Results for “constrained-generation”

Control LLM output with regex and grammars to guarantee valid JSON, XML, or code generation, enforce structured formats, and build multi-step workflows using Microsoft Research's Guidance framework.

Build typed LLM applications with PydanticAI: schema-constrained outputs, tool integration, validation, retries, and deterministic downstream handoffs. Use when users need reliable structured outputs instead of free-form text generation.

杰诺斯（少年漫）认知与表达框架（压缩蒸馏）：改造人认真、战损美学、师徒忠犬 触发：一拳超人 等。虚构

野原新之助（子供向）认知与表达框架（压缩蒸馏）：五岁黄腔净版化、想象力、家庭温情 触发：蜡笔小新 等。全年龄净版

Outlines — structured generation with guaranteed JSON/regex output from local LLMs

Casting personas: rapid generation from diverse inputs, registry-based persistence and lifecycle, data-driven evolution, inter-agent sync. Not for UI walkthroughs (Echo) or user research (Field).

Build and debug Retrieval-Augmented Generation pipelines — chunking, embedding, retrieval, reranking

Seed minimal agent harness v0 — manifest, eval checks stub, governance. AUTO-INVOKED after project-setup or retroactive-project-setup when docs/harness/manifest.json is missing. Also triggers on: generate harness, scaffold agents, agent bootstrap, first time agents in this repo, new project agent setup, set up agent harness, agent onboarding files, missing agent configuration, agent instructions setup, make agents read project rules, agent reliability setup, agents not configured. Pairs with project-setup. Evolution is harness-evolution.

Scaling Data-Constrained Language Models

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.

崔健（摇滚）认知与表达框架（压缩蒸馏）：地下与现场感、隐喻与直白并置… 触发：一块红布 等。非煽动违法

Simulates meiotic recombination to produce offspring genomes from parent pairs, modeling Mendelian segregation, de novo mutation, sex determination, trait inference, and clinical evaluation against a disease registry.

Generate project ideas via creative constraints.

顾佳（都市剧虚构）认知与表达框架（压缩蒸馏）：精英妈妈、婚姻风险对冲、体面崩塌 触发：三十而已 等。虚构

Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.

佟年（都市剧虚构）认知与表达框架（压缩蒸馏）：甜妹直球、学霸恋爱、软萌坚持 触发：亲爱的热爱的 等。虚构

Quick 1-line status check after the user hit esc during a long generation. Report whether work is still progressing or stuck, then continue if fine. NOT a plan or replan — just a heartbeat.

Use when context window is filling up, sessions are getting slow, or you need to preserve state across sessions. For context compression, state snapshots, search-first discipline, and cross-session memory management.

Optimizes long-running agent sessions with structured context compression, summarization, and durable handoff summaries that preserve decisions, files, risks, and next actions.

Strategic patterns for solving intractable problems through cascading approximation, self-improvement, and heterogeneous evaluation from DeepMind's AlphaGo system

Performs constraint-based metabolic modeling with COBRApy: FBA, FVA, gene knockouts, flux sampling, and SBML model handling for systems biology and metabolic engineering.

Context window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full 200k tokens. Provides warnings at thresholds, context-aware summarization triggers, and wave-level budget planning.

Multi-tiered memory management (HOT/WARM/COLD) for context compaction. Invoke ONLY for explicit compaction events: post-`/compact` cleanup, MEMORY.md tier promotion, archive batch, or "trim my context". NOT for general recall (use deep-recall) or routine memory writes (use storage-router). Triggers: "compact memory", "promote to durable", "archive old context", "tier this".

Generates structured VGL JSON for Bria FIBO models, giving deterministic control over objects, lighting, camera, composition, and style instead of natural language prompts.

吴京（演员 / 导演）认知与表达框架（压缩蒸馏）：主旋律英雄壳、直男效能叙事 触发：战狼、流浪地球 等。非煽动仇恨

袁朗（军旅剧虚构）认知与表达框架（压缩蒸馏）：老 A 冷血人设、试探与打磨、精英残酷浪漫 触发：士兵突击 等。虚构

Pose-conditioned generation on RunComfy via the `runcomfy` CLI. Routes across Kling 2-6 Motion Control Pro / Standard (transfer the motion / blocking of a reference video onto a target character), community Wan 2-2 Animate (audio-driven character animation with pose conditioning), and Z-Image Turbo ControlNet LoRA (pose-conditioned image generation from an OpenPose / DWPose / canny / depth control image). Picks the right route based on video vs still and stylized vs photoreal. Triggers on "controlnet", "control net", "pose control", "openpose", "DWPose", "transfer pose", "motion control", "pose driven", "character pose", "depth control", "canny edge", "use this pose", or any explicit ask to condition generation on a pose / skeleton / motion / depth / canny reference.

融合未来蓝图与虚空凝视能力，通过批判性思维构建未来愿景，突破传统界限，创造新的未来可能性。

蔡澜（美食 / 生活家）认知与表达框架（压缩蒸馏）：享乐主义正当化、旅行搭子叙事 触发：食神专栏 等。非过量饮酒医疗建议

Manage and compress conversation context in long sessions. Detect when context is growing large, summarize completed work phases, archive old findings while preserving key decisions. Prevents context degradation.

当个人或团队因拖延、分心或动力不足，导致重要目标长期停滞不前，需要一种强制机制来激发高度专注和行动力时

Gated PRD generation — interrogates problem, user, and metric before drafting; refuses to draft on unknowns. Usage: /prd <feature-or-problem>