Planning with Files
Keep multi-step work organized with persistent plan, findings, and progress files.
Find workflows for designing, testing, and maintaining reusable agent capabilities.
73 skillsKeep multi-step work organized with persistent plan, findings, and progress files.
Design agents around capabilities, domain knowledge, context and progressively added complexity.
Find suitable partners and define shared campaign goals, responsibilities and measurement.
Register a named or text-defined visual style in the numbered library using a supplied or generated representative image.
Update context-mode and repair its installed hooks and configuration.
Audit a codebase, prioritize evidence-backed findings, and write implementation plans for another agent or developer.
Review a specification or implementation plan with a multi-agent panel before starting work.
Search indexed project content and session knowledge with focused context-mode queries.
Manage Paseo projects, workspaces, scripts, agents, schedules and heartbeats through its CLI or MCP.
Add the Agentation visual-feedback toolbar to a React or Next.js project, choose manual feedback or MCP sync, and verify the selected connection.
Capture command failures, corrections, missing capabilities, and better approaches as structured learnings that can improve future agent work.
Turn an idea or objective into a goal package for /goal. Interviews the user, builds a reviewed fact sheet via Plannotator, then explores the codebase to produce an execution plan.
Examine AI research directions, generalization, scaling and the relationship between capabilities and safety.
Convert books, document folders and related sources into structured Agent Skills, with chapter files, frameworks, a glossary and reusable reference notes.
Explore a software idea with fresh-context reviewers and produce a concept brief.
Maintain a durable workspace for complex reasoning and repository tasks, with explicit goals, evidence, decisions, and resumable progress.
Use language-specific Claude API and SDK references for streaming, tools and agent integrations.
Combine a subject with numbered hand-drawn styles, layouts and colors to create copyable image prompts.
Learn to build Python or TypeScript MCP servers with tools, resources and service integrations.
Build and validate experimental WebMCP tools for an existing web page.
Design and author DeepTutor skills (SKILL.md packages).
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities.
Find and install Agent Skills for a specific task.
Consolidate previous agent sessions into reviewed memory and skill improvements through an offline sleep workflow.
Find workflows for designing, testing, and maintaining reusable agent capabilities.