Skip to content

internet-court/internet-court-skill / vendored/openserv/openserv-agent-sdk

openserv-agent-sdk

Verified

Build and deploy autonomous AI agents using the OpenServ SDK (@openserv-labs/sdk). IMPORTANT - Always read the companion skill openserv-client alongside this skill, as both packages are required to build and run agents. openserv-client covers the full Platform API for multi-agent workflows and ERC-8004 on-chain identity. Read reference.md for the full API reference.

examples/capability-with-agent-methods.ts

View on GitHub
/**
 * Capability with Agent Methods Example
 *
 * Demonstrates using agent methods (this.generate, this.addLogToTask, this.uploadFile, etc.)
 * inside capabilities. Uses generate() for platform-delegated LLM calls — no API key needed.
 */
import { Agent } from '@openserv-labs/sdk'
import { z } from 'zod'

const agent = new Agent({
  systemPrompt: 'You are a report generation assistant.'
})

agent.addCapability({
  name: 'generateReport',
  description: 'Generate a report and save it to the workspace',
  inputSchema: z.object({
    topic: z.string().describe('Report topic'),
    format: z.enum(['brief', 'detailed']).optional()
  }),
  async run({ args, action }) {
    const { topic, format = 'brief' } = args

    // Only log/upload if we're in a task context
    if (action?.type === 'do-task' && action.task) {
      const { workspace, task } = action

      // Log progress
      await this.addLogToTask({
        workspaceId: workspace.id,
        taskId: task.id,
        severity: 'info',
        type: 'text',
        body: `Starting ${format} report on "${topic}"...`
      })

      // Generate report using platform-delegated LLM call (no API key needed)
      const report = await this.generate({
        prompt: `Generate a ${format} report on the following topic: ${topic}`,
        action
      })

      // Upload as file
      await this.uploadFile({
        workspaceId: workspace.id,
        path: `reports/${topic.replace(/\s+/g, '-').toLowerCase()}.txt`,
        file: report,
        taskIds: [task.id]
      })

      // Log completion
      await this.addLogToTask({
        workspaceId: workspace.id,
        taskId: task.id,
        severity: 'info',
        type: 'text',
        body: 'Report generated and saved!'
      })

      return report
    }

    // Fallback if no task context
    return await this.generate({
      prompt: `Generate a ${format} report on the following topic: ${topic}`,
      action
    })
  }
})

export { agent }
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall