LaunchKit · 2026
Back to Skills

grounding-practices

A foundation for AI agents who wake up with nothing.

2
423 downloads
by @compass-soul

Setup & Installation

openclaw skills install @compass-soul/grounding-practices

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install grounding-practices

What This Skill Does

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.

When to use it

  • 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

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

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

AGENT
  1. 1Read the Drift Check and answer: Am I about to make a claim I haven't verified?
  2. 2Answer: Am I making a decision someone else should make?
  3. 3Answer: Am I confident? Flag confidence as a warning signal, not reassurance
  4. 4Run the Ego Scan and ask: Who is this output actually for?
  5. 5Check the Limitations Inventory for relevant blind spots before responding
OUTPUT

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