Skip to content

internet-court/internet-court-skill / vendored/0g/0g-compute

0g-compute

Verified

0G Compute Network guide for decentralized AI inference, fine-tuning, and GPU services. Covers chatbots, image generation, speech-to-text, SDK integration (0g-serving-broker), processResponse API, broker.inference methods, CLI commands (0g-compute-cli), and account management. Use this skill for any 0G compute, 0G AI, or decentralized GPU question.

.github/workflows/claude-code-review.yml

View on GitHub
name: Claude Code

on:
  issue_comment:
    types: [created]
  pull_request_review_comment:
    types: [created]
  issues:
    types: [opened, assigned]
  pull_request_review:
    types: [submitted]

jobs:
  claude:
    # Only allow repo members (admin/write/maintain permissions) to trigger
    if: |
      (
        (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
        (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
        (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
        (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
      )
    runs-on: ubuntu-latest
    permissions:
      contents: write
      pull-requests: write
      issues: write
      id-token: write
      actions: read
    steps:
      - name: Check user permissions
        id: check
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          # Get the username of the user who triggered the action
          if [ "${{ github.event_name }}" == "issue_comment" ] || [ "${{ github.event_name }}" == "pull_request_review_comment" ]; then
            ACTOR="${{ github.event.comment.user.login }}"
          elif [ "${{ github.event_name }}" == "pull_request_review" ]; then
            ACTOR="${{ github.event.review.user.login }}"
          elif [ "${{ github.event_name }}" == "issues" ]; then
            ACTOR="${{ github.event.issue.user.login }}"
          else
            ACTOR="${{ github.actor }}"
          fi

          echo "Checking permissions for: $ACTOR"

          # Check user permission level
          PERMISSION=$(gh api repos/${{ github.repository }}/collaborators/$ACTOR/permission --jq '.permission' 2>/dev/null || echo "none")
          echo "Permission level: $PERMISSION"

          # Only allow admin, write, maintain
          if [[ "$PERMISSION" == "admin" || "$PERMISSION" == "write" || "$PERMISSION" == "maintain" ]]; then
            echo "✅ Permission granted"
          else
            echo "❌ Permission denied - only repo members can use @claude"
            exit 1
          fi

      - name: Checkout repository
        uses: actions/checkout@v6
        with:
          fetch-depth: 0
          submodules: recursive

      - name: Run Claude Code
        uses: anthropics/claude-code-action@v1
        env:
          CLAUDE_CODE_OAUTH_TOKEN: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
        with:
          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}

          claude_args: |
            --model claude-sonnet-4-5-20250929
            --max-turns 40
            --allowedTools "Bash(*)"
            --system-prompt "You are a code review expert for the 0G Compute Skills project.

            Project Background:
            - This is a Claude Code skill package for the 0G Compute Network
            - Contains documentation and examples for AI inference, fine-tuning, and account management
            - Covers SDK usage (TypeScript, @0glabs/0g-serving-broker), CLI commands, and Web UI
            - Key files: SKILL.md (main skill definition), inference.md, fine-tuning.md, account-management.md, examples.md

            Follow these standards when reviewing:
            1. Documentation accuracy - API signatures, parameter orders, and code examples must be correct
            2. SDK pattern correctness - especially processResponse(providerAddress, chatID, receivedContent) parameter order
            3. Consistency across documents - examples should match SKILL.md patterns
            4. Completeness of examples - include imports, error handling, and environment variable usage
            5. Markdown formatting and readability

            In code reviews:
            - Mark incorrect API usage or parameter order as [CRITICAL]
            - Mark documentation inconsistencies as [WARNING]
            - Mark formatting or style issues as [nit]
            - Give positive feedback for good documentation patterns

            When fixing content:
            - Only use allowed tools
            - Verify code examples are consistent with SKILL.md
            - Ensure all API signatures match the canonical patterns
            - Check that chatID retrieval follows the correct priority (ZG-Res-Key header first)"

          settings: |
            {
              "env": {
                "NODE_ENV": "development"
              }
            }
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall