123 items
1 post, 122 guides
Configure model, effort, tools, MCP servers, and invocation scope.
Hide skills from Claude's auto-selection until manually triggered.
Pre-approve tools before a skill executes so it runs without prompts.
Changes to skill files are detected and reloaded automatically.
Researcher, auditor, reviewer, and other ready-made subagent types.
Create reusable subagent definitions at project or user level.
Auto-memory that persists across multiple subagent invocations.
Prevent bloating the main conversation with research or exploration.
Fires when a session begins; load env vars and initialize state.
Fires before Claude processes user input; can validate or block.
Fires when a slash command expands; can block or inject context.

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.