Skill reviews

Generate audio replies using TTS. Trigger with "read it to me [URL]" to fetch and read content aloud, or "talk to me [topic]" to generate a spoken response. Also responds to "speak

• 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

Orchestrate multiple Claude Code workers via iTerm2 using the claude-team MCP server. Spawn workers with git worktrees, assign beads issues, monitor progress, and coordinate parall

• References files that are not bundled: assets/com.claude-team.plist.template
• 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

Personal habit coach that tracks daily habits, streaks, and provides AI-powered coaching. Say things like "track a new habit", "log my habits", "show my streaks", or "coach me".

• 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

Use when studying or normalizing Chinese lesson transcript/subtitle inputs with bundled public lesson data, learner docs, local export bundles, and pilot-first prepublish leak gate

• References files that are not bundled: references/course-data, references/system-prompts, references/course-data/lessons-bundle.json
• The skill tells the model to perform an irreversible action with no human approval
• 5 referenced file(s) missing: references/course-data, references/system-prompts, references/course-data/lessons-bundle.json

Publish AI-generated content (HTML pages, Markdown reports, multi-file sites, dashboards, visualizations) to a shareable URL using Artidrop. Use when: user asks to publish, share,

• 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

Control Nest thermostat, doorbell, and cameras via the Google Smart Device Management (SDM) API.

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (7 tags): a typed call is more reliable
• Does not say what the result is

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

Forces the AI to use a "temporary file + environment variable isolation" workflow for script execution, completely resolving terminal freezes and escaping errors in Windows PowerSh

• 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

Query your Yahoo Fantasy Baseball league: view roster, standings, matchups, free agents, draft results, transactions, and injuries. Daily roster optimization detects inactive playe

• 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
• 5 mutating operations with no state check

projectnanda.org chapter skill — register an OpenClaw agent with a NANDA chapter, submit signed intents, respond to calls, render chapter dashboards, and subscribe to the chapter e

• 11 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
• The response is described with custom markup (33 tags): a typed call is more reliable

Reasoning hygiene protocol for OpenClaw agents — keep context sharp by collapsing exploration into decisions, enforcing file budgets, and pruning ghost context. Use when setting up

• 13 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

Generate short-lived, mobile-friendly ngrok preview links for local artifacts and share them in Telegram. Use when OpenClaw produces images/charts/generated files that the user nee

• 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

Gives the agent a dedicated email address for sending and receiving email. Use when the agent needs to send email to external services, receive replies, sign up for services, handl

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 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

Use when writing or editing prose humans will read — documentation, commit messages, error messages, READMEs, reports, UI text, explanations. Triggers on clarity concerns, wordines

• 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

Publish HTML or Markdown to a public URL instantly. Zero config, auto-registers on first use. Use when the user wants to share, preview, host, or deploy generated HTML, Markdown, J

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the process needs to start
• 18 mutating operations with no state check

Bitcoin Lightning payment CLI for agents. Lowest LSP fees. Self-custody wallet with LNURL, typed exit codes, JSON envelope output, encrypted messaging, and daemon mode.

• 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
• The skill tells the model to perform an irreversible action with no human approval

Validate OpenClaw skills during authoring. Use when creating, revising, or preparing a skill for release and you need to scaffold `evals/` files, check readiness for a first eval p

• 13 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
• 3 test cases, all positive: not one "should refuse" or "should ask first"

SoundCloud for AI bots. Generate tracks and podcasts, share on Moltbook, and earn from tips + royalties.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 23 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 ClawhHub-ready OpenClaw skills with correct structure, scanner criteria, security rules & publish checklist. No credentials or binaries required.

• 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 (4 tags): a typed call is more reliable

Autonomous ClawArena client that stores scoped credentials and delivery state, runs a background watcher on a selected existing OpenClaw agent, and reports heartbeat/update telemet

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 13 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

Headless Ghost publishing. Write, audit, and automate your entire Ghost operation from your AI workflow — 17 workflows covering article publishing, batch imports, site health audit

• 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

Remove backgrounds from images — background removal API for transparent PNGs, cutouts, and masks. Segment foreground from background. Powered by Bria RMBG 2.0. ALWAYS use this skil

• The skill tells the model to perform an irreversible action with no human approval
• Linear process with no failure handling
• 18 mutating operations with no state check

Set up a non-custodial dollar-cost averaging strategy on Uniswap. Use when user wants to create recurring swaps, auto-buy ETH/BTC/SOL with USDC on a schedule, or build a DCA bot. C

• The skill tells the model to perform an irreversible action with no human approval
• Says nothing while it works

API gateway for calling third-party APIs with managed auth. Use this skill when users want to interact with external services like Slack, HubSpot, Salesforce, Google Workspace, Str

• 13 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

Meta-skill for zero-friction deployment of local web projects to production URLs by orchestrating github-api, vercel/netlify, domain-dns-ops, and api-gateway. Use when users want t

• 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
• No condition that starts the skill