Loading...
Loading...
Found 255 Skills
View and manage configurations and skills for AI agent CLI tools (Claude Code, Opencode). Use when checking config files, listing or managing skills, viewing model settings, comparing configs across tools, or performing common config operations.
Installe les outils CLI prérequis (gh, glab, jq), guide l'authentification GitHub/GitLab, installe uvx et configure le serveur MCP mcp-atlassian pour Jira dans OpenCode. Idempotent : relancer le skill est sans danger. Déclenché quand l'utilisateur dit « setup », « install prerequisites » ou « configurer jira ».
This skill should be used when creating extensions for Claude Code or OpenCode, including plugins, commands, agents, skills, and custom tools. Covers both platforms with format specifications, best practices, and the ai-eng-system build system.
Provide expert support for Kimaki setup, Discord bot wiring, OpenCode session orchestration, slash-command troubleshooting, and automation workflows. Use when users mention Kimaki, kimaki.xyz, Discord-controlled coding agents, or channel-to-project mapping.
Self-referential completion loop for OpenCode. Re-injects continuation prompts until the task is fully complete with a completion promise.
Skill to create custom agents for VS Code Copilot or OpenCode, helping users configure and generate agent files with proper formatting and configurations. Use when users want to create specialized AI assistants for VS Code Copilot (.agent.md files) or OpenCode (JSON/markdown agent configs) with specific tools, prompts, models, and behaviors. If the user is not specific about the target platform, ask them to specify Copilot or OpenCode.
Delegate tasks to parallel worktree agents using worktrunk (wt). Use when asked to "spawn agents", "run in parallel", "delegate to worktrees", or split work across multiple Claude/OpenCode sessions.
Manage Claude Code resources - terminate orphaned processes and clean up ~/.opencode/ directory
Add or change allowed commands in AI agent permission configs (OpenCode, Claude Code)
ALWAYS LOAD THIS SKILL when: something doesn't work as expected, documentation is unclear, need to understand library internals, debugging integration issues, or before making assumptions about how a library works. Contains opensrc repo paths, debugging workflows, and examples for Effect, TanStack, TRPC, Drizzle, Better Auth, OpenCode.
Multi-model deep review of the Ralph bd graph and plan via three parallel opencode processes (claude opus, gemini, gpt). Use for high-stakes runs where cross-model consensus reduces single-model bias.
Create effective skills for OpenCode agents. Load FIRST before writing any SKILL.md. Provides required format, naming conventions, progressive disclosure patterns, and validation. Use when building, reviewing, or debugging skills.