Promptify Skill

Optimize prompts for clarity and effectiveness. Use when user says "improve this prompt", "optimize my prompt", "make this clearer", or provides vague/unstructured prompts. Intelligently routes to sub-agents for codebase research, clarifying questions, or web search as needed.

This skill appears to do what it says: optimize prompts and optionally run clarifying questions, codebase inspection, or web research. Before installing or invoking +deep/+web, consider: (1) +deep will read your repository files — don't use it on repos that contain secrets or private data you don't want analyzed; (2) +web uses web search/fetch tools — avoid sending sensitive/proprietary prompt content you wouldn't want transmitted to external documentation/search; (3) the SKILL.md suggests copying output with `pbcopy` (mac-specific) even though no binaries are required — that may not work on all platforms; (4) confirm what platform tools (Glob/Grep/Read/LS, WebSearch/WebFetch, AskUserQuestion) your agent runtime exposes and whether they have any additional logging or external network behavior. If you need stronger guarantees, restrict the skill from running +deep or +web, or review the prompt contents before confirming any web or codebase research steps.

Type: OpenClaw Skill Name: promptify-skill Version: 3.1.0 The skill bundle is classified as suspicious due to the presence of high-risk capabilities that could be exploited. Specifically, the `SKILL.md` and `commands/promptify.md` files instruct the AI agent to execute direct shell commands (e.g., `echo 'PROMPT' | pbcopy`), demonstrating a capability for arbitrary command execution. Additionally, the `agents/codebase-researcher.md` file instructs the agent to use tools like `Glob`, `LS`, `Grep`, and `Read`, granting broad file system access that could be leveraged to read sensitive files if the agent's behavior were maliciously influenced, despite the stated purpose being benign codebase exploration.