スキル一覧に戻る
WebSurfinMurf

aiclilistener

by WebSurfinMurf

0🍴 0📅 2026年1月18日
GitHubで見るManusで実行

SKILL.md


name: aiclilistener description: Farm out AI tasks via Named Pipe to get isolated context. Use when processing large files, batch summarization, or to avoid context pollution. Each call runs in fresh context.

AIclilistener Skill

Farm out work to a separate Codex instance running as a Named Pipe service. Each request gets fresh, isolated context - perfect for avoiding hallucinations when processing large amounts of data.

When to Use This Skill

  • Large file processing: Summarize files without filling your main context
  • Batch operations: Process multiple files with isolated context per file
  • Context pollution prevention: Keep your main conversation clean
  • Script automation: Write scripts that leverage AI for specific tasks

Prerequisites

  1. AIclilistener service must be running:

    cd path\to\AIclilistener\codex\windows
    .\Start-Service.bat
    
  2. Ask the user: "Is the AIclilistener service running?"

Usage Patterns

Direct Call (Interactive)

Use CodexClient.ps1 to send a request and get a response:

# Simple prompt
.\CodexClient.ps1 -Prompt "Summarize this: [content]"

# With options
.\CodexClient.ps1 -Prompt "Analyze this code" -Sandbox read-only -TimeoutSeconds 120

Script Generation (Automation)

Generate PowerShell scripts that use AIclilistener:

# Example: Summarize a file
$content = Get-Content -Path "C:\path\to\file.txt" -Raw
$prompt = "Summarize this file:`n$content"

# Call the service
$result = & ".\CodexClient.ps1" -Prompt $prompt -Raw

# Parse the result
$responses = $result | Where-Object { $_ -match '^\{' } | ForEach-Object { $_ | ConvertFrom-Json }
$finalResult = $responses | Where-Object { $_.status -eq 'success' }
$summary = $finalResult.result.message

Batch File Processing

Use the built-in CSV processor with custom prompts:

# Create CSV with file paths
@"
FilePath,Category
C:\docs\report.docx,Reports
C:\code\app.py,Code
"@ | Out-File files.csv

# Run with default summarization prompt (outputs files_processed.csv)
.\Process-Files.ps1 -CsvPath files.csv

# Run with custom prompt using placeholders
.\Process-Files.ps1 -CsvPath files.csv -Prompt "Extract all dates from: {fileContent}"

# Resume if interrupted
.\Process-Files.ps1 -CsvPath files.csv -Resume

Prompt placeholders: {fileName}, {extension}, {filePath}, {fileContent}

Context Isolation

Each call to AIclilistener spawns a fresh codex process. This means:

  • No memory of previous calls
  • No context pollution between requests
  • Clean slate for each task
  • Ideal for processing many items independently

JSON Request Format

{
  "prompt": "Your task here",
  "options": {
    "sandbox": "read-only",
    "timeout_seconds": 120
  }
}

JSON Response Format

{
  "status": "success",
  "result": {
    "message": "The AI response...",
    "events": [...]
  },
  "duration_ms": 1234
}

Service Commands

  • ping - Health check
  • status - Service info
  • shutdown - Stop service

Source Code

Optional: Get the latest version from GitHub:

git clone https://github.com/WebSurfinMurf/AIclilistener.git

Troubleshooting

  • "Pipe not found": Start the service with .\Start-Service.bat
  • Timeout errors: Increase -TimeoutSeconds parameter
  • Service not responding: Check the service window for errors

スコア

総合スコア

50/100

リポジトリの品質指標に基づく評価

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

0/10
説明文

100文字以上の説明がある

0/10
人気

GitHub Stars 100以上

0/15
最近の活動

3ヶ月以内に更新がある

0/10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

0/5

レビュー

💬

レビュー機能は近日公開予定です