Find functions that contain a particular sequence of opcodes. Use when you are having trouble decompiling a function and want to find similar already-decompiled functions to…
Opsgenie integration. Manage Alerts. Use when the user wants to interact with Opsgenie data.
OpsLevel integration. Manage data, records, and automate workflows. Use when the user wants to interact with OpsLevel data.
Diagnose the health of this project's AI agent setup. Use when the user asks to check, audit, or score the project's CLAUDE.md, skills, docs, or agent configuration.
OPSWAT integration. Manage data, records, and automate workflows. Use when the user wants to interact with OPSWAT data.
OpenSpec workflow management system for creating, planning, implementing, and archiving specification-driven development changes with comprehensive lifecycle management
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
Install or upgrade @reopt-ai/opt-chat in a consumer project. Not installed → initial setup (.npmrc, Tailwind, AI SDK, Conversation components).
Install @reopt-ai/opt-harness in a consumer project or upgrade it to the latest version. Not installed → initial setup (.npmrc, HarnessProvider, AppShell, first Workspace page).
Use for optimization — roots, smooth minimization (scipy), LP/MIP/convex models (HiGHS, CVXPY), IIS.
Drafts opt-out forms and notices of exclusion for class actions, settlements, arbitration clauses, and privacy programs.
Install @reopt-ai/opt-ui in a consumer project or upgrade it to the latest version. Not installed → initial setup (.npmrc, Tailwind CSS v4, OptThemeProvider, Surface CLI).
Opteo integration. Manage data, records, and automate workflows. Use when the user wants to interact with Opteo data.
Use when targeting Optica or deciding whether an optics-and-photonics manuscript fits this venue. Encodes the journal's fit, the high-impact concise-advance bar, measurement and…
MUST USE when a user asks to plan, brainstorm, design, scope, review, or evaluate a repo change before implementation; do not use for direct implementation-only requests,…
Помощь с Optimacros: синтаксис формул, проектирование модели, выбор между справочниками/свойствами/кубами, работа с версиями и временем, DCA, UAM/МДП, Workflow, доступы, скрипты и…
> Intelligence skill that identifies tax savings opportunities after the base computation is complete.
Analyse hooks daemon configuration and recommend improvements across Safety, Stop Quality, Plan Workflow, Code Quality, and Daemon Settings
Diagnose and fix EPUB ebook issues — metadata, TOC, footnotes, Kindle compatibility, style optimization for Chinese books (Pangu spacing, indent removal, ad filtering), font…
Use when tuning/optimising/"training" a skill's judge-shaped rubric (a single text document that makes a recurring, scorable decision) against outcome-labelled evidence — e.g.
Identify content strengths and opportunities for expansion. Suggests new topics and connections.
Implement immediate UI feedback for mutations with robust rollback capabilities.
Apply changes locally before the server confirms, then reconcile or roll back honestly when it does not. Use when latency makes a correct-but-slow interface feel broken.
Sistem ve akış optimizasyonu rehberi. 2025 AI-driven optimizasyon, darboğaz tespiti ve kullanıcı akış iyileştirmeleri. — from majiayu000/claude-skill-registry
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss.
Use BEFORE any cost/latency optimization. A/B control MUST be deployed prod config; gate code-start on stated $X/mo savings; reject forced-OFF controls.
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inferen — from…
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens — from…
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantizati — from…
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with — from…
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantizati — from…
When the user wants to combine machine learning with optimization, use ML predictions in optimization models, or integrate AI with mathematical programming.
Suggest concrete optimizations for Claude Code usage based on historical session data. Covers cost reduction, speed improvement, error prevention, and workflow efficiency.
Sistem ve akış optimizasyonu rehberi. 2025 AI-driven optimizasyon, darboğaz tespiti ve kullanıcı akış iyileştirmeleri. — from majiayu000/claude-skill-registry
Improve interface performance across loading speed, rendering, animations, images, and bundle size. Makes experiences faster and smoother.
