Skip to main content
Glama

kit

Browse personal agents, commands, and skills. List all items, search by query, or get details by name and kind.

Instructions

Browse the personal kit: agents, commands, skills.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYes
kindNoFor action=get
nameNoFor action=get
queryNoFor action=search

Implementation Reference

  • Registration of the 'kit' tool in the TOOLS array with input schema defining actions: list-agents, list-commands, list-skills, get, search.
    const TOOLS = [
      {
        name: 'kit',
        description: 'Browse the personal kit: agents, commands, skills.',
        inputSchema: {
          type: 'object',
          properties: {
            action: { type: 'string', enum: ['list-agents', 'list-commands', 'list-skills', 'get', 'search'] },
            kind:   { type: 'string', enum: ['agent', 'command', 'skill'], description: 'For action=get' },
            name:   { type: 'string', description: 'For action=get' },
            query:  { type: 'string', description: 'For action=search' },
          },
          required: ['action'],
        },
      },
  • The handleKit function — the actual handler that dispatches on action (list-agents, list-commands, list-skills, get, search) and calls listKit, findItem, or searchKit from kit.js.
    async function handleKit(args) {
      const kit = await listKit();
      switch (args.action) {
        case 'list-agents':   return kit.agents.map(slim);
        case 'list-commands': return kit.commands.map(slim);
        case 'list-skills':   return [...kit.skills, ...kit.skillsExtras].map(slim);
        case 'get': {
          const item = findItem(kit, args.kind, args.name);
          if (!item) return { error: `Not found: ${args.kind}/${args.name}` };
          return { kind: item.kind, name: item.name, absPath: item.absPath, content: item.content ?? item.skillContent };
        }
        case 'search': return searchKit(kit, args.query ?? '');
        default: return { error: `Unknown action: ${args.action}` };
      }
    }
  • listKit() — reads the canonical kit/ directory (agents, commands, skills) and returns a structured index with caching.
    export async function listKit(kitRoot) {
      kitRoot = resolveKitRoot(kitRoot);
      const cached = kitCache.get(kitRoot);
      if (cached && Date.now() - cached.ts < KIT_CACHE_TTL_MS) {
        return cached.value;
      }
      const [agents, commands, skills, skillsExtras] = await Promise.all([
        readMdDir(path.join(kitRoot, 'agents'),    'agent'),
        readMdDir(path.join(kitRoot, 'commands'),  'command'),
        readSkillsDir(path.join(kitRoot, 'skills')),
        readSkillsDir(path.join(kitRoot, 'skills-extras')).catch(() => []),
      ]);
      const value = { agents, commands, skills, skillsExtras, kitRoot };
      kitCache.set(kitRoot, { value, ts: Date.now() });
      return value;
    }
  • searchKit() — filters kit items by name/description matching the query string.
    export function searchKit(kit, query) {
      const q = query.toLowerCase();
      const all = [...kit.agents, ...kit.commands, ...kit.skills, ...kit.skillsExtras];
      return all.filter(item =>
        item.name.toLowerCase().includes(q) ||
        (item.description ?? '').toLowerCase().includes(q)
      ).map(({ kind, name, description, absPath }) => ({ kind, name, description, absPath }));
    }
  • findItem() — retrieves a single item by kind (agent/command/skill) and name from the kit index.
    export function findItem(kit, kind, name) {
      const buckets = { agent: kit.agents, command: kit.commands, skill: [...kit.skills, ...kit.skillsExtras] };
      const b = buckets[kind];
      if (!b) throw new Error(`Unknown kind: ${kind}`);
      return b.find(x => x.name === name) ?? null;
    }
Behavior2/5

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

With no annotations, the description must disclose side effects or requirements. It does not state whether actions are read-only, require permissions, or have other behavioral traits.

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

Conciseness3/5

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

One sentence, appropriately short, but it lacks substance. It is concise but at the expense of clarity.

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

Completeness2/5

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

Given multiple actions and parameters, the description is too brief. It omits explanation of the 'get' and 'search' actions and their parameter requirements, and no output schema is provided.

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 coverage is 75% (kind, name, query have descriptions). The description adds no additional meaning beyond the schema. It does not clarify the action enum values or parameter dependencies.

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

Purpose3/5

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

The description states 'Browse the personal kit: agents, commands, skills.' which gives a general purpose but oversimplifies by not covering 'get' or 'search' actions. It vaguely distinguishes from siblings but lacks specificity.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives like forensics or install. The description does not mention use cases or exclusions.

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/luanpdd/kit-mcp'

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