本文へスキップ
TakoAPI
スキル一覧に戻る

hz-proactive-agent

lidekahdjdhdhsjjs-lang 作

Productivity & Tasks
370ダウンロード数はclawskills.shが公開している値です
1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

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve.

説明

このスキルでできること

A behavioral architecture for AI agents that adds proactive action, memory persistence, and self-improvement. Defines protocols for capturing corrections before responding, surviving context truncation, running background tasks autonomously, and evolving safely over time.

Standard agents lose state between sessions and wait for instructions; this provides concrete file-based protocols and trigger rules that make persistence and proactive behavior reliable by default.

使いどころ

  • Automatically saving a user correction like a color preference before the agent responds
  • Recovering full context after a long session gets compacted or truncated
  • Running memory maintenance as an isolated background cron without interrupting active work
  • Surfacing unprompted suggestions based on patterns in past conversations
  • Auditing all config files and cron prompts when migrating away from a deprecated tool

ワークフロー例

入力

User says: 'Use the blue theme, not red'

エージェント
  1. 1

    Detects a correction trigger in the message

  2. 2

    Stops before composing a response

  3. 3

    Writes 'Theme: blue (not red)' to SESSION-STATE.md

  4. 4

    Confirms the write succeeded

  5. 5

    Responds to the user

出力

Correction is durably stored in SESSION-STATE.md and survives context compaction

インストール

clawhub install lidekahdjdhdhsjjs-lang/hz-proactive-agent

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