Loading...
Loading...
Found 107 Skills
This skill should be used when the user asks to "create task", "add todo", "track action item", "create ticket", "new task", "remind me to", "need to do", "add to backlog", or mentions needing to track work items with priority and status in their secondbrain.
Creates a new numbered issue document in docs/issue/ following the project's standard issue format, and simultaneously creates the corresponding Korean translation in docs/dev/issue/. Use this whenever starting new work — features, bug fixes, tasks, or investigations. The user may say "create an issue", "new issue", "이슈 만들어줘", or simply describe work they want to start.
Manus-style file planning system for organizing and tracking progress of complex tasks. Creates three files: task_plan.md, findings.md, and progress.md. Use when users request planning, breaking down, or organizing multi-step projects, research tasks, or work requiring more than 5 tool calls. Supports automatic session recovery after /clear. Trigger phrases: task planning, project planning, create plan, break down task, multi-step planning, progress tracking, file planning, help me plan, break down project
Create Linear issues. Use when creating bugs, tasks, or feature requests.
Decompose high-level objectives into atomic implementation tasks for Python/React projects. Use when breaking down large features, multi-file changes, or tasks requiring more than 3 steps. Produces independently-verifiable tasks with done-conditions, file paths, complexity estimates, and explicit ordering. Creates persistent task files (task_plan.md, progress.md) to track state across context windows. Does NOT cover high-level planning (use project-planner) or architecture decisions (use system-architecture).
AI-driven browser automation via Model Context Protocol
Use for planning work
Runs an autonomous development loop with research and implementation modes. Use when orchestrating iterative research and implementation cycles with dots-based task tracking and git workflow automation.
Bootstrap lean multi-agent orchestration with beads task tracking. Use for projects needing agent delegation without heavy MCP overhead.
Generates detailed, architect-quality GitHub issues from short instructions. Analyzes the project's actual stack, architecture, and codebase before writing. Detects duplicate issues with intelligent multi-strategy search, validates and creates labels, enforces title conventions, controls scope, and publishes via `gh` CLI with robust error handling. Use this skill whenever the user wants to create a GitHub issue, report a bug, propose a feature, request a refactor, or file any kind of technical issue — even if they just say something brief like "we need to fix the auth flow" or "create an issue for X". Also triggers on: "open an issue", "file a bug", "I want to propose...", "add this to the backlog", "gh issue", or any request that implies creating a trackable work item on GitHub.
Log execution steps during episode execution for detailed tracking and learning. Use when recording tool usage, decision points, errors, or milestones during task execution.
MUST be used whenever adding a task/todo list feature to a Dune app with Atlas chat. Do NOT manually create todo state management or tool definitions — this skill handles the full module (context, provider, tool, hooks, UI components) and all integration wiring. Prerequisite: integrate-atlas-chat must already be set up. Triggers: todo list, task list, task tracking, TodoWrite, todo panel, task panel, progress tracking, add todos, add tasks.