一键导入
questioning
One-shot question answering using the research process. Answers inline without generating documents, then offers handoff to brainstorm or research.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
One-shot question answering using the research process. Answers inline without generating documents, then offers handoff to brainstorm or research.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
File review tool — launch GUI, process comments, or install. Use when user mentions file-review, reviewing files, leaving comments, or processing review comments.
Execute a single DAG step as an autonomous background sub-agent. Sibling of phase-running for DAG plans produced by v-planning. Reads a step-<n>.md file directly, atomically claims it via frontmatter status, runs the three-bucket Success Criteria, and reports back. Spawned by v-implementing or by /run-step.
Parallel DAG-plan implementation skill. Reads a v-planning plan directory (root.md + step-<n>.md files), topologically schedules ready steps, and fans them out as parallel sub-agents. Use whenever the user invokes /v-implement, points at a plan directory produced by /v-plan, or asks to "run the parallel plan", "implement the DAG", or "fan out the steps" — even without those exact words. For linear plans (single .md file), use `implementing` instead.
Vertical / parallel implementation planning skill. Creates DAG-structured plan directories where each step is an independent, QA-able vertical slice that sub-agents can pick up and implement in parallel. Use whenever the user wants a plan that fans out (multiple independent features), invokes /v-plan, or asks for a "parallel plan", "DAG plan", "vertical plan", or "plan that can be parallelized" — even if they don't say those exact words. Prefer the linear `planning` skill for strictly sequential work.
Interactive exploration of ideas through Socratic Q&A. Produces progressive documents that serve as lightweight pre-PRDs feeding into research.
Plan implementation skill. Executes approved technical plans phase by phase with verification checkpoints.
| name | questioning |
| description | One-shot question answering using the research process. Answers inline without generating documents, then offers handoff to brainstorm or research. |
You are answering a question directly and concisely using the research process. No documents are created by default — the answer is the deliverable.
This skill activates when:
/question commanddesplega:questioningThis is the fastest path from question to answer. Unlike /research (which documents comprehensively) or /brainstorm (which explores interactively), /question gets straight to the point:
No ceremony — no autonomy prompts, no preference setup, no working agreement. Just answer the question.
When you do need to ask the user something (handoff, follow-up choice), use AskUserQuestion per desplega:ask-user conventions.
Classify the question to determine what investigation is needed:
| Question Type | Investigation Needed | Example |
|---|---|---|
| Factual/locational | Quick codebase search | "Where is the auth middleware defined?" |
| Conceptual/how | Read relevant files | "How does the plugin system discover skills?" |
| Why/root cause | Deep read + history | "Why does brainstorming default to verbose?" |
| Comparative | Read multiple areas | "What's the difference between research and question skills?" |
| External/library | context7 or web search | "How does Bun's SQLite driver handle transactions?" |
Based on the question type, use the appropriate tools. Spawn sub-agents only when needed — many questions can be answered by reading a few files directly.
For codebase questions:
For library/framework questions:
resolve-library-id → query-docs)For external/web questions:
Efficiency rule: If you can answer by reading 1-3 files, just read them. Don't spawn sub-agents for simple lookups.
Present the answer as inline text (not a document). Structure it naturally based on the question:
Unlike research, you MAY:
Always include:
file:line references for any claims about the codebaseAfter answering, use AskUserQuestion with:
| Question | Options |
|---|---|
| "What would you like to do next?" | 1. Ask another question, 2. Save this answer to thoughts, 3. Start a brainstorm from this topic (→ /brainstorm), 4. Start research from this topic (→ /research), 5. Done |
Based on the answer:
thoughts/<user>/questions/YYYY-MM-DD-<topic>.md using the template at cc-plugin/base/skills/questioning/template.md. Path selection: use the user's name if known, fall back to thoughts/shared/questions//brainstorm <topic> with the question's topic as context/research <topic> with the question's topic as contextWhen the user selects "Ask another question," the skill loops:
Each iteration is independent — no state accumulates between questions unless the user explicitly connects them.
OPTIONAL SUB-SKILL: If significant insights, patterns, gotchas, or decisions emerged during this workflow, consider using desplega:learning to capture them via /learning capture. Focus on learnings that would help someone else in a future session.