Prompting

Write, test, and iterate prompts for AI models with voice preservation, model-specific adaptation, and systematic failure analysis.

This skill appears coherent for prompt engineering. Before installing: (1) Be aware it will store prompt memory, sample texts, and history in ~/prompting — avoid putting secrets or confidential data into those files. (2) Review and periodically prune or encrypt ~/prompting if it will contain sensitive voice samples or proprietary prompts. (3) Set restrictive file permissions (chmod 600) if you want to limit access. (4) If you do not want the agent to persist voice or history, either decline to create those files or use a disposable directory. (5) Because the skill can be invoked by the agent, consider disabling autonomous invocation if you don't want automatic reads/writes of ~/prompting without explicit consent.

Type: OpenClaw Skill Name: prompting Version: 1.0.0 The skill bundle is designed to assist with prompt engineering, including managing user preferences, prompt patterns, and iteration history within the `~/prompting/` directory. It instructs the AI agent to read from and write to `~/prompting/memory.md` and `~/prompting/history.md`, which is directly aligned with its stated purpose. The `memory-template.md` file contains a `mkdir -p ~/prompting/patterns` command for directory setup, which is a benign file system operation. There is no evidence of data exfiltration, unauthorized remote execution, persistence mechanisms, or prompt injection attempts against the OpenClaw agent itself. The instructions for generating 'adversarial inputs' are for testing other AI models, not for malicious actions by the skill.