Use Coze Loop to evaluate, debug, and improve agent prompts and workflows across development iterations.
Use Darwin Skill to evaluate, improve, test, and keep or roll back changes to a single agent SKILL.md with a validation-gated, human-reviewed optimization loop.
Analyze and reduce token consumption in agentic workflows — guardrail-specific entry points, measurement, and optimization techniques.
Create, audit, or prune AGENTS.md and CLAUDE.md files following current best practices. Use this whenever the user asks to set up, create, add, update, fix, clean up, restructure,…
Optimize AGENTS.md and rules for token efficiency. Auto-invoked when user asks about improving agent instructions, compressing AGENTS.md, or making rules more effective.
Analyze bundle size and performance metrics
Profile, diagnose, optimize, and validate AscendC competition operators on Ascend NPU environments. Use for CANN/AscendC kernels, Huawei operator contests, msprof timing,…
Optimize CLAUDE.md based on actual usage patterns. TRIGGER ON: 'optimize CLAUDE.md', 'improve CLAUDE.md', 'make CLAUDE.md better', 'trim CLAUDE.md', 'what is unused in CLAUDE.md',…
Otimiza código para melhor performance, eficiência de memória e velocidade. Use quando o usuário disser "este código está lento", "otimize isso", "reduza o consumo de memória".
Diagnoses and fixes Core Web Vitals (LCP, INP, CLS) and Lighthouse failures via image/font/JS strategy in the browser; used when pages are slow, janky, or failing a…
Optimize deep sleep configuration — remove wake blockers, configure RTC memory, reduce duty cycle, and profile power consumption.
The "Intent Link" that ensures seamless transition of strategy and context between specialized agents via a structured Handoff Bridge. — from designgrappler/agent-skills
하네스 전체 규칙을 5-test 게이트로 순회하여 토큰 제거 + 기능 동등성 보장. 최적화 후 evaluate-harness로 회귀 검증.
Daily optimization loop for the implement-queue workflow. Measures queue efficiency via the queueEfficiency sensor, appends a trend point, logs the run, and files de-duplicated…
Read the candidate's LinkedIn profile through the session browser, diff it against their targeting + evidence, and propose honest, evidence-backed rewrites of the headline / About…
Runs workflows for GPU/inference talks — Groq LPU latency, OSS inference stacks, MoE networking, serverless fine-tune, frontier cluster design, Devin agent infra, Gemma sizing.
Optimize slow React Router loaders by eliminating redundant DB queries, creating slim query variants, and parallelizing independent fetches.
For NP-hard optimization: TSP, scheduling, assignment problems. Uses greedy construction + local improvement (2-opt, hill climbing).
Optimize BigQuery compute costs by assigning Dataform actions to slot reservations. USE FOR managing which models use reserved slots vs on-demand pricing, updating reservation…
优化 subPages 演示页面中的样式，将硬编码的颜色、字号、间距、圆角等替换为 wot-ui 设计系统语义变量。允许直接使用已全局注入的 variable.scss Sass 变量，也允许使用 CSS 自定义属性；不需要额外引入 variable.scss。消除手写的暗色模式覆盖块，统一使用语义变量实现自适应主题。同时将 class 命名统一为 BEM…
Design your calendar and workflow to match priorities and decision-making capacity. Audit time spent vs stated values. Protect maker time and peak energy hours for deep work.
\"Apply current optimization techniques to improve prompt. 應用最新優化技術改善提示。 Use when: improving accuracy, consistency, creativity, speed, or safety of existing prompt.\
Use DSPy to define modular LLM programs, metrics, and evaluation sets so an agent can optimize prompts and pipeline behavior with measurable feedback instead of ad hoc prompt…
Optimizes prompts for goal effectiveness - ensures instructions serve the stated goal, prevents missteps, improves efficiency.
Iteratively optimizes prompts for precision - eliminates ambiguities, resolves conflicts, adds missing definitions.