413건 · 관련도순
Retrieve compacted ReasoningBank context for cost-analysis queries and summarize retrieved memories, reported token savings, cache hit rate, and package availability. The savings figure is an estimate from the integration, not a measured comparison against a baseline.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Investigate database slowdowns and plan measurable improvements to queries, indexes, caching, and scaling. The skill covers SQL and NoSQL systems, with guidance on monitoring, load testing, migrations, and balancing performance against cost.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Create blog posts and social media content with a consistent brand voice, meaning a recognizable writing style. Includes tools for analyzing existing text and suggesting search optimization improvements, plus templates for adapting content and planning publication calendars.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Improve an existing skill’s instructions using benchmark tasks that measure its output. Generate starter tasks, preview costs, and keep version history, with validation checks deciding whether proposed edits can replace the current instructions.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Review Doris code changes using project-specific checklists for data correctness, concurrency, memory safety, compatibility, performance, and tests. Trace related code paths and explain findings with concrete failure scenarios, using query plan trees when reviewing optimizer behavior.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Deploy code changes to a live hero training run by starting a new run from a permanent checkpoint, a saved training state. Compare matching training steps against agreed criteria and roll back if the trial fails.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when the user asks to "plan my paid account structure", "pick Search vs PMax", "lay out ad groups / asset groups", or "audit paid-vs-organic cannibalization"; designs campaign-type selection, ad-group/asset-group layout, targeting + match types, negative/exclusion hygiene, and a paid↔organic overlap audit, and scores the ROAS A (Audience) dimension + structure. Not for computing the final RQS — use ad-account-auditor; not for budget split — use budget-optimizer; not for organic site architecture — use site-structure-optimizer. 付费广告账户结构/广告系列规划/否定关键词
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
SkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Expert database optimizer specializing in modern performance tuning, query optimization, and scalable architectures. Masters advanced indexing, N+1 resolution, multi-tier caching, partitioning strategies, and cloud database optimization. Handles complex query analysis, migration strategies, and performance monitoring. Use PROACTIVELY for database optimization, performance issues, or scalability challenges.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
SPIRV-Tools optimizer pass development, IR manipulation, PassTest registration, and LuisaCompute spvtools::Optimizer integration (presets, LUISA_SPIRV_OPT_* env knobs).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Analyze a software codebase for algorithmic complexity and performance hotspots, then propose or implement safe optimizations without breaking behavior. Use when Codex is asked to scan many files, find inefficient loops, nested iteration, repeated scans, costly rendering/recomputation, N+1 queries, avoidable O(n^2) or O(n) operations, or reduce complexity such as O(n^2) to O(n log n) / O(n), while preserving tests, APIs, outputs, and maintainability.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Write SEO-optimized blog posts, landing pages, and long-form page copy following Google's E-E-A-T and Helpful Content guidelines. Handles new content creation from a keyword, topic, or brief, and full-page rewrites. Use when asked to "write a blog post", "create a landing page", "write content about X", "content for keyword X", "draft an article", "blog post about", "landing page for", "service page", "product page copy", "rewrite this page", "how-to guide", or "listicle". NOT for analyzing/auditing existing content (seo-geo-optimizer, content-quality-auditor), title tags or meta descriptions (meta-tags-optimizer), or keyword expansion (keyword-research) — those skills own their triggers.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
ENHANCE overlay on [[dspy]] — the upfront rubric for choosing a reasoning SHAPE (Predict / ChainOfThought / ReAct / ProgramOfThought) BEFORE you write a prompt or pick an optimizer. The local `dspy` skill lists the modules but never surfaces the *selection criterion*: reasoning shape is chosen by task structure, not by reflexively defaulting to CoT. Activate every time a new LM-calling node/step is added to a pipeline. Do NOT activate for one-shot prompts, optimizer/teleprompter choice (that is the dspy SOP's job), or non-LM control flow. Search keywords: chain of thought vs ReAct, when to use CoT, reasoning type, ReAct vs CoT vs PoT, which dspy module, predict vs chain of thought.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Decision rubric for promoting a prose prompt into a typed DSPy Signature. This is an ENHANCE overlay on top of the [[dspy]] library skill: it does NOT teach DSPy syntax — it answers the coder-agent decision "when do I stop hand-writing a prompt string and declare it as a `dspy.Signature`, and how do I name/describe its fields so the optimizer and the calling code both get a clean contract." Activate when: a prompt string grows past ~50 lines; the LM output is consumed by code (parsed, branched on, stored) rather than read by a human; the same prompt is reused across >1 call site; or a teammate asks "should this be a Signature?". Do NOT activate for one-shot throwaway prompts, or for HOW-TO questions about DSPy modules /optimizers/compile — defer those to the [[dspy]] skill and the [[agentsop-dspy]] workflow skill. Search keywords: typed prompt, structured prompt, DSPy Signature, prompt as a function, prompt contract, when to formalize a prompt.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Route AI-Optimizer reinforcement-learning collection tasks across model-based RL, easy-MARL, offline RL, safe command builders, and repository limitations.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Optimize DSPy programs with dspy.GEPA — a reflective/evolutionary optimizer to consider against task-specific baselines within an authorized evaluation budget. Use when the user says optimize, compile, GEPA, reflective optimization, or "make this program better" and a DSPy program + metric + trainset exist.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
基于目标岗位 JD、中文简历和用户确认的真实经历，完成中国大陆求职场景下的 JD 解析、证据映射、缺口诊断、素材追问、定制简历重写、ATS/HR/面试官审查及投递沟通材料生成。用于应届、社招、转行及互联网、AI、产品、运营、销售、技术、数据、设计等岗位；当用户要求针对 JD 优化中文简历、提高匹配度、生成 Boss 直聘或猎头话术、检查面试自洽性时使用。
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
DSPy is a Python framework from Stanford NLP that replaces hand-written prompts with code: you declare LLM tasks as typed signatures, compose them into modules, and let optimizers (BootstrapFewShot, MIPROv2, GEPA) tune the prompts and few-shot examples against your metric. Use when the user asks about DSPy, signatures, ChainOfThought, ReAct, teleprompters or optimizers, or wants to stop hand-tuning prompts.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Optimize a site or app for SEO, AI-bot search and app-store search in one run: detect web vs store, run each audit once, merge one prioritized report; fixes only via member gates. Don't use for one fix (seo-ai-optimizer, aso-marketing).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Improve a Hinge dating profile through research-backed screenshot audits, photo selection and ordering, conversational discovery, prompt and caption writing, settings review, or post-launch troubleshooting. Use for a full profile rebuild or a focused request about photos, copy, positioning, match quality, or profile performance.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Add a new single-objective optimization algorithm to the sci-comp library. Use when the user asks to implement a new optimizer (e.g. gradient descent, BFGS, simulated annealing, differential evolution).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design and operate multi-agent orchestration patterns (ReAct loops, evaluator-optimizer, orchestrator-workers, tool routing) for LLM systems. Use when building or debugging agent workflows, tool-use loops, or multi-step task delegation; triggers: agentic, multi-agent, orchestration, ReAct, evaluator-optimizer, tool-use, handoff.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Audit and rewrite a YouTube channel end-to-end for 2026: name and @handle, banner (2560x1440 with the 1235x338 mobile/TV safe area), profile picture, About plus searchable keywords, trailer for non-subscribers vs featured video for subscribers, sections and playlist layout, watermark, links. Triggers on "optimize my YouTube channel", "rewrite my channel about", "fix my banner", "channel audit", "set my trailer". Converts a viewer into a subscriber. Not for writing a video title (use yt-title-optimizer).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.