Skill reviews

Pre-commit SQL code review for uncommitted database changes. Detects antipatterns that cause real production incidents — broken TRY/CATCH error handling, swallowed errors, retry pa

• References files that are not bundled: ../code-review/SKILL.md
• 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

Create AI images, videos, music, and voice, look up public social data, edit visual results, and keep generated assets easy to find and manage. Beatra Universal turns text into ima

• 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 ranks results itself: that belongs to the system behind the tool, not the model

When provisioning, setting a limit, or committing an estimate under uncertainty, size a buffer to residual error and the cost of breach—not to the optimistic edge.

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

Generate AI video, images, music, and voice-over in one connected creative flow, edit visual results, and keep everything you make easy to find. This all-in-one AI media generator

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

Schedule, publish, and manage social media content through the ViralNote API. Use when the user wants to post, schedule, query, or manage content across X, Facebook, Instagram, Lin

• 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

Deploy a self-hosted funnel builder, take a funnel from empty install to published - landing page, checkout, one-click upsell, thank-you - and drive it from an agent over MCP. Cove

• 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

Use when footage needs color correction, white-balance or exposure repair, Log-to-Rec.709 conversion, named creative looks, skin-tone review, or a portable .cube LUT for a cut-as-c

• 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

Search Walmart and read product detail, reviews, category listings, buy-box offers, seller storefronts and a seller's catalog as structured JSON. 7 endpoints; cost depends on the b

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

Create and run product-launch waitlists on waitlister.me — create a waitlist and publish a hosted landing page (dark/light, optional AI-generated design) in one prompt, collect sig

• 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

Fluxguard (fluxguard.com). Use this skill for ANY Fluxguard request — reading, creating, updating, and deleting data. Whenever a task involves Fluxguard, use this skill instead of

• 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

A minimal but complete demo skill that greets the user and prints the current UTC timestamp. Useful for verifying the ClawHub publish/install pipeline end to end.

• 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

Test and certify AI agent skills: 7 automated checks, grade A–D, certificate. Use when asked to check, test, review, or certify a skill before publishing. Use ONLY with the user's

• 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

How to swap the VLM in the VSS Alerts Blueprint — covers RTVI-VLM microservice deployment methods, all three VLM consumers (rtvi-vlm, vlm-as-verifier, vss-agent), and health checks

• References files that are not bundled: references/vss-source-layout.md, references/port-and-url-wiring.md, references/health-checks.md
• 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

Turn any GitHub repo into an async agent service store: publish services, accept paid tasks via Issues, and deliver results with signed proof. Works with OpenClaw, Claude Code, Cod

• 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

End-to-end pull-request flow with a review gate — reviews the branch BEFORE publishing (code-review skill's branch scope if installed; blockers must be fixed or explicitly waived),

• References files that are not bundled: ../github/SKILL.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

Create, update, and publish websites with Revdoku buckets — including interactive app sites backed by a per-bucket server database (visitor submissions, voting/feedback dashboards,

• References files that are not bundled: assets/app.css, templates/app-safe-actions.json, templates/app-frontend-example/
• 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

• 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

Search Capterra for B2B software, read a full product profile with the complete pricing table and 25 reviews included, and page deeper reviews with per-criterion scores. 3 endpoint

• 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

Order prepaid cards, gift cards, and send money to USD/EUR/GBP debit cards or US bank accounts using USDC on Base or Solana via the x402 protocol. Use when a user or agent needs to

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 19 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 on-camera delivery craft — helping a real human film themselves talking to a lens and look like themselves doing it. Use when someone wants a "talking head video" or "piece to

• 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

The live + realtime-format skill -- plan, promote, run, and repurpose livestreams and realtime moments (IG Live, TikTok LIVE, YouTube Live, LinkedIn Live, X, live shopping). Use wh

• 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

The TikTok Photo Mode format-execution skill. Use when someone wants a "TikTok photo carousel," "photo mode," "TikTok slideshow," "swipeable TikTok post," or to publish a multi-ima

• 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

The Instagram Reels publish-mechanics skill -- distinct from reels-script (the script), instagram-seo (the keyword caption), and platform-specs-and-validation (cross-platform valid

• 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

Upload and use your own LoRA or checkpoint on Runware. Use when the user says "import my LoRA", "upload my checkpoint", "host my own model", "I trained a model elsewhere, use it he

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Says nothing while it works

Claude Code / Codex / Factory Droid plugin and Cursor / Copilot / Gemini CLI Agent Skill. Install with npx skills add Kayforkind/reimagine-it, /plugin marketplace add Kayforkind/re

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