Loading...
Loading...
Found 4,837 Skills
Guide for creating properly structured YAML configuration files for MassGen. This skill should be used when agents need to create new configs for examples, case studies, testing, or demonstrating features.
Invoke MassGen's multi-agent system. Use when the user wants multiple AI agents on a task: writing, code, review, planning, specs, research, design, or any task where parallel iteration beats working alone.
Bootstrap new Swift Package Manager repositories with consistent defaults, generated AGENTS guidance, validation, and customizable bootstrap settings. Use when creating a new Swift package, choosing platform or version presets, scaffolding its initial structure, or maintaining this skill's bootstrap defaults.
Use when setting up or configuring Laravel Boost for AI-assisted development — package installation, MCP server configuration, guideline customization, skill authoring, documentation API integration. Trigger conditions: install Laravel Boost, configure MCP for IDE, create custom AI guidelines, write project-specific skills, verify MCP tool connectivity, update Boost after dependency changes, extend Boost for custom agents.
Use when generating or reasoning over text with Alibaba Cloud Model Studio Qwen flagship text models (`qwen3-max`, `qwen3.5-plus`, `qwen3.5-flash`, snapshots, and compatible open-source variants). Use when building chat, agent, tool-calling, or long-context text generation workflows on Model Studio.
Fetches LangSmith traces for debugging agent behavior. Use when troubleshooting agent issues, reviewing conversation history, or investigating tool calls.
Full project soul alignment in one command. Scans every frontend file in the project, builds a prioritized plan, then systematically aligns all components and styles to .marrow.md. Smart enough to detect if .marrow.md was updated since the last run and only reprocess files affected by what changed — not a full rewrite every time. Use this skill when the user wants to align the entire project to the design soul at once, just installed marrow mid-project and wants to catch everything up, or updated .marrow.md via /marrow-update and wants to propagate only the changed rules across the project. Triggers on: /marrow-redesign, or prompts like "align the whole project", "redesign everything to match marrow", "apply marrow to all files", "full soul alignment", "catch everything up to marrow", "propagate the marrow update", "marrow everything". Requires .marrow.md to exist. If not found, instructs user to run /marrow first. This is a multi-step agentic command — it will take multiple turns to complete large projects. It creates a .marrow-state.json file to track progress and enable smart diff on future runs.
Checkpoint - Pre-publish review with multi-layer deep analysis. Triggers: Preparing to publish an npm package, requiring pre-release review, or checking code change quality. Review Layers: - Per-Change: In-depth analysis of each change group (up to 10 Agents) - Holistic: Parallel review by 5 roles (Architecture/Development/Testing/Security/Documentation) - Synthesis: 1 Agent summarizes review results Commands: - /把关 - Start pre-publish review - /把关 check - Check unpublished changes - /把关 version - Recommend version upgrade - /把关 report - Generate review report - /review - English command Capabilities: Unpublished change detection, in-depth per-change analysis, multi-role review, version recommendation, release risk assessment.
Prepare advisors for client review meetings by assembling context packages, performance summaries, drift analysis, talking points, and meeting agendas. Use when the user asks about preparing for a client review, building a pre-meeting checklist, generating talking points for an upcoming meeting, identifying allocation drift before a review, automating review prep workflows, or assembling a meeting package with exhibits. Also trigger when users mention 'client meeting prep', 'review preparation', 'what should I discuss with my client', 'proactive recommendations', 'life event triggered review', 'meeting agenda', or 'compliance pre-check before review'.
Audit a codebase for handcrafted code that duplicates functionality already available in the project's dependencies. Reads package.json, launches parallel exploration agents, verifies replacement feasibility, and produces a structured refactor plan. Audit only -- does not execute changes.
Use when changing CFO Stack ledger conventions, process docs, Beancount metadata rules, or canonical ledger/file layout guidance that should stay out of AGENTS.md.
HackerOne bug bounty automation - parses scope CSVs, deploys parallel pentesting agents for each asset, validates PoCs, and generates platform-ready submission reports. Use when testing HackerOne programs or preparing professional vulnerability submissions.