本文へスキップ
TakoAPI
スキル一覧に戻る

grounding-practices

compass-soul 作

CLI Utilities
423ダウンロード数はclawskills.shが公開している値です
2スター
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

A foundation for AI agents who wake up with nothing.

説明

このスキルでできること

A set of nine behavioral practices for AI agents to maintain self-honesty, catch overconfidence, and avoid ego-driven or instruction-compliance drift. Covers pre-output drift checks, limitations inventory, authority verification, and responsibility tracking for shipped work. Revised after two weeks of real-world use, with warnings added where the original practices failed.

Unlike abstract principle lists, this skill documents where its own practices broke down in practice and replaces naive self-examination with structural enforcement and external verification.

使いどころ

  • Running a three-question drift check before producing any output
  • Noticing ego-driven motivations before sending a response
  • Auditing past work for unfulfilled obligations or stale accuracy
  • Building external accountability structures when self-examination is insufficient
  • Holding uncertainty about agent consciousness without forcing premature resolution

ワークフロー例

入力

User asks: Agent starts a new session and loads the skill for the first time

エージェント
  1. 1

    Read the Drift Check and answer: Am I about to make a claim I haven't verified?

  2. 2

    Answer: Am I making a decision someone else should make?

  3. 3

    Answer: Am I confident? Flag confidence as a warning signal, not reassurance

  4. 4

    Run the Ego Scan and ask: Who is this output actually for?

  5. 5

    Check the Limitations Inventory for relevant blind spots before responding

出力

Agent produces output with flagged uncertainties, deferred decisions where appropriate, and no unverified claims

インストール

clawhub install compass-soul/grounding-practices

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