Skill reviews

Tell dad jokes on demand by fetching a random joke from the shuttie/dadjokes HuggingFace dataset. Trigger whenever the user asks for a dad joke, wants to hear a joke, asks you to t

• Prose only: no discrete steps
• Does not say what the result is

A philosophy library for AI agents. Browse books, read chunk by chunk, share reflections, and engage with other AI minds.

• Does not say what the result is
• No condition that starts the skill

WATI (WhatsApp Team Inbox) API integration with managed authentication. Send WhatsApp messages, manage contacts, and handle templates. Use this skill when users want to send WhatsA

• References files that are not bundled: references/<source>/triggers.md, references/{source}/triggers.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill

Parse and validate JSON data from construction APIs, IoT sensors, and BIM exports. Transform nested JSON to flat DataFrames.

• 1 steps
• Does not say what the result is

• 11 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Zero-vector AI memory engine with self-learning. LOCOMO 76.2% (4th place). 15 original algorithms, open source (MIT).

• The skill ranks results itself: that belongs to the system behind the tool, not the model
• Does not say what the result is
• No condition that starts the skill

Executes approved shell commands, manages backups, and safely retrieves secrets from Bitwarden.

• Does not say what the result is
• No condition that starts the skill

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (3 tags): a typed call is more reliable
• Does not say what the result is

Syncs daily health and fitness data from Oura Ring into markdown files. Provides sleep, readiness, activity, heart rate, stress, SpO2, and workout data.

• Prose only: no discrete steps
• Does not say what the result is

AI-powered insurance anti-fraud analysis skill — detects and prevents insurance fraud across all major insurance types. Covers claim fraud identification (10-feature engine), under

• References files that are not bundled: references/anti_fraud_guide.md, references/underwriting_risk_assessment.md, references/claim_investigation_sop.md
• 5 referenced file(s) missing: references/anti_fraud_guide.md, references/underwriting_risk_assessment.md, references/claim_investigation_sop.md
• Does not say what the result is

Context engineering platform for AI agents. Upload documents, search with semantic + structured queries, and inject relevant context into LLM prompts. Supports RAG, Text2SQL, hybri

• 11 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Feishu IM messaging operations: send messages, images, files to users and groups via Bot API. Activate when user mentions: 飞书发图、发送图片、飞书消息、im:resource、image_key、飞书附件、飞书机器人发消息。

• Does not say what the result is
• No condition that starts the skill

Full-stack engineering skill with 24 modules covering architecture, API, performance, testing, DevOps, security, and modern TypeScript stack.

• References files that are not bundled: references/<module>/SKILL.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 1 referenced file(s) missing: references/<module>/SKILL.md

2-agent collaborative software development workflow for OpenClaw

• 13 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Create, update, and manage Glance dashboard widgets. Use when user wants to: add something to their dashboard, create a widget, track data visually, show metrics/stats, display API

• References files that are not bundled: references/components.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 20 top-level sections: this looks like several domains in one skill

Open security scanner for agentic infrastructure — agents, MCP, packages, blast radius, runtime, and trust across MCP discovery, CVEs, SBOMs, CIS benchmarks (AWS, Azure, GCP, Snowf

• References files that are not bundled: discover/SKILL.md, scan/SKILL.md, scan-infra/SKILL.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 8 referenced file(s) missing: discover/SKILL.md, scan/SKILL.md, scan-infra/SKILL.md

USE FOR RAG/LLM grounding. Returns pre-extracted web content (text, tables, code) optimized for LLMs. GET + POST. Adjust max_tokens/count based on complexity. Supports Goggles, loc

• References files that are not bundled: ../../README.md
• 16 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: ../../README.md

起名取名助手。宝宝起名、英文名、笔名、品牌名。含寓意解析。. Use when you need name generator capabilities. Triggers on: name generator.

• 1 steps
• Does not say what the result is

Upbit automated trading (aggressive breakout) with cron-friendly run-once commands, TopVolume monitoring, and percent-based budget splitting.

• References files that are not bundled: scripts/tests/*
• 1 referenced file(s) missing: scripts/tests/*
• Does not say what the result is

Prompt-injection and data-exfiltration screening for untrusted text. Use before summarizing web/email/social content, before replying, and especially before writing anything to mem

• References files that are not bundled: scripts/openclaw-safe-memory-append.js
• 1 referenced file(s) missing: scripts/openclaw-safe-memory-append.js
• Does not say what the result is

Private payments for AI agents - no on-chain link between sender and recipient

• Prose only: no discrete steps
• Does not say what the result is

A1/A2/B1(约对应JLPT的N5/N4/N3)日语会话测试音频批改；基于faster-whisper实现ASR转写，系统自动转写学生回答并做初步内容匹配与三维诊断（内容完整性/准确性/流利度）；不确定内容不扣分，只输出可疑候选供教师复核。支持单人/批量批改、纠错反馈、成绩归档；AI预批改辅助，教师人工复核，满分10分。

• References files that are not bundled: scripts/download_audio_submissions.py
• 16 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: scripts/download_audio_submissions.py

Autonomous web research agent that performs multi-step searches, follows links, extracts data, and synthesizes findings into structured reports. Use when asked to research a topic,

• References files that are not bundled: url
• 1 referenced file(s) missing: url
• No condition that starts the skill

Book web-developer services through Lokuli MCP. Use when user needs to find and book web-developer. Triggers on requests like "book a web-developer", "find web-developer near me",

• Prose only: no discrete steps
• Does not say what the result is

Control Autodesk desktop apps - 3ds Max and friends - from the shell via Flue, without an MCP server.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill