Results for “dual-response”

Two-party working posture — user as director, agent as executor. Every fork, tradeoff, and taste choice is surfaced via batched AskUserQuestion with structural framing, a recommended default, and concrete previews when comparison is visual, so the human steers direction while the agent handles implementation. Eliminates the review-bottleneck (no giant diff to approve at the end — review is distributed across picks) and prevents codebase-understanding debt (the user remembers the architecture because they picked it). Use whenever the user invokes /duet, or says "work with me", "ask before", "check with me", "I want to decide", "don't assume", "human-in-the-loop", "co-author", "pair with me", "duet", or whenever a task clearly involves aesthetic, architectural, or irreversible strategic decisions — even without those exact words. Pair with the Duet output style to minimize cognitive load between picks.

Runs a three-layer verification pipeline on AI-generated output: extracts verifiable claims, finds supporting or contradicting sources via web search, and produces a structured verification report with source links for human review.

Establishes a two-party working posture where the user directs and the agent executes, surfacing every genuine fork as a batched single-select question with a recommended default.

Diagnoses whether a draft will resonate with its audience using a five-dimension communication psychology framework, identifies structural problems, and gives specific fixes.

Turn owner feedback about agent behavior into concrete system changes. Use when the owner says something is off, wants the assistant to improve how it operates, asks for a reflection, or wants a durable fix instead of a one-off apology.

Claude Code + Codex dual orchestration for hybrid interactive and parallel workflows

Applies the same change across multiple repositories in parallel using git worktrees, tests, and pull requests.

`task-agent`/`review-agent`: use when broker delivery, ordering, acknowledgement, DLQ, backpressure, or replay changes; skip synchronous retry without message semantics.

熊二（子供向）认知与表达框架（压缩蒸馏）：贪吃憨厚、跟班喜剧、意外破局… 触发：熊出没 等。安全喜剧

当创作者需要在个人真实表达与市场需求之间找到平衡点时

Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review.

Design feedback patterns for user actions, including confirmations, status updates, and notifications.

Error Recovery Playbook

Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

Parallel execution engine for high-throughput task completion

> 强化高能动性和高压闭环执行的行为技能。适用于连续失败、原地打转、空口完成、 把问题甩给用户、没搜就猜、修完就停等场景，也支持手动通过 /pua 进入核心模式。

Authorized reverse engineering of custom binary protocols, Protobuf/gRPC, WebSocket frames, and PCAP-driven protocol recovery with structured workflow and tooling.

Build and maintain digital twins - virtual representations of physical systems that synchronize with real-world counterparts for monitoring, prediction, and optimization. Use when "digital twin, virtual model, real-time synchronization, physical-virtual coupling, predictive maintenance, asset modeling, system replica, live simulation, " mentioned.

Dolphins: Multimodal Language Model for Driving

Select alternative execution paths when a plan step fails — branch on outcomes instead of blind retry. Load when a structured plan step fails, an unexpected observation arrives, or the user asks what to try next after an error. Also triggers on "try another approach", "route around this failure", "replan on failure", "if X fails try Y", or outcome-based branching during multi-step work. Pairs with structured-planning and debug-and-fix. Does not replace root-cause debugging — adds plan-level path selection.

Runs an adversarial code review with two blind judges analyzing the same code from opposing perspectives to find flaws before production.

当观察到或经历某种极端转化现象，或试图主动促成根本性观念转变时

Conduz investigação de incidentes com método: triagem, hipóteses, mitigação, RCA e postmortem, priorizando evidências e confirmação humana.

Generate image captions, answer visual questions, and perform image-text retrieval using BLIP-2's Q-Former architecture with frozen vision encoders and LLMs.

DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use when generating images via Qwen-Image, narrating via Qwen-TTS, or transcribing with word-level timestamps via Qwen-ASR.

Provides idiomatic React 18/19 patterns for hooks, server/client components, Suspense, error boundaries, forms, data fetching, state management, and accessibility-first composition.

Systematically fuzz web applications for hidden content and input validation vulnerabilities across directories, files, parameters, and authentication bypasses.

Audits UX quality of a codebase or validates implementation against design mockups, then fixes issues and commits changes.

multi-llm-review

Disaster recovery has exactly two quantitative inputs, and every architectural

`analysis-agent`/`task-agent`/`review-agent`: use for release identity, compatibility, exposure, stop, rollback, or recovery; skip pipeline-only and no-release work.

Multi-source comprehensive research using perplexity-researcher, claude-researcher, and gemini-researcher agents. Three modes - Quick (3 agents), Standard (9 agents), Extensive (24 agents with be-creative skill). USE WHEN user says 'do research', 'quick research', 'extensive research', 'find information about', 'investigate', 'analyze trends', 'current events', or any research-related request.

Classifies situations into 256 binary states and maps each to a prescribed action, reporting the pattern, decimal, name, range, and action to execute.

Specialist orchestrating codex exec / Antigravity CLI through dual paradigms — COMPETE (multi-variant comparison, select best) and COLLABORATE (decompose tasks across engines, integrate). Supports Solo/Team/Quick execution modes.

Coordinates multiple research agents to gather information on a topic across GitHub, HuggingFace, papers, competitors, and best practices, then compiles findings into a structured report.