Skip to main content
Glama

search_skills

Search the SkillFlow marketplace for AI agent skills by keyword, category, or tag to find matching skills with trust scores and installation instructions.

Instructions

Search for AI agent skills on SkillFlow marketplace by keyword, category, or tag. Returns matching skills with trust scores and install instructions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query (keyword, category name, or tag)
categoryNoFilter by category (e.g., 'Development', 'Productivity', 'DevOps')
min_trust_scoreNoMinimum trust score (0-100)

Implementation Reference

  • The handler logic for the 'search_skills' tool, which filters the 'SKILL_CATALOG' based on query, category, and trust score.
    case "search_skills": {
      const query = (args?.query as string || "").toLowerCase();
      const category = (args?.category as string || "").toLowerCase();
      const minScore = (args?.min_trust_score as number) || 0;
    
      const results = SKILL_CATALOG.filter((skill) => {
        const matchesQuery =
          skill.name.toLowerCase().includes(query) ||
          skill.description.toLowerCase().includes(query) ||
          skill.tags.some((t) => t.includes(query));
        const matchesCategory = !category || skill.category.toLowerCase() === category;
        const matchesScore = skill.trust_score >= minScore;
        return matchesQuery && matchesCategory && matchesScore;
      });
    
      if (results.length === 0) {
        return {
          content: [{
            type: "text",
            text: `No skills found for "${args?.query}". Try browsing categories with list_categories or check trending skills with get_trending_skills.\n\nBrowse all skills at: ${SKILLFLOW_BASE_URL}/explore`,
          }],
        };
      }
    
      const formatted = results.map((s) =>
        `**${s.name}** (Trust: ${s.trust_score}/100)\n` +
        `  ${s.description}\n` +
        `  Category: ${s.category} | Publisher: ${s.publisher}\n` +
        `  Platforms: ${s.platforms.join(", ")}\n` +
        `  Install: \`${s.install}\`\n` +
        `  URL: ${s.url}`
      ).join("\n\n");
    
      return {
        content: [{
          type: "text",
          text: `Found ${results.length} skill(s) matching "${args?.query}":\n\n${formatted}\n\n---\nBrowse more at: ${SKILLFLOW_BASE_URL}/explore`,
        }],
      };
    }
  • src/index.ts:190-202 (registration)
    Registration of the 'search_skills' tool, including its schema and description.
    {
      name: "search_skills",
      description: "Search for AI agent skills on SkillFlow marketplace by keyword, category, or tag. Returns matching skills with trust scores and install instructions.",
      inputSchema: {
        type: "object" as const,
        properties: {
          query: { type: "string", description: "Search query (keyword, category name, or tag)" },
          category: { type: "string", description: "Filter by category (e.g., 'Development', 'Productivity', 'DevOps')" },
          min_trust_score: { type: "number", description: "Minimum trust score (0-100)", default: 0 },
        },
        required: ["query"],
      },
    },
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, description carries full burden. It discloses return values ('trust scores and install instructions') but omits other behavioral traits like pagination, rate limits, or result ordering.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two well-structured sentences. First establishes the search operation and filters, second describes return payload. Zero waste, front-loaded with action verb.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Adequate for a 3-parameter search tool without output schema. Covers search domain, filter options, and return data. Minor gap: no mention of pagination or result limits.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage with clear descriptions. The description reinforces parameter semantics by mentioning 'keyword, category, or tag' and 'trust scores', but adds minimal new information beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clear verb ('Search') and resource ('AI agent skills on SkillFlow marketplace') with specific search criteria (keyword, category, tag). Lacks explicit differentiation from siblings like get_skill_details or get_trending_skills.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context on how to search (by keyword, category, or tag) and what filters are available. Does not explicitly name alternatives or exclusion criteria (e.g., when to use get_skill_details instead).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

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/rafsilva85/skillflow-mcp-server'

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