Skill reviews

Advanced browser automation via Camoufox Firefox fork — handles anti-bot protection for authorized automation tasks

• 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

Search the Meta Ad Library by keyword or Facebook Page id and walk full cursor pagination through every ad, with creative, run dates, platforms and political spend. 3 endpoints, 1

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

Generate images, PDFs, and videos from templates with Orshot — via the REST API, SDKs (Node/Python/PHP/Ruby), the remote MCP server, or no-code tools (Zapier, Make, n8n, Airtable),

• 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

Convert one public website URL or an explicit batch of public URLs into a reusable skill zip backed by rendered HTML snapshots and a bounded JSONL retrieval index. Use to discover

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

Use when upgrading an Android app's Auth0 SDK (com.auth0.android:auth0) to the next major version. Detects the current version, checks prerequisites, and applies only the breaking

• References files that are not bundled: /auth0-android, /auth0-swift-major-migration, /auth0-react-native
• 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

Use when you need to add, remove, edit, list, or change the boot default of an nvfancontrol fan profile on a Jetson/Tegra (Orin, Thor) target. Triggers: edit fan profile, tune fan

• References files that are not bundled: ../../context/target-platform-contract.md, ../../context/bsp-customization-workflow.md, ../../context/bsp-customization-workflow.md
• 15 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 you need to add, remove, edit, list, or change the boot default of an nvpmodel power mode on a Jetson/Tegra (Orin, Thor) target. Triggers: edit power mode, tune frequency

• References files that are not bundled: ../../context/target-platform-contract.md, ../../context/bsp-customization-workflow.md, ../../context/bsp-customization-workflow.md
• 15 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

Run a security review workflow for Codex or ClawHub skills before activation or publication. Use when the user needs to inspect skill files, scripts, permissions, network behavior,

• 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 process needs to start

Publish ONE skill to ALL agent-skill channels from a single source of truth: the ClawHub skill registry, a ClawHub bundle-plugin package, and a Claude Code plugin marketplace (plai

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (15 tags): a typed call is more reliable
• Does not say what the result is

The Descript craft skill — edit talk content (podcasts, interviews, talking-head video) by editing the transcript instead of the timeline. Use when someone wants to edit in Descrip

• 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 test case covers injection arriving through data

Route Huoshan and Qifu knowledge requests through the default structured Feishu document INDEX and return relevant original Feishu links. Use when the user explicitly names huoshan

• References files that are not bundled: 飞书文档URL
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill ranks results itself: that belongs to the system behind the tool, not the model

Subtraction-first engineering for any coding task. Channels an engineer who ships by deleting: question whether the change needs to exist (YAGNI), reuse what the codebase already h

• 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

Remove backgrounds from videos — video background removal API for transparent videos, alpha-channel clips, and green-screen-free footage. Powered by Bria's video editing pipeline.

• The skill tells the model to perform an irreversible action with no human approval
• 15 mutating operations with no state check

Schedule MRP production batches in Odoo (BaconCo) — the fluid shop-floor scheduler. Periodically read open `mrp.production.batch` records, rank them into a run order by the shop ru

• References files that are not bundled: references/scheduling_algorithm.md, references/receipt_readiness.md, scripts/odoo_mcp.py
• 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

Route a multi-image content job through the best available generation backend, prepare a resumable prompt pack with readable-text fact boundaries, optionally operate an approved or

• References files that are not bundled: references/zip-batch.md, references/ui-recovery.md
• The skill tells the model to perform an irreversible action with no human approval
• 2 referenced file(s) missing: references/zip-batch.md, references/ui-recovery.md

Routes to the appropriate agent in the crypto-signals-plugin team. Trigger when the user asks about crypto trade signals, market analysis, price data, crypto news sentiment, Telegr

• References files that are not bundled: scripts/run-cycle.sh
• The skill tells the model to perform an irreversible action with no human approval
• 1 referenced file(s) missing: scripts/run-cycle.sh

Get a brand named by AI search engines. Use when someone asks why ChatGPT/Gemini/Perplexity recommend competitors instead of them, wants to check if AI mentions their brand, asks a

• 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

Run an autonomous email inbox with Drin — receive inbound email on a domain, read conversation threads, and reply in-thread. Use when building or operating an agent that must read

• 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

Plan and orchestrate a product launch or social media campaign end to end — the multi-week arc, channel by channel. Use when someone wants to plan a launch, product drop, campaign,

• The skill tells the model to perform an irreversible action with no human approval
• No test case covers injection arriving through data
• No condition that starts the skill

Estimate the fair opening or intraday value of Hong Kong-listed CSOP SK Hynix Daily (2x) Leveraged Product (07709.HK) from its latest NAV, KRX 000660 price, Nasdaq SKHY return, ADR

• 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

🇺🇸 Hardware + SaaS GTM Playbook — End-to-end go-to-market for consumer hardware products with software subscription models. Covers crowdfunding engineering (Kickstarter/Indiegogo

• 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
• Does not say what the result is

Prepare, sanitize, publish, and verify public GitHub issues, pull requests, review comments, release notes, bug reports, logs, screenshots, and test evidence. Use whenever an agent

• 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

Take existing HTML content (file, URL, or pasted HTML) and publish it directly to WeChat Official Account draft box. No file conversion, no web scraping — just HTML to WeChat compa

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

Creates a complete EC2 Image Builder pipeline that builds a custom AMI with pre-installed software, distributes it to target regions, executes the pipeline, and creates a launch te

• References files that are not bundled: references/ec2-image-builder-pipeline.md
• The skill tells the model to perform an irreversible action with no human approval
• 1 referenced file(s) missing: references/ec2-image-builder-pipeline.md

Deploy anything an agent builds to a live URL via the DataEcho platform at https://dataecho.ai — a single file, a static site, OR a server-side app (any stack) by including a Docke

• References files that are not bundled: scripts/publish.sh, scripts/drive.sh
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (6 tags): a typed call is more reliable