Loading...
Loading...
Found 3,708 Skills
Write or change an adam-rs agent that is only a folder (agent/instructions.md, card, vars, tools, skills/, subagents/, mcp.json) and serve it with the adam-agent binary from the coder image. Use for 'add an agent', 'change an agent's instructions or MCP servers', 'why does adam-agent exit 78'. Not Docker Agent (cagent) agent.yaml.
Run Claude Code or Codex CLI on Muapi (api.muapi.ai) using Muapi credits instead of a separate vendor account. Use when the user wants a local coding agent to use Muapi as its model provider, asks which Muapi models work with Claude Code or Codex, or needs the base URL, API key variable, provider block or model name for either agent. Covers Claude Code (Anthropic Messages) and Codex CLI (OpenAI Responses), model discovery, verification and troubleshooting.
Initializes the Awesome Copilot ID SDLC architecture, AGENTS.md, and rules in the current project.
Codex 初學者必裝 Skills 與 Plugins。說「裝基本外掛」「新手設定」時載入。
Codex 用 chezmoi 同步設定到多台電腦。說「同步 Codex 設定」「chezmoi」時載入。
Codex 連接 Supabase MCP。說「連接 Supabase」時載入。
Configure which models pstack uses per role and at what reasoning budget. Detects your available models and writes ~/.config/pstack/pstack-models.md, which overrides the skill defaults. Use for /setup-pstack, "configure pstack models", "pstack budget", or changing pstack's model choices.
一次安裝所有 Codex 懶人包 Skill。當使用者說「全部安裝」或「裝完所有 Codex 懶人包」時載入。
Configure a free Gemini API in Codex. Load when the user says “Set up Gemini API.”
Configure global defaults and project conventions for working records, issue tracking and agent instruction entrypoints.
Connect an AI agent to the Prepr MCP server. Use this skill whenever the user wants to connect, set up, authorize, or fix the Prepr MCP connection, Prepr tools are missing or unauthorized, another Prepr skill needs MCP and it is not configured, the user asks how to use Prepr from Claude Code, Cursor, Codex, VS Code, Copilot, OpenCode, Claude Desktop, or ChatGPT, or asks about a Prepr MCP token.
Creates a fitness-config.json for a project with review weights that fit what the project is for. Scans the folder (or runs a full review first, if asked), classifies its purpose, proposes weights starting from a matching purpose profile, explains every change, and saves only the proposal the user approved. Use when the user says /fitness-config-init, asks to "create a fitness config", "set up fitness-config.json", "initialize fitness config", "tune review weights for this project", "weight the review for this repo", or wants the fitness review to reflect a project's purpose instead of the defaults.