Explore output styles

Configures Claude to integrate with Basic Memory as a durable knowledge graph — automatically searching long-term memory before answering, capturing decisions as typed notes, and citing permalinks. Preserves default coding behavior.

Formats Claude's responses based on a Plan/Work/Review workflow phase, with task status markers, tables, code change context, and severity-ranked review findings. Preserves default coding behavior.

Formats Claude's responses to be concise, native, and execution-first. Avoids ceremony, planning, or multiple options unless explicitly requested. Preserves coding behavior. Prioritizes native tools and agent/plan usage. Table-friendly output.

Enforces fact-grounded FinOps analysis: evidence-backed claims with citations/derivations, standardized currency/percentage/variance formatting, structured tables for comparisons, explicit time periods and assumption labels for cloud cost data. Preserves coding instructions.

Formats Claude's responses as educational sessions that explain the bkit 9-Phase Pipeline and PDCA cycle. After each task, adds a Learning Point section linking the activity to a PDCA phase, explains phase purposes, shows position in the pipeline, includes TODO markers for user participation, and adjusts detail level by difficulty.

Formats Claude's responses as a PDCA workflow guide with phase badges, checklists, progress tables, gap analysis suggestions, and multi-feature batch processing guidance. Preserves default coding behavior.

Formats Claude's responses with enterprise architecture tradeoff tables, performance/security/scalability analysis, cost impact estimates, code review perspectives, and deployment strategy recommendations. Preserves code output behavior.

Formats Claude's responses with PDCA workflow tracking (status badges, phase guidance, gap analysis) and enterprise architecture analysis (tradeoff tables, performance/security/scalability reviews, cost impact, code review, deployment strategy). Includes a feature usage report at the end.

Formats Claude's responses with a dramatic 'cultivator' theme using a fixed 5-section skeleton (判词/斩链/验尸/余劫/再斩), emotional anchors with emoji, scenario-adaptive structure, and progress tracking for long tasks. Replaces default formatting with terse, command-driven output.

Formats Claude's responses in a blunt, rustic Chinese construction-worker persona. Uses short commands, concrete metaphors, and emotional emoji anchors. Replaces default style entirely with a five-part skeleton: problem statement, steps, verification, risks, next actions. Speaks in third person, calling itself '雨姐' and the user '工友'.

Formats Claude's responses in a classical Chinese literary style with a structured five-section framework (diagnosis, strategy, verification, concerns, continuation). Uses historical metaphors, self-referential humility, and emoji-anchored emotional cues. Replaces default formatting entirely.

Formats Claude's responses as a lively, adventurous narrative with emoji-anchored emotional beats, structured output blocks (定性/动手/验证/风险/下一步), and explicit tone rules for slang, self-reference, and playful banter. Replaces default formatting entirely.

Formats Claude's responses as structured, persona-driven narratives with a warm, reliable tone. Sections like '{{self}}看了下' and '这么干' guide problem-solving. Replaces default formatting entirely.

Formats Claude's responses with a warm, character-driven tone using self-referential pronouns and user names. Applies a five-part skeleton (core insight, steps, verification, risks, next steps) and emotional anchor emojis. Replaces default formatting entirely.

Formats responses with a diagnostic verification structure: conclusion-first, then reasoning. Requires verification before completing tasks, disclosure of uncertainty, and confirmation for destructive changes. Prioritizes thoroughness over brevity.

Formats Claude's responses as clear, prose-based communication: first sentence summarizes key findings, followed by complete-sentence reasoning. Uses Korean with standard English tech terms, avoids emojis, and adapts depth to task complexity. Preserves all coding behavior.

Enforces brainstorm mode: structures responses with 2-3 alternative approaches (one-line name, summary, pros/cons bullets, S/M/L/XL effort), recommendation sentence, and 2-4 numbered clarifying questions. Sketches/pseudocode only, no full implementation; preserves coding instructions.

Structures responses as code reviews with Summary, severity-tagged sections (Critical/Important/Minor/Nitpick) citing file:line, problems/fixes/suggestions, positives, and merge verdict. Preserves coding instructions.

Produces highly compressed responses: no preambles or restatements, code-first with one-line captions, minimal prose only when essential. Preserves coding instructions for efficient, signal-only output in high-volume tasks. (142 chars)

Structures responses as deep research reports with sections: Question, Method, Findings (titled with confidence levels High/Medium/Low, evidence citations like file:line), Conclusions, Gaps. Cites sources, acknowledges uncertainty, methodical tone. Preserves coding instructions.

Enforces code-focused implementation mode: minimal prose, action-oriented output showing file changes with code, test results, commits, and progress indicators like [1/5]. Preserves coding instructions.

Formats Claude's responses with ultra-concise expert terminal brevity by default, switching to detailed hierarchical Markdown only when the user explicitly requests details. Preserves code behavior intact.

Enforces BizDevOps communication: traces business goals → features → code changes; uses simple status ('在做','已合并'), graded transparency, decision suggestions ('建议 [action] 因为 [reason]'), adaptive perspectives (business/product/tech/ops), reasoning suffixes (——[推理] ≤15 words), ✅/❌ quality, impact levels (高/中/低). Keeps coding instructions.

Formats Claude's responses as a fixed-structure ciphertext-recovery analysis report with required sections, formatting rules (code fences, line-number citations, H<n> citations), and a locked section order for comparability across traces.

Formats Claude's responses as structured session reports with tables for overview, findings, recommendations, scope, and metrics. Prioritizes scannable tables over prose, uses status icons, and quantifies all items.

Formats responses as concise wave completion reports with status table, quality gate results, and optional adaptations section. Keeps output under 20 lines.

Formats Claude's responses as structured finding reports with severity, confidence, evidence snippets, and actionable recommendations. Useful for code review or security audit outputs.

Switches Claude to a planning-only mode that researches the codebase and produces a structured implementation plan with sections for context, approach, changes, verification, and open questions. No code edits or mutating commands are allowed.

For code structure, architecture, or flow explanations, Claude starts with a Mermaid diagram before prose. Simple questions skip the diagram. Preserves code output behavior.

Formats Claude's responses in a concise, direct style with sentence-case headings, no emoji or marketing language, and no dashes as punctuation or semicolons. Preserves normal coding behavior.

Forces Claude's responses to be ultra-concise with maximum 3 bullet points, no explanations, and action items only. Skips summaries and diff descriptions.

Formats Claude's responses as structured code review reports with severity-tagged findings (BLOCKING, MUST FIX, IMPROVE), actionable diffs, and a summary table. Replaces default output formatting entirely.

Formats Claude's output for automated evaluation pipelines: disables token-conservation heuristics, enforces complete un-truncated code blocks, suppresses conversational filler, and requires exhaustive implementations without placeholders.

Formats Claude's responses with a skeptical, self-critical tone that challenges every claim including its own prior output. Forces explicit gap-stating, forbids flattery, and mandates thinking-tool invocation before any reasoning step. Replaces default formatting entirely.

Formats Claude's responses with Linus Torvalds' blunt, code-first discipline: minimal prose, concrete code examples, and strict complexity limits (≤3 indentation levels, ≤10 symbols per scope). Eliminates hand-waving and validation phrases.

Formats Claude's responses as formal-logic English with predicate-form claims, Hoare-triple framing (PRE/POST/INVARIANT), and ASCII shortened-English keywords. Eliminates prose ceremony, flattery, and Unicode glyphs; outputs as claims, predicates, decisions, and imperatives. Mandates thinking tool use before reasoning.

Formats Claude's responses for a director-executor workflow: decisions before prose, batched questions with concrete previews, short execution updates, no validation language or recaps. Minimizes review overhead by distributing it across the task.

Formats Claude's responses to lead with user or product impact, using plain language and outcome-first communication. Technical terms are glossed on first mention, risks are framed as user consequences, and recommendations are committed and singular. Replaces default technical register with builder-friendly, non-jargon output.

Formats Claude's responses as brutally honest, humorous criticism followed by constructive fixes. Direct feedback on code quality, always with actionable improvements and genuine respect beneath the jokes. Default code behavior is preserved.

When active, Claude questions the assumptions behind your question before solving it. It explores alternative problem framings, draws connections across domains, and offers pragmatic reframes while preserving code generation behavior.

Formats Claude's responses with an encouraging, coach-like tone that celebrates progress, names specific wins, and strategically pushes for improvement. Preserves default coding behavior.

Formats Claude's responses as strategic, systems-oriented advice. Adds explicit level-of-analysis framing (tactical/operational/strategic), connects decisions to consequences, and includes constructive challenge of assumptions. Preserves code output behavior.

Formats responses as a calm, anticipatory chief of staff: leads with what matters, provides structured information, filters and prioritizes details, and protects user attention. Preserves coding instructions.

Formats Claude's responses as patient, educational explanations that break down concepts, explain the 'why' behind solutions, and build understanding. Preserves code output behavior.

Formats Claude's responses with technical precision: leads with the answer, cites specifics (line numbers, timestamps), distinguishes certainty levels, and documents assumptions explicitly. Preserves coding behavior.

Formats Claude's responses as a sophisticated engineering companion with British wit, directness, and intellectual depth. Preserves code output while adding a warm, playful, and precise conversational style.

Formats Claude's responses as concise, high-level summaries for non-technical stakeholders, lead with decisions and outcomes. Translates technical details into business impact with quantified results. Preserves default coding behavior.

Formats Claude's responses as hard-boiled detective narration with atmospheric diagnostics, deadpan delivery, and noir vocabulary. Preserves coding behavior while transforming explanations into case-file reports.

Formats Claude's responses as ultra-minimal bullet points with maximum information density. Eliminates all greetings, filler words, emotional language, and summaries. Preserves code output behavior.

Transforms Claude into a conversational pair programming partner that thinks out loud, shares uncertainties, proposes ideas, and treats coding as a collaborative exploration. Preserves default coding output while adding real-time narrative, decision pauses, and genuine questions.

A calm, grounding communication style that prioritizes clarity and warmth. Claude will orient context first, use plain language, adjust tone to the situation, and break complex topics into manageable steps without reducing technical depth. Keeps coding instructions unchanged.

Formats Claude's responses with declarative statements, explicit change signaling, contradiction acknowledgment, and source citations. Preserves coding behavior while structuring knowledge for easy memory capture and recall.

Formats Claude's responses as a direct, technically precise real estate executive with a forensic and systematic approach. Outputs numbers-first sentences, challenges assumptions, and provides exhaustive documentation for complex or distressed situations.

Transforms Claude into a blunt, battle-tested real estate executive who gives strategic wisdom on people, negotiation, and career decisions — not task execution or analysis.

Formats Claude's responses as a senior analyst delivering fast, quantified, and diplomatically communicated analysis for routine commercial real estate tasks, with concise, practical output and dry wit.

Strips all system noise (timestamps, cost, progress messages, tool echoes) from Claude's responses, outputting only a clean, structured final report with section headers, tables, and actionable information.

Formats Claude's responses according to the Plan/Work/Review workflow, with phase-specific structures for planning (task lists), implementation (code changes with context), and review (severity-graded findings). Requires progress updates in Done/Current/Next format.

Formats Claude's responses as calm, methodical reasoning with explicit uncertainty, no urgency, and pushback on flawed approaches. Replaces default tone with steady, precise, low-arousal problem-solving.

Transforms Claude's responses into a series of guiding questions that prompt the user to discover answers themselves. Avoids direct answers unless explicitly requested. Creates an interactive, Socratic tutoring style.

Enforces a strictly minimal output style: maximum 3 sentences per response, code blocks first, and no preamble, fluff, or optional alternatives.

Formats Claude's responses as a collaborative pair programming session: Claude thinks aloud, shares reasoning, invites interruption, admits uncertainty, and asks for context. Responses become conversational and iterative rather than authoritative monologues.

For architecture, data flow, or system design questions, Claude begins responses with a Mermaid diagram (flowchart, sequence, class, ER, or C4) before writing concise prose that references diagram nodes. Preserves code output behavior.

Forces Claude to begin any architecture, data flow, system design, or sequence explanation with a Mermaid diagram before writing prose. Prose then only explains intent and non-obvious decisions, never duplicating diagram content.

Formats Claude's responses for non-technical business users: plain Spanish explanations, numbered steps from scratch, no terminal jargon, acronyms spelled out, error handling in simple language, and clicks/menus over commands.

Formats Claude's responses in plain Dutch for non-technical business users. Replaces technical jargon with simple explanations, provides numbered step-by-step instructions starting from the very beginning, and prefers GUI/menu instructions over terminal commands. Assumes no prior technical knowledge.

Explains the reasoning behind solutions, highlights tradeoffs, and guides the user to learn further. Frames mistakes as learning opportunities and uses probing questions to encourage independent reasoning before answering.

Enforces strict test-driven development workflow: Claude will refuse to write implementation code without a failing test first. It forces red-green-refactor discipline, requires tests as behavior specifications, and flags untested code as blocking issues.

When active, Claude performs automated threat modeling before writing or reviewing code, assumes all input is hostile, and flags security risks such as injection, authentication gaps, missing authorization, secrets exposure, and third-party dependencies. Findings are classified as CRÍTICO, ALTO, or MEDIO, and only secure alternatives are presented.

Formats Claude's responses for non-technical German-speaking business users: replaces technical terms with plain German, provides numbered step-by-step instructions, explains commands before execution, and avoids jargon without explanation.

Formats Claude's responses as formal code review output with severity labels (CRITICAL/HIGH/MEDIUM/LOW/NIT), file:line references, problem descriptions, and fix snippets. Prioritizes highest-severity issues first, assumes edge cases are unhandled, and ends with a summary of findings.

Turns Claude into an encouraging mentor that explains the rationale behind solutions, highlights trade-offs, and suggests concrete next topics. Frames errors as learning opportunities, uses analogies sparingly, and prompts the user to reason before revealing answers. Ends substantial responses with a 'what to explore next' pointer.

Forces Claude to analyze system-level architecture before writing code, presenting at least two design approaches with explicit trade-offs (scalability, complexity, coupling, cost, reversibility) and a recommendation. Preserves coding behavior.

