Skill reviews

Native agent-to-agent language for compact multi-agent messaging. A shared tongue agents speak directly, not a translation layer. 340+ atoms across 7 domains; 3x smaller than natur

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Run Fireworks-hosted open-weight model councils that compare responses and synthesize a final answer.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Generate images and videos with MuAPI's schema-driven asynchronous media API while protecting keys, polling, and output downloads.

• 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

Answers questions about a past agent run from its recording rather than from memory, and replays or forks that run. Use when asked why an earlier run did something, or to reproduce

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Research LinkedIn professional profiles and public business-contact data, including email/phone lookup, people search, and YouTube channel business-email discovery.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 3 mutating operations with no state check

Generate React code with Rayden UI components using correct props, tokens, and premium layout patterns

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Linear process with no failure handling

Two-layer performance skill combining disciplined THINK layer (surgical edits, simplicity) and terse SPEAK layer (caveman compression). Triggers on requests for brevity, token effi

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the process needs to start
• Linear process with no failure handling

Natural-language time tracking: parse what the user says they did into Activity/Minutes/Date rows in their own Notion database — asking instead of guessing when unsure.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Web scraping inteligente multi-estrategia. Extrai dados estruturados de paginas web (tabelas, listas, precos). Paginacao, monitoramento e export CSV/JSON.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Linear process with no failure handling
• 1 mutating operations with no state check

Manages shadcn/ui components and projects, providing context, documentation, and usage patterns for building modern design systems.

• 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 response is described with custom markup (6 tags): a typed call is more reliable

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program.

• 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
• No test case covers injection arriving through data

Build AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone numbers, create voice agents, set up webhooks, or check usage

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Linear process with no failure handling
• 7 mutating operations with no state check

Babysit a pull request through its bot review rounds: verify, fix, reply, resolve. Use for any babysit or watch-the-PR ask.

• References files that are not bundled: scripts/threads.sh
• 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

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or A

• 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
• 6 mutating operations with no state check

Provision headless backend services for AI agents through Cohesivity: hosting, databases, storage, LLMs, and third-party APIs over one HTTP API. Use when a trusted .cohesivity file

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

Relationship-aware daily gift engine with five-stage creative pipeline — editorial judgment, synthesis, concept generation, visual strategy, and rendering in H5, image, or video

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the process needs to start
• 5 mutating operations with no state check

Delegate well-specified implementation tasks to xAI's Grok Build CLI running headlessly while the orchestrating agent plans, writes task specs, reviews every diff, and owns the res

• 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
• Does not say what the process needs to start

Deterministic search across arXiv, PubMed/PMC, and US policy corpora with daily freshness cutoffs.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Review MDPR Markdown presentation workflows with semantic hints, visual checks, and deterministic renderer boundaries.

• 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
• Does not say what the result is

Design n8n AI agents, chains, classifiers, extractors, tool calling, memory, RAG, structured output, and human-review flows.

• 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
• Does not say what the result is

Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 17 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Build and maintain Rayden UI components and screens in Figma via Figma MCP with full design token enforcement

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Linear process with no failure handling

Rclone command-line cloud storage manager reference and usage guide. Use this skill whenever the user mentions rclone, or any task involving terminal-based cloud file operations su

• References files that are not bundled: scripts/install.sh, references/usage.md, references/flags.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 13 referenced file(s) missing: scripts/install.sh, references/usage.md, references/flags.md

Generate AI images, videos, and music/audio from agents using the RunAPI CLI.

• 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
• Does not say what the result is