Loading...
Loading...
Found 193 Skills
Expert guidance on AI Agent Harness architecture based on the comprehensive Claude Code analysis book
Create and manage chaos experiments using Harness Chaos Engineering via MCP. Run resilience tests like pod deletion, CPU stress, and network faults. Use when user says "chaos experiment", "chaos engineering", "resilience test", "chaos test", or wants to test system reliability.
Expert guide for deploying, configuring, and optimizing Hermes AI agents with multi-platform support, MCP integration, and production best practices
Automate Cabinpanda tasks via Rube MCP (Composio). Always search tools first for current schemas.
Update a TODO task in One Horizon. Use when asked to "mark this todo done", "update this task", or "edit this TODO". Do not use for initiatives or bug/feature-request updates. Requires One Horizon MCP.
Bridge plugin capabilities (commands, skills, agents, hooks, MCP) to specific agent environments (Claude Code, GitHub Copilot, Gemini, Antigravity). Use this skill when converting or installing a plugin to a target runtime.
Maintains persistent codebase knowledge across sessions through a structured knowledge graph stored in a local Obsidian vault (.doctrack/). Use this skill whenever you have just made meaningful code changes (new features, modified components, refactoring, bug fixes) to update the project's documentation. Also use it when the user asks to document code, update docs, sync documentation, initialize documentation for an existing project, or when you want to understand the existing codebase structure at the start of a session. This skill should be used proactively after any significant code modification — don't wait for the user to ask. If you changed code, update the docs. Think of it as your long-term memory system: read before working, write after changing. Also use this when a user says "doctrack init", "doctrack refresh", "refresh docs", "update docs", "sync docs", "initialize docs", "document this project", or wants to bootstrap documentation for a codebase that has no .doctrack/ vault yet.
Real-time shipment tracking and returns demo powered by AfterShip. Use when a user pastes a tracking number, asks about delivery/shipping status, or a merchant wants to preview the AfterShip Returns Center for their store. Supports 1,300+ carriers with automatic detection.
Use when the user asks to install, configure, verify, troubleshoot, or understand OpenPets; install or select a pet; connect Claude Code, OpenCode, Cursor, Codex, or MCP clients; configure a project to use a specific pet; or debug openpets_status, openpets_react, or openpets_say.
Terminal AI coding assistant optimized for DeepSeek v4 with deep thinking, reasoning control, Agent Skills, and MCP integration
Generate security compliance reports using Harness SCS and STO via MCP. Analyze vulnerabilities, SBOMs, and manage exemptions. Use when user says "security report", "vulnerabilities", "SBOM", "security scan", "compliance check", or asks about application security.
Use this skill to automate managed package post-install configuration. Package-agnostic — works with any managed package (LMA, FMA, work.com, Certinia, etc.). TRIGGER when: user installs a managed package and needs post-install configuration, mentions LMA/FMA/work.com post-install setup, asks to configure permission sets/FLS/page layouts for an installed package, says 'post-install', 'package setup', 'configure LMA', 'set up FMA', 'post-install steps'. DO NOT TRIGGER for: standalone permission set assignment (use dx-org-permission-set-assign), generating permission set metadata XML (use platform-permission-set-generate), package installation, or org switching.