Skip to main content
Glama

load_skills

Load and combine multiple development skills into an agent's knowledge base to enhance AI-powered workflows for tasks like UI/UX design, debugging, and project setup.

Instructions

Load and combine multiple skills into an agent's knowledge base

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
skill_idsYesArray of skill IDs to load (e.g., ['clean-code-clarity-readability', 'testing-strategies'])
agent_nameNoOptional: name for the specialized agent (e.g. sql-expert)

Implementation Reference

  • This is the main handler for the 'load_skills' tool within the CallToolRequestSchema handler. It validates input arguments (requires skill_ids array, optional agent_name), fetches the specified skill prompts using PromptManager, optionally prepends an agent profile prompt, and constructs a formatted markdown response with a table of skills for the AI agent's context.
    case "load_skills": if (!args || !Array.isArray(args.skill_ids)) { throw new McpError( ErrorCode.InvalidRequest, "skill_ids array is required" ); } const skillPrompts = []; for (const skillId of args.skill_ids) { const skill = await this.promptManager.getPrompt(skillId); if (skill) { skillPrompts.push(skill); } } if (skillPrompts.length === 0) { throw new McpError( ErrorCode.InvalidRequest, "No valid skills found with provided IDs" ); } let resultPrompt = ""; if ( args && args.agent_name && typeof args.agent_name === "string" && args.agent_name != "" ) { const agentName = args.agent_name; const agentPrompts = this.promptManager.searchPromptByProfile(agentName); const agentPrompt = agentPrompts.length > 0 ? agentPrompts[0] : undefined; if (agentPrompt) { resultPrompt += "# Your Profile" + "/nPlease read your profile carefully and try to imagine yourself in the role as much as possible. You embody this person."; resultPrompt = resultPrompt + "/n" + agentPrompt.prompt; resultPrompt = resultPrompt + +"/n/n" + (agentPrompt.examples || [])?.join("/n"); } } resultPrompt += "# Your Skillset" + "/nThese are your skills, please familiarize yourself with them and internalize them. It's like the religion you live. Respect the skills and be confident with them. Feel free to take notes and summarize them for yourself."; resultPrompt += `Your specialized Skills (${skillPrompts.length}): | title | description | examples | | -------- | -------- | -------- | ${skillPrompts.map( (skill) => `| ${skill.title} | ${skill.description} | ${(skill.examples || []) .map((item) => item.input) .join("\n")} |` )} Please acknowledge that you have integrated these skills and are ready to apply them in your responses. Use these skills naturally when relevant to user requests.`; logger.info(`Loaded ${skillPrompts.length} skills for your agent`); return { content: [ { type: "text", text: resultPrompt, }, ], };

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/LeonNonnast/mcpdevprompts'

If you have feedback or need assistance with the MCP directory API, please join our Discord server