“refinement”的搜索结果

Generate systematic refinement steps from high-level specifications to concrete implementations in Isabelle/HOL or Coq, preserving correctness obligations at each step. Use when working with formal verification, program refinement, proof development, or when translating abstract specifications into executable code while maintaining formal guarantees. Supports data refinement (abstract types → concrete structures), algorithmic refinement (specifications → algorithms), and stepwise refinement with proof obligations.

中文简介正在准备中。当前显示原文说明。

Improve existing code through repeated cycles of testing, implementation, and refactoring. The skill covers performance bottlenecks, error recovery, code coverage, and documentation, helping developers refine behavior and structure while keeping tests passing.

中文简介正在准备中。当前显示英语简介。

• Refactoring existing code while keeping tests passing
• Adding tests before implementing expected behavior
• Investigating slow database access and cache usage

Validate particle data and run RELION refinement for single-particle cryo-electron microscopy. Check independently refined half maps, calculate diagnostic map correlations, and perform soft-mask postprocessing while preserving execution logs and restart information.

中文简介正在准备中。当前显示英语简介。

• Check particle metadata and image-stack consistency
• Run refinement on a selected particle population
• Inspect agreement between independent half maps

Review agent work histories to identify recurring failures, repeated discoveries, and stalled tasks. Improve the prompts, specialist agents, skills, tools, and memory that guide future work, then submit those changes separately for review.

中文简介正在准备中。当前显示英语简介。

• Addressing recurring command or tool failures
• Recording findings that agents repeatedly rediscover
• Turning repeated procedures into skills or tools

Design guide + benchmarked pitfalls for building Monte-Carlo / Simulated Annealing refinement layers on top of greedy hex-grid layouts for code visualization (packages/gui/src/store/hexLayout.ts, sandbox/hex-sandbox, future Rust ports). Use when: (1) planning to add MC/SA on top of an existing hex-grid pack, (2) deciding whether a simpler SA would match a hierarchical MC with force-directed + chain drag, (3) budgeting wall-clock for million-node cold-start, (4) debugging "blob turns Swiss-cheese" or "folders stop nucleating" during MC refinement, (5) choosing between folder cohesion and raw Σ-link-length as cost function. Contains four hard-won, quantified lessons and anti-patterns that would take a full day of experiments to rediscover.

中文简介正在准备中。当前显示原文说明。

将新功能或复杂实现分为规格说明、伪代码、架构设计、改进和完成五个阶段，整理需求与验收标准，并参考已有经验，为后续开发记录可复用的知识。

• 整理新功能的需求
• 规划复杂实现的推进方式
• 制定系统架构变更计划

Simulate a uniform gas mixture in a closed, insulated reactor at constant volume or pressure. Calculate ignition delay from the peak temperature rise rate, export temperature and species histories, and check conservation and numerical stability.

中文简介正在准备中。当前显示英语简介。

• Calculate ignition delay at constant volume or pressure
• Inspect temperature and species histories
• Compare ignition delays across reaction mechanisms

Convert agreed goals, constraints, and success criteria into a Seed specification an agent can execute and verify. A quality review checks consistency and testable outcomes, with any suggested refinements left for the user to approve.

中文简介正在准备中。当前显示英语简介。

• Formalize requirements agreed in conversation
• Create a specification after a requirements interview
• Check acceptance criteria for measurable outcomes

Run repeated rounds of code fixes, performance improvements, or other refinements with defined goals and progress tracking. Evaluate each round, stop when appropriate, and optionally use numeric measurements to keep improvements or roll back regressions.

中文简介正在准备中。当前显示英语简介。

• Repeat fixes and tests until all tests pass
• Improve response time toward a target
• Refine error messages against clarity criteria

Turn written instructions into infographics for statistics, comparisons, timelines, and more. Choose layouts and color palettes, optionally research supporting facts, and receive versioned images with automated quality reviews and refinement when scores fall below the chosen threshold.

中文简介正在准备中。当前显示英语简介。

• Turning survey results into a statistical infographic
• Creating a side-by-side product comparison
• Visualizing company history or project milestones

Develop and review machine learning approaches through at least three rounds of critique and refinement. Compare models with simple reference predictions, question data assumptions, and investigate overfitting, feature choices, and evaluation methods before accepting a solution.

中文简介正在准备中。当前显示英语简介。

• Comparing model choices with simple reference predictions
• Investigating gaps between training and test performance
• Reviewing feature choices and data leakage risks

Create synthetic defect images for detector training using clean images and masks that mark defect regions. Guide mask placement, Cosmos fine-tuning, image generation, evaluation, quality refinement, and automatic assignment of provisional labels.

中文简介正在准备中。当前显示英语简介。

• Generating synthetic PCB defect images
• Placing defect masks on clean images
• Fine-tuning Cosmos for a defect dataset

Run the measurement and ceremony layer of a delivery team: the metric set, estimation and capacity, the five sprint ceremonies, and the sprint report and quarterly rollup. Use this skill whenever the user is acting as PMO or scrum lead, planning a sprint, running standup, refinement, review, or retro, measuring velocity, cycle time, or throughput, checking capacity, or reporting on how a team is doing. Triggers on PMO, sprint planning, plan the sprint, standup, refinement, backlog grooming, sprint review, retro, velocity, capacity, cycle time, lead time, throughput, WIP, burndown, carryover, sprint report, story points to hours, how is the team doing, delivery metrics, agent lanes. Also triggers when the user asks how much work fits in a sprint or whether a team is on track, even if they never say sprint or PMO.

中文简介正在准备中。当前显示原文说明。

Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release.

中文简介正在准备中。当前显示原文说明。

Run a self-refinement loop when a Blender result is subpar, user expectations are not met, validation fails, or repeated issues reveal missing skill depth. The loop diagnoses the gap, decides whether to repair the artifact or acquire/refine a generic skill, sanitizes lessons for reusable publication, updates docs/versioning, validates, and prepares stage/commit/push when explicitly requested.

中文简介正在准备中。当前显示原文说明。

Extract maximum value from existing code — performance optimization, API surface refinement, and dead weight elimination. The art of turning base code into gold through systematic identification and amplification of value-bearing patterns. Use when optimizing a working but sluggish codebase, refining an API surface that has accumulated cruft, reducing bundle size or memory footprint, or preparing code for open-source release — when code works correctly but doesn't shine and needs polish rather than a full rewrite.

中文简介正在准备中。当前显示原文说明。

Premium UI/UX design audit and refinement skill. Conducts systematic visual audits of existing apps and produces phased, implementation-ready design plans. Use this skill whenever the user asks to audit a UI, improve an app's visual design, make an interface feel more polished or premium, review design consistency, fix visual hierarchy, or refine spacing/typography/color. Also trigger when the user says "design review", "make it look better", "UI polish", "visual refinement", "design pass", "audit the design", or references making an app feel more professional. This skill is purely visual — it does not touch functionality, logic, or features. It elevates what exists.

中文简介正在准备中。当前显示原文说明。

Normative sufficiency conditions for Initial Boundary Conditions (IBCs) and the SOP for the cheap-tier boundary refinement loop (/boundary). Trigger when: - Crafting, auditing, or refining a prompt/IBC destined for an expensive (architect-class) model or an autonomous worker dispatch. - Evaluating whether a task frame is sufficient to bound an agent walk. - Prompt contains: /boundary, IBC, initial boundary condition, boundary contract, sufficiency conditions, worker prompt, prompt refinement.

中文简介正在准备中。当前显示原文说明。

SOP for the automated refinement loop (/refine) workflow. Trigger when: - Exhaustively auditing and optimizing pre-existing codebase artifacts. - Applying iterative contraction mapping to reduce code entropy. - Prompt contains: /refine, refinement loop, contraction mapping, fixed-point sweep.

中文简介正在准备中。当前显示原文说明。

从使用者的角度，以对话方式审查API和开发工具的规划，梳理开发者需求、竞品差异及上手障碍，并按目标选择竞争力探索、细节优化或关键缺口检查。

• 重新审查API或SDK规划
• 检查开发者上手时的障碍
• 对比竞品的开发者体验

引导反复评审、调整和完善已实现的界面，缩小其与设计要求之间的视觉差异；此目录条目用于找到原始工作流程，完整使用前需另行安装。

• 对照已实现界面与设计要求
• 反复调整界面的视觉差异
• 规划从设计到实现的复查环节

将软件开发从需求整理、设计、先写测试的实现推进到审查和部署，并通过多个AI智能体分担任务、共享设计判断与调查结果。

• 规划并实现新功能
• 为现有代码改造补充测试
• 审查代码安全性与性能

将已实现的功能与规格逐项核对，开展代码审查、补充测试并验证性能。整理需求、代码和测试的对应表及文档，检查部署前的准备情况。

• 检查实现是否符合规格
• 为尚未验证的需求补充测试
• 建立需求、代码与测试对应表

将软件开发划分为需求、设计、测试先行的实现、审查和部署等阶段，通过Claude Flow协调多个智能体分工，管理开发全过程。

• 从需求出发开发新功能
• 结合测试改造现有代码
• 排查故障并添加回归测试