「attention」の検索結果

Choose responsibility for substantial work before deep execution: keep one responsibility's coupled parts in a single lane, and hand a bounded or independent lane to a worker when clean context, an unknown cause, independent review, or coordinator attention materially improves the outcome.

日本語の概要は準備中です。原文の説明を表示しています。

Generate a prioritized review queue of registry skills and catalog items that need attention. Use this skill whenever someone asks: "what needs review?", "what's overdue for audit?", "where are the weak spots in the registry?", "what should I audit next?", "run a health check on the registry", "show me flagged skills", "find problems in the registry", "what skills need fixing?", or "triage the registry". This is the triage layer — it surfaces candidates ranked P0–P4 so that focused work (via /gaia-audit) targets the right things first. Run this before any audit pass. Also invoke proactively when a PR changes registry/named/ at scale, or before a release, to catch regressions early.

日本語の概要は準備中です。原文の説明を表示しています。

Extracts ASCII and Unicode strings from a binary and classifies them into investigative categories: URLs, IPs, file paths, registry keys, mutexes, commands, and API names, prioritizing the analyst's attention. Activates for requests to extract strings, classify strings output, or pull human-readable artifacts from a sample.

日本語の概要は準備中です。原文の説明を表示しています。

Use when a task needs the judgment of a Customer Success Manager — driving product adoption after the sale, assessing renewal/churn risk, handling an at-risk account, or deciding how to prioritize limited attention across a book of accounts.

日本語の概要は準備中です。原文の説明を表示しています。

Use when a task needs the judgment of a Childcare Worker — checking ratio/headcount compliance across mixed-age groups, deciding whether a fall or minor incident needs a written report versus a verbal mention at pickup, redirecting a behavior problem in an unstructured (non-curriculum) setting, or triaging which of several simultaneous demands (a crying toddler, a fight over a toy, a diaper) gets attention first.

日本語の概要は準備中です。原文の説明を表示しています。

Use when a task needs the judgment of a CEO/chief executive — setting company strategy, allocating scarce resources (capital, headcount, attention) across competing priorities, making a call that only the top of the org can make, or communicating direction to the board, investors, or the whole company.

日本語の概要は準備中です。原文の説明を表示しています。

Use when a task needs the judgment of a doctoral-level Clinical or Counseling Psychologist — building a psychological test battery to answer a referral question, interpreting a WAIS/MMPI/PAI profile against validity indices, working a differential diagnosis (e.g. ADHD vs. anxiety-driven inattention, depression vs. early dementia), or writing a feedback-session-ready diagnostic formulation report.

日本語の概要は準備中です。原文の説明を表示しています。

Design focus modes that actually protect attention: Do Not Disturb schedules, app filtering, notification tiers, and context-specific setups. Use when interruptions fragment your day or 'do not disturb' never stays on.

日本語の概要は準備中です。原文の説明を表示しています。

Plan and protect deep work: scheduling focus blocks, task selection, shutdown rituals, and measuring depth. Use when important work never gets sustained attention or days fill with shallow tasks.

日本語の概要は準備中です。原文の説明を表示しています。

Write marketing content in the user's brand voice using PAS (Problem-Agitate-Solution) and AIDA (Attention-Interest-Desire-Action) copywriting frameworks. Use when the user asks to write a LinkedIn post, blog article, email, ad copy, landing page section, social post, newsletter, or any short-to-medium form marketing content. Reads brand voice and ICP from knowledge/ so the output sounds like the company, not like generic AI. For improving copy that already exists, see copy-review. For a landing page specifically, see landing-page-writer. For a LinkedIn post, see linkedin-post. For long-form POV, see thought-leadership-writer.

日本語の概要は準備中です。原文の説明を表示しています。

Review Caveman Cloud evidence read-only: costs, Cave Score, Cave Plan, workflows, traces, latency, errors, compression, routing, and verified savings. Use when the user asks what Caveman found, where LLM spend goes, why cost or quality changed, which workflows need attention, or asks for a trace or analytics review. Prefer Caveman MCP tools; fall back to CLI JSON.

