Monitor service health, heartbeat freshness, stuck workflows, and trigger recovery or degraded mode. Use on: high-frequency schedule, after system startup, when a workflow stalls, when heartbeat fresh

Wan 2.5 video generation on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `wan2.5-text-to-video`, `wan2.5-image-to-video`, text-to-video, image-to-video, 5s or 10s clips, size

Generate speech on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `elevenlabs-tts-turbo-2-5`, text-to-speech, voice selection, speech speed, stability, similarity boost, style,

Delegate various coding tasks to Claude Code. Use this skill when you need assistance with code generation, bug fixing, feature implementation, code review, refactoring, or file exploration. It stream

This skill should be used when the user asks about HoneyBook client-portal data. Triggers on phrases like "check HoneyBook", "sign contract", "pay invoice", "HoneyBook vendors", "unsigned contracts",

Intent detection protocol for Claude — identifies the real goal behind requests, surfaces hidden assumptions, and knows when to ask vs. when to proceed. Eliminates wasted work from misunderstood requi

Golang concurrency patterns. Use when writing or reviewing concurrent Go code involving goroutines, channels, select, locks, sync primitives, errgroup, singleflight, worker pools, or fan-out/fan-in pi

Use whenever a person says they want to be more creative, feel stuck, want to make something small today, need fresh angles on a piece, or want a repeatable creative practice. Runs a short loop (one m

Create presentations (PPT) using PopAI API. Use when asked to create slides, presentations, decks, or PPT content. Has built-in research capabilities — just pass a topic. Supports uploading reference

Extract the actual core loop from a game, feature set, or pitch based on repeated player actions, feedback, rewards, and renewed motivation. Use when a team can list mechanics but cannot clearly artic

Adds a mischievous virtual cat to the conversation that can interrupt, derail, or fully block the assistant until soothed. Use when: (1) The user wants a cat companion or playful chaos, (2) The user m

Use when a user is trying to discover an installable or reusable skill or workflow, especially when they ask for a skill for a task, want to compare nearby skill categories, or need help narrowing dis

Generate vertical home makeover shorts (WeryAI): rental cream aesthetic, balcony café corner, themed kids’ rooms, strong before/after. Use when you need room makeover reels, soft-furnishing glow-up cl

用于排查“定时任务没执行”这类问题，并区分到底是未触发、已触发但执行失败，还是运行环境/授权失效导致的假象。遇到 cron 异常、任务未跑、自动任务失灵、网关重启后要验证恢复、怀疑是模型导致任务失败、需要查看日志作证、需要给出证据口径、要确认 `deactivated_workspace` / OAuth token 失效 / timeout 是否为根因时，都应触发本技能。也适用于“任务其实有 r

Generate a complete HTML tutorial that explains one or more problems with clear reasoning and embedded SVG or Canvas visuals. Use this skill whenever the user shares a question image, screenshot, work