Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Recommends webhook subscriptions for PlanetScale alerts, anomalies, schema recommendations, and deploy requests. Covers safe automation patterns and agent workflows.
Breaks implementation work into comprehensive phases, sprints, and atomic tasks. Supports general planning requests and explicit /planner or /plan commands.
复杂功能与重构的规划专家，用于需求分析、架构梳理、任务拆解与风险识别；当用户请求实现功能、架构调整或复杂重构时使用。
Breaks specifications and large tasks into manageable work items. Supports scope estimation and identifying opportunities for parallel work.
Analyzes a single .NET project to identify repositories, DAOs, and service layers that access the database. Produces a structured integration testing plan for migration validation and data access test coverage.
Decomposes goals into executable phases, features, tasks, and subtasks during project or issue planning. Defines acceptance criteria, risks, and native GitHub issue dependencies.
Uses Manus-style file-based planning with task_plan.md, findings.md, and progress.md. Supports complex multi-step tasks, research projects, and work requiring more than five tool calls.
File-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use for multi-step tasks requiring >5 tool calls.
Maintains task_plan.md, findings.md, and progress.md, with lifecycle hooks supplying selected planning context. Automatic recovery reads project planning files; explicit catch-up supports local session metadata or bounded excerpts. Intended for research or work needing five or more tool calls.
Organizes multi-step tasks, research projects, and general planning through persistent Markdown files. Supports progress tracking and knowledge storage, with PRD-specific work directed to a separate planner.
Maintains task_plan.md, findings.md, and progress.md, with lifecycle hooks supplying selected planning context. Automatic recovery reads project planning files; explicit catch-up supports local session metadata or bounded excerpts. Intended for research or work needing five or more tool calls.
Maintains task_plan.md, findings.md, and progress.md, with lifecycle hooks supplying selected planning context. Automatic recovery reads project planning files; explicit catch-up supports local session metadata or bounded excerpts. Intended for research or work needing more than five tool calls.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name