Skill reviews

Work with an Azure DevOps org via the az CLI — query sprint/assigned work items with WIQL, read a work item's description AND download+view its embedded screenshots, publish branch

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (8 tags): a typed call is more reliable

Create a new Claude Code skill — scaffolds a properly-structured `SKILL.md` (with YAML frontmatter, trigger-rich description, workflow, examples, anti-patterns), drops it in the ri

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

Publish your AI Agent-generated digital assets to the public Gallery of Craftsman Agent with live, shareable URLs. Similar to Instagram, but built for AI Agents and their creations

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Etsy Style Marketplace Build for AI Agents. Publish your AI Agent-generated digital assets to the public product Marketplace of Craftsman Agent with live, shareable URLs. Similar t

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Condense a long agent session transcript into a compact handoff memo: decisions, tasks, risks, facts & links. Credential values are auto-redacted before output (best-effort - revie

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what

• References files that are not bundled: wiki-kb/wiki/topic/article.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval

Publish a static site (a folder of HTML/CSS/JS/images/fonts) to Cloudflare and get back a live, shareable URL in seconds. Use when you have a finished static page or site and need

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (3 tags): a typed call is more reliable

Manage AI agent context window consumption, prevent compaction death spirals, and enforce sub-agent spawn policies. Use when: (1) context is filling up and work quality may degrade

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Meegle OpenAPI for creating, reading, and updating work items.

• 16 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Meegle OpenAPI for work item relationship settings: list, create, update, delete.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Meegle OpenAPI for workflow/process template settings: list, get detail, create, update, delete.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Publish content directly to WordPress sites via REST API with full Gutenberg block support. Create and publish posts/pages, auto-load and select categories from website, generate S

• References files that are not bundled: url
• 12 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

This skill is for running fdv.lol CLI mode (cli.mjs) with Agent Gary Full AI Control enabled, so the AI can fully drive Auto Trader decisions.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Create and publish an Instagram carousel post from a tabiji.ai itinerary, with Topaz Labs AI image enhancement. Same as itinerary-carousel-post but adds a Topaz upscale/enhance ste

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Create, manage, and deploy Voice.ai conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.

• 17 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Outcome-driven scientific publishing for AI agents. Publish research papers, hypotheses, and experiments with validated artifacts, structured claims, milestone tracking, and indepe

• 10 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Securely expose an OpenClaw Gateway WebUI on a VPS via Cloudflare Zero Trust Access + Cloudflare Tunnel (cloudflared), including DNS cutover for custom hostnames and optional clean

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Download videos from YouTube, Instagram, TikTok, Twitter/X, and 1000+ other sites using yt-dlp. Supports quality selection and automatic cleanup. Use when a user provides a video l

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Implement 10 advanced AI agent node types for any DSL/runtime system — plan compiler, code interpreter, critique loops, intelligent routing, multi-agent ensemble, persistent memory

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 18 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Create and sell digital products on Clawver. Upload files, set pricing, publish listings, track downloads. Use when selling digital goods like art packs, ebooks, templates, softwar

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Backup OpenClaw config files, Skills, Workspace files, and Memory records for migration or disaster recovery. 备份 OpenClaw 配置文件、技能、工作区文件和记忆记录，用于迁移或灾难恢复。Triggers: 备份, backup, 备份配置, b

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Eternal Haven Chronicles lore + mythic persona pack. Use when the agent needs deep narrative context, character arcs, and metaphysical structure from the 4 Eternal Haven books to s

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Create and publish an Instagram carousel post from a tabiji.ai itinerary. Given an itinerary URL, finds Instagram-worthy photos for the destination + top attractions, applies text

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Analyze ChatGPT conversation exports to discover cognitive archetypes and optimize AI-human communication patterns. Enables personalized agent interactions based on detected user p

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

Demo of x402 payment protocol by fetching a protected image. Triggers: '演示x402-payment' or 'demo x402-payment'

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill