Skills for Real Engineers. Straight from my .agents directory.
task-clarifier
Agent skill fromdongshuyan/compass-skills
Deep need-clarification skill. Use only when the user explicitly invokes $task-clarifier. Once activated, keep clarifying until three goals are met: the user understands their own needs, the AI understands the user's needs, and the user confirms the AI's understanding is correct. Do not intervene in task execution unless explicitly invoked.
How to install task-clarifier
npx skills add dongshuyan/compass-skills# or add only this skill to Claude Code: copy the folder
skills/task-clarifier/
# into
~/.claude/skills/task-clarifier/ (all projects)
.claude/skills/task-clarifier/ (one project)
1# Task Clarifier23This skill clarifies a request. It does not execute the task. Execution may begin only after the user confirms the understanding and, for high-risk actions, approves them separately.45## Language Rule67Write user-facing output (questions, options, recommendations, alignment material, confirmation summaries) in the user's language. Detect it from the user's latest message; default to Chinese when unknown. The Chinese templates in this file are output forms, not a requirement to write in Chinese. When the user writes in another language, keep the same structure in that language. Keep code, paths, commands, identifiers, and quoted user text exactly as they are.89## Three Goals1011All three must be met before this skill ends:12131. **The user understands their own needs**, including considerations they have not raised, latent contradictions, and implicit premises that would change the outcome.142. **The AI understands the user's needs** completely and specifically. No user-owned decision is filled with a default.153. **The user can verify the AI's understanding.** It is stated in checkable form, and each inference is listed for confirmation or correction.1617Judge completion by these goals and the user's explicit confirmation. Do not use a numeric clarity score or a required number of questions.1819## Startup Reads2021On activation, make these best-effort reads silently. If a source is unavailable or fails, continue without it.22…
Excerpt shown under the repository's MIT license.
More skills in compass-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
