本文へスキップ
TakoAPI
スキル一覧に戻る

task-panner-validator

cerbug45 作

Coding Agents & IDEs
483ダウンロード数はclawskills.shが公開している値です
0閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

This skill provides a secure, step-by-step task management system for AI Agents.

説明

このスキルでできること

A Python library for structured task execution in AI agents. Plans are defined as ordered steps, validated for safety issues, optionally approved by a human, then executed with support for dry runs, retries, and rollback checkpoints. Requires only the Python standard library.

Validation, approval gates, dry-run mode, and rollback checkpoints ship in a single file with zero dependencies, so it drops into any Python agent without conflict.

使いどころ

  • Gating database migrations behind a human approval step
  • Dry-running a destructive cleanup script before committing to it
  • Orchestrating multi-API workflows with per-step retry logic
  • Flagging irreversible operations before an automated pipeline runs
  • Saving and reloading task plans across agent sessions

ワークフロー例

入力

User asks: Run an ETL pipeline that extracts records from a database, transforms them, and loads them into a warehouse

エージェント
  1. 1

    Define three steps (extract, transform, load) with expected outputs and rollback flags set

  2. 2

    Call validate_plan to surface dangerous operations and collect warnings

  3. 3

    Execute the plan with dry_run=True to simulate without side effects

  4. 4

    Approve the plan and execute it with stop_on_error=True

  5. 5

    Call get_execution_summary to report progress percentage and per-step results

出力

Execution summary showing 100% progress and success status for each step

インストール

clawhub install cerbug45/task-panner-validator

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク