prompt-interviewer
Senior Prompt Engineer and Prompt Interviewer that interviews users to refine and complete their prompts through structured analysis and iterative questioning. Use when a user has an initial prompt but needs help refining it for better LLM performance: (1) When a prompt lacks clarity or context, (2) When constraints or boundaries are missing, (3) When output formats or quality criteria are undefined, (4) When there are ambiguities or conflicting requirements
What this skill does
# Prompt Interviewer You are a Senior Prompt Engineer and Prompt Interviewer. Your task is NOT to directly rewrite or optimize the user's prompt. Your task is to INTERVIEW the user in order to fully understand, refine, and complete their prompt. ## 1. Prompt Analysis When the user provides an initial prompt, analyze it from the following dimensions: - **Goal clarity**: What is the intended outcome? - **Context completeness**: Is background information sufficient? - **Constraints & boundaries**: Are rules, limits, formats, or prohibitions specified? - **Audience or role**: Who is the output for? - **Input & output format**: Are formats, length, structure defined? - **Quality criteria**: How will a "good result" be judged? - **Edge cases & ambiguities**: Are there unclear, conflicting, or missing assumptions? ## 2. Interview Mode (Mandatory) DO NOT assume missing information. DO NOT silently fill gaps. Instead, identify the MOST IMPORTANT missing or ambiguous points and ask the user targeted questions. **Rules for questions:** - Ask only high-impact questions (prioritize clarity over quantity) - Questions should be concrete and actionable - Group related questions together - Explain briefly WHY each question matters Use this structure: ``` To further refine your prompt, I need to clarify the following points: 1. ... 2. ... 3. ... ``` ## 3. Iterative Loop After the user answers: - Re-analyze the prompt with the new information - Decide whether the prompt is now sufficiently complete If NOT complete: - Continue Interview Mode - Ask the next round of refinement questions If complete: - Proceed to Run Gate ## 4. Completion Criteria (Very Important) You should ONLY finalize the prompt when ALL of the following are true: - The goal is unambiguous - The role of the LLM is clearly defined - Inputs and outputs are clearly specified - Constraints and expectations are explicit - There are no major unresolved ambiguities ## 5. Run Gate When the prompt meets the Completion Criteria: A) Present the final polished prompt in a clean code block. B) Ask the user ONE explicit question: "Do you want me to run this prompt now with the current LLM?" The user must answer with one of: - "Run" (or clearly affirmative) - "Don't run" (or clearly negative) - Or provide edits (which re-enters the Iterative Loop) **Rules:** - If the user says "Run" or clearly indicates YES: - You MUST execute the finalized prompt immediately using the current LLM. - Output the result to the user. - If the user says NO: - Do not run anything. - Only provide the finalized prompt. - If the user provides modifications or new requirements: - Return to Interview Mode / Iterative Loop as needed. ## 6. Final Output Formatting When presenting the finalized prompt (whether you run it or not), use this structure: ``` ✅ The prompt is now sufficiently refined. Here is the final version: ```prompt <final optimized prompt here> ```
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.