Loading...
Loading...
Found 9,569 Skills
Guide for creating effective skills. Use when you want to create a new skill (or update an existing skill) that extends an agent with specialized workflows, tool integrations, or repo conventions.
Track calories with Lose It! - log food, track weight, and monitor nutrition goals
Configure and customize skills for your workspace by asking questions and updating skill files with your preferences.
[Utilities] Set coding experience level for tailored explanations
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md short enough for prompt use.
Use this skill to set up Holistics MCP and enable useful tools such as `search_docs`, `execute_aql`, and `generate_viz`
Audit a non-technical repo's folder structure for agent-navigability and propose a refactor plan. TRIGGER when user says "review structure", "audit folders", "audit my repo", "check organization", "is my repo agent-friendly", "clean up structure", or runs "/review-structure".
Shape conversation context (or a fresh task description) into a 5-part brief — Context / Task / Constraints / Verification / Output format — ready to hand off to an agent. Use when the user is ready to execute a task and wants it structured first. Composes naturally with /grill-me upstream, but works standalone too. Triggers: "/create-brief", "draft a brief", "shape this into a brief", "turn this into a task spec", "write a brief for this".
Universal task dispatcher. Start, route, and execute any task through the development workflow (Steps 0-9). Invoke on every task — /task <description>, /task
Train SONA neural patterns from successful task completions, view learned patterns, and optimize the intelligence pipeline
Explain a piece of code, a subsystem, or an architectural concept in the codebase, grounded in real files. Use when user says 'explain this', 'walk me through X', 'how does Y work', 'what does this module do', 'help me understand the Z flow', or 'onboard me on this component'. Do NOT use for writing permanent docs (use write-doc or arc42) or for code review (use review-diff).