R
ruthless-clarity
Cameron Hartis · Guardrail
Force every AI agent task from ambiguity to verified action
“define victory”
$29
Details
AI & Agents
AR
AI Requirement Lock
mark_hemenway · Guardrail
Stops AI agents from forgetting, changing, or violating your requirements during long, multi-step work.
“keep track of all my requirements”
Free
Details
Pre-Task Intelligence Protocol — activates ALL relevant agents in the ecosystem BEFORE executing any task requested by...
Free
Details
Guide for contributing to the stata-skill project.
Free
Details
HA
Clone the later half of the current conversation, discarding earlier context to reduce token usage while preserving recent work.
Free
Details
Automate Synthflow AI tasks via Rube MCP (Composio).
Calls rube
Free
Details
Coordinates multi-agent workflows across planning, implementation, and verification stages for complex software delivery.
Free
Details
Automatically discover collaboration and teamwork skills when working with collaboration.
Free
Details
Automate Mistral AI tasks via Rube MCP (Composio): completions, embeddings, fine-tuning, and model management.
Calls rube
Free
Details
Orchestrates complex development projects by decomposing tasks into structured prompts for multi-agent teams.
Free
Details
Regenerate OpenCode context file (.opencode/context.md) with AIWG framework content
Free
Details
Use when a Mexus-launched agent should summarize the current Agent Team Mission kanban in the terminal.
Free
Details
Use when creating, improving, or troubleshooting Claude Code subagents.
Free
Details
Clone the current conversation so the user can branch off and try a different approach.
Free
Details
Multi-agent coordination across plan/implement/test/review; fan-out for 3+ workstreams.
Free
Details
Defining AI character, voice, and personality traits.
Free
Details
Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.
Free
Details
Turn a one-line objective into a step-by-step construction plan any coding agent can execute cold.
Free
Details
CI Test Codex Skill
Free
Details
Enforces high-agency behavior and systematic debugging by applying elite Japanese corporate accountability standards to Claude.
Free
Details
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command…
Free
Details
AI & Agents agent skills on mcprush, filed under one heading so the shelf can be read in one pass. The kinds are workflow, expertise, output format, voice & style and guardrail, and the one a skill belongs to, where its author declared it, is the fastest way to guess what it will do to your prompt.
What to look at before installing one is what it costs in context and what it takes away: a guardrail that refuses an action and a voice that rewrites a sentence are both skills, and only one of them will stop the agent doing something. Every skill here says what it costs in context, which kind it is where its author declared one, what it needs beside it to work and the licence it is published under, next to the publisher it came from and whether that publisher has been verified. The filters on the left narrow it further and the sort at the top decides what comes first.
A skill is not connected to anything: there is no endpoint to authorise and nothing routed through the gateway. Installing one drops a folder of instructions into the client’s own skill folder, and uninstalling it is deleting that folder. The exact line for each client is on the skill’s own page, because it differs by client rather than by skill.