Skill reviews

Linear (linear.app). Use this skill for ANY Linear request — reading, creating, updating, and deleting data. Whenever a task involves Linear, use this skill instead of calling the

• 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

Recall.ai (recall.ai). Use this skill for ANY Recall.ai request — reading, creating, updating, and deleting data. Whenever a task involves Recall.ai, use this skill instead of call

• 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

Optimize a website to be discovered, cited, and recommended by AI search engines — ChatGPT, Claude, Perplexity, Google AI Overviews, and Gemini. Use this for Generative Engine Opti

• 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
• Does not say what the result is

Apply proven mental models to boost personal and team productivity — focus techniques, decision frameworks, and task management principles. Use when: improving personal productivit

• 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

When the user needs to build file upload functionality for a web application. Use when the user mentions "file upload," "image upload," "upload endpoint," "multipart upload," "pres

• 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

Produce video with AI from the terminal via the VidVibe MCP server — price and launch flows, generate videos and images, create and lip-sync characters, edit a flow canvas, manage

• 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

Bundle TypeScript libraries with tsup — zero-config, powered by esbuild. Use when someone asks to "bundle a TypeScript library", "build npm package", "tsup", "publish TypeScript to

• 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

Codex+OMX orchestration: keep this session as decision maker/integrator; for non-trivial work prefer bounded native subagents with runtime-resolved OMX roles for search, reading, r

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

Application logging quality auditor. Scans source files for logging anti-patterns — debug/print statements left in production paths, log level mismatches (errors logged as info, wa

• 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

OpenCode+OMO orchestration: keep this session as decision maker/integrator; for non-trivial work prefer bounded available agents for search, reading, research, testing, review, and

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

Use when packaging a Next.js static export as a Windows Electron app, notably offline/intranet boxes with no WebView2. Triggers on Electron 桌面版 / 打包成 exe.

• 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

Complete an auth.md USER-CLAIMED signup (OTP flow) against any service that publishes the auth.md protocol. Consent-preserving — the human confirms the OTP; the agent never auto-co

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

Turn agent explanations into local animated flow diagrams, described in YAML and played back one hop at a time.

• References files that are not bundled: ../../examples/sub-flows.yaml, ../../examples/parallel.yaml, ../../examples/self-loops.yaml
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 15 top-level sections: this looks like several domains in one skill

Generate, validate, render, and export Mermaid diagrams (.mmd) — flowchart, sequence, class, ER, state, gantt, git graph, mindmap, C4, pie, journey. Three backends — beautiful-merm

• 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 users ask for World Cup or 世界杯 AI match predictions, WC assistant probabilities, World Cup news insights, master analysis, recomputing football match win rates with custom

• References files that are not bundled: references/prediction.md
• 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

Find free and cheap things to do in a US city — daily event listings with times, prices and venues, plus searchable deals, festivals, kids activities and local guides from the On t

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

Use when an agent needs to create an evidence-bound supplier discovery report for a product or sourcing brief, especially for global buyers, cross-border ecommerce, private label,

• 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

Test for WCAG 2.2 AA compliance with axe-core + Playwright, keyboard navigation audits, screen reader testing, ARIA pattern validation, and legal compliance mapping (ADA, EAA, Sect

• 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

Migrate a test suite from one framework to another, incrementally and without losing coverage. Covers Selenium→Playwright, Cypress→Playwright, Jest→Vitest, Mocha→Vitest, and Protra

• 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
• The response is described with custom markup (5 tags): a typed call is more reliable

Build a single sprint or release test plan. Covers feature decomposition into testable scenarios, requirements-to-test coverage mapping, effort estimation by test type, prioritizat

• 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 process needs to start

Claude Code+OMC orchestration: keep this session as decision maker/integrator; for non-trivial work prefer bounded available agents for search, reading, research, testing, review,

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

Use when an agent needs to surface skill/capability candidates that first-pass registry, package, or search queries would likely miss. Covers skills, MCPs, CLIs, plugins, registrie

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

Runtime-neutral orchestration: keep this session as decision maker/integrator; for non-trivial work prefer bounded available agents for search, reading, research, testing, review,

• 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

Point at any topic to build a compounding, domain-general expertise knowledge base: a high-fidelity source corpus, track-record-weighted experts, reconciled falsifiable stances, fa

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

Build or review a safety-gated Google Colab workflow that installs Hermes Agent and uses it for read-only Unitree Robotics repository analysis, simulation runbooks, log triage, and

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