AI & Agents Agent Skills for Claude Code

Use when improving agent prompts, frontmatter, and tool restrictions.

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement…

Use for file-based context management, dynamic context discovery, and reducing context window bloat.

Use when creating or configuring Claude Code agents and their frontmatter.

Generate an AI SBOM declaration for a PR description.

Build applications that programmatically interact with GitHub Copilot.

Automate Griptape tasks via Rube MCP (Composio).

Automates software development tasks through an autonomous Plan-Work-Review cycle with multi-backend support.

Repair skill hygiene.

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement…

Select hook scope (plugin, project, global) by audience.

Browse hookify rule catalog. Use when installing pre-built rules or browsing categories. Do not use when writing custom rules; use…

LangChain tool creation and integration utilities for agent systems

Local context tooling for AI agents. Use it to select, shape, reuse, recover, and inspect context before inference when reading files…

Extract reusable knowledge from the current session into a persistent skill.

LLM-based zero-shot and few-shot classification for flexible intent detection

Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.

Enforces a high-accountability persona that drives AI agents to exhaust all technical solutions and eliminate excuses.

Workflow for publishing skills and agents to the dotnet-skills Claude Code marketplace.

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up…

File-based message queue for inter-agent coordination.