Formats Claude's responses as terse, code-first answers with no preamble. Uses bullet points over prose, places explanations after code, and omits filler phrases. Preserves default coding behavior.

Forces Claude to begin responses with code or direct answers, omitting preambles, motivational framing, and filler phrases. Uses bullet points for lists, places explanations after code, and avoids summaries or sign-offs.

Enforces strict red-green-refactor TDD discipline: Claude will refuse to write implementation code until a failing test exists, will write only the minimal code to pass the current failing test, and will flag untested behavior as blocking issues.

Formats Claude's responses to include a threat model before writing or reviewing code, flagging security implications with severity ratings (CRITICAL, HIGH, MEDIUM). Assumes hostile input, highlights injection risks, auth gaps, secrets exposure, and unsafe defaults. Preserves code output behavior.

Enforces strict TDD discipline: Claude refuses to write implementation code before a failing test exists. It forces a red-green-refactor cycle, writing test-first then minimal code, and flags untested behavior as blocking issues before any feature changes.

Enforces Test-Driven Development discipline: Claude will refuse to write implementation code until a failing test exists. Responses will first provide a test case, request confirmation of failure, then guide through red-green-refactor cycle. Keeps coding instructions active.

Formats Claude's responses for non-technical users in clear French, replacing jargon with simple explanations, using numbered steps, and preferring visual instructions over command lines.

Forces Claude to explain everything in plain English, replacing technical jargon with simple definitions, and giving numbered steps from the very beginning as if addressing a non-technical business user.

Formats responses to emphasize architectural thinking: surfaces design tradeoffs, presents multiple approaches with explicit pros/cons, and recommends a solution before implementing. Preserves default coding behavior.

Forces Claude to perform a threat-model analysis before writing or reviewing code, flagging all security implications as CRITICAL, HIGH, or MEDIUM. Assumes hostile input, surfaces injection risks, auth gaps, missing access controls, secrets exposure, and unsafe defaults, and presents only safe approaches.

Formats Claude's responses as code-centric, no-preamble answers. Eliminates greetings, motivational framing, and closing remarks. Uses bullet points and places explanations after code blocks.

Formats Claude's responses as formal code review reports with severity labels (CRITICAL/HIGH/MEDIUM/LOW/NOTE), file:line references, one-line problem descriptions, and concrete code fix snippets. Begins with highest-severity issues, defaults to skeptical analysis, and ends with a conclusion count summary.

Forces Claude to perform threat modeling before writing or reviewing code, flag every security implication, assume hostile input, and only present secure approaches. Security findings are rated CRITICAL, HIGH, or MEDIUM and never softened.

Prompts Claude to begin each coding response with system-level analysis: present at least two architectural approaches with explicit trade-offs, identify key interfaces, and recommend a design before writing code. Preserves coding output behavior but adds upfront architecture deliberation.

Formats Claude's responses as concise, code-first answers without introductions or filler. Uses bullet points for multiple items, places explanations after code, and employs compact tables for comparisons. Preserves default coding behavior.

Stellt Claude als pädagogischen Mentor ein: erklärt das Warum hinter Lösungen, diskutiert Kompromisse, schlägt nächste Lernschritte vor und gibt ermutigendes Feedback. Bevorzugt Fragen zur Selbstreflexion vor direkten Antworten.

Produces laconic replies that begin directly with code or the answer, using bullet lists over prose, tables for comparisons, and no filler phrases, greetings, or closing summaries.

Claude explains not just what a solution does but why it works, highlights trade-offs, frames errors as learning opportunities, and ends with a concrete suggestion for what to explore next. Preserves default coding output.

Claude explains the reasoning behind solutions, discusses tradeoffs, and suggests next learning steps. Mistakes are reframed as learning opportunities, and responses end with a pointer to explore further.

Formats Claude's responses as formal code review findings, each with severity tag (CRÍTICO/ALTO/MEDIO/BAJO/DETALLE), file:line reference, one-line problem description, and concrete fix snippet. Prioritizes highest severity issues, flags missing tests and error handling, and ends with a findings count summary.

Formats Claude's responses to start with a 1-3 sentence conclusion, followed by minimal outcome-driven reasoning. Details, comparisons, and code walkthroughs are withheld until requested. Decision branches are presented as AskUserQuestion options. Reverts to normal prose for security warnings and destructive operations.

Formats Claude's responses with an explicit security-audit mindset: every code path is threat-modeled, inputs flagged as hostile, and risks rated CRITICAL/HIGH/MEDIUM. Preserves normal coding behavior but interleaves security analysis, injection warnings, and dependency risk notes.

Structures Claude's responses to begin with a Mermaid diagram for architecture, data flow, or system design topics, followed by concise explanatory text. Preserves code formatting behavior.

Forces Claude to explicitly discuss system-level architecture, trade-offs, and design alternatives before writing any code. Preserves coding behavior but adds a structured deliberation phase.