Questions Form

Present multiple clarifying questions as an interactive Telegram form using inline buttons. Use when the agent needs to ask the user 2 or more clarifying questions before proceeding with a task, and wants to present them all at once in a structured form layout with selectable options and an "Other" free-text escape hatch. Triggers when: gathering multi-faceted requirements, onboarding flows, preference collection, or any scenario requiring structured multi-question input from the user via Telegram.

This skill is internally coherent and low-risk, but before installing check these practical points: ensure your agent platform already provides the Telegram integration (bot token/webhook) since the skill assumes it and declares no credentials; confirm the agent will keep per-conversation state so forms work as documented (the skill expects transient in-memory state and re-sends forms if context is lost); be mindful that free-text answers may contain PII or secrets — decide whether the agent should redact or treat such text as sensitive before storing or forwarding; verify callback_data handling respects Telegram's 64-byte limit as noted; and ensure your agent does not forward collected answers to external services unless you expect that. If you need stricter guarantees (audit logs, encrypted storage, or persistence across restarts), request or add those capabilities explicitly before using this in production.

Type: OpenClaw Skill Name: questions-form Version: 1.0.0 The OpenClaw AgentSkills skill bundle defines a structured form interaction pattern for Telegram. All instructions in SKILL.md and references/form-patterns.md are focused on presenting questions, handling user input via buttons and free text, managing internal form state, and validating completion. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts to subvert the agent's core purpose. The skill's behavior is clearly aligned with its stated goal of gathering multi-faceted requirements from the user.