日本語の概要は準備中です。原文の説明を表示しています。

DiT 计算模块（L3）：把**已定位的 DiT 计算瓶颈**落成特性级选档与实施—— 量化档（W8A16 / W4A16 / W8A8 系列 / W4A4 / MXFP8 / FA 量化）、稀疏（rf_v2 / ada_bsa）、 缓存（DiTCache / AttentionCache / 时间步优化）、编译启用（MindieSDBackend / Pattern 融合 / ACLGraph） 的**开不开、开哪一档、怎么开、怎么复验**；依据是 `docs/zh/features/*`（特性真源）+ framework-integration/references/framework-support-matrix.md（支持状态）。 即使用户只说"这个模型怎么加速""量化/稀疏/Cache 怎么选怎么开""要不要开量化、开哪一档""这个档位开了有没有效果" 而未提 profiling，也应触发。 **入口条件**：瓶颈点已明确（用户带一句实测锚点，或编排层交付标签）时由域入口 `performance-optimization` 按标签分发到本技能；**瓶颈未明（"怎么加速 / 跑通 / 采 profile"）先走 `model-auto-optimization` 定位**，不在本技能内做占比分析。 near-miss：多卡并行形态 / 通信掩盖 / TP·offload 选型 → `dit-parallel-opt`；VAE 解码段与 host 固定开销 → 各自模块（VAE / host）；单算子实现级实测选型（mindie_bench）→ `benchmark-dev`； 需要新增 pattern / 算子才能落地本档 → `pattern-dev` / `operator-dev`；框架侧开关与使能验证 → `framework-integration`；量化器位级契约与精度对齐（编码公式 / 舍入 / scale 粒度）→ `quantization-dev`；精度验收判据 → `accuracy-gate`；数字入库口径 → `perf-gate`。

日本語の概要は準備中です。原文の説明を表示しています。

Add CSS animations to HTML elements, React/JSX components, or WordPress PHP templates using Animate.css (v4.1.1). Use this skill whenever the user wants to animate UI elements, add entrance/exit effects, attention-seeker animations, or any CSS-based motion to their markup. Trigger on phrases like "add animation", "animate this", "make it bounce/fade/slide/zoom", "add transitions", "CSS animations", or any request to bring elements to life visually. Works with raw HTML snippets, full HTML files, React JSX, and WordPress PHP templates. Claude picks the most contextually appropriate animation — no guesswork needed from the user.

日本語の概要は準備中です。原文の説明を表示しています。

Continuously bridges DESIGN.md into the active planning phase. When the user is working on a UI phase, reads the project's DESIGN.md, extracts the relevant token slice, and appends it to findings.md under "## Design Context" so the agent sees design constraints in its attention window. Never edits DESIGN.md, never edits task_plan.md. Idles when DESIGN.md is absent.

日本語の概要は準備中です。原文の説明を表示しています。

Resolve repository documentation authority, repair reading paths and explanations, or shape a bounded public projection. Maintain docs after a bounded change when indirect reader promises, generated or paired sources, version/evidence boundaries, or unclear authority need attention. Ordinary known updates stay in normal development; not for isolated prose polishing, code review, or broad runtime audits.

日本語の概要は準備中です。原文の説明を表示しています。

Estenda janelas de contexto de modelos transformer usando RoPE, YaRN, ALiBi e técnicas de interpolação de posição. Use ao processar documentos longos (32k-128k+ tokens), estender modelos pré-treinados além dos limites de contexto originais ou implementar codificações posicionais eficientes. Cobre embeddings rotativos, vieses de atenção, métodos de interpolação e estratégias de extrapolação para LLMs.

日本語の概要は準備中です。原文の説明を表示しています。

Acelere a inferência de LLMs usando especulative decoding, múltiplas cabeças Medusa e técnicas de lookahead decoding. Use ao otimizar velocidade de inferência (aceleração de 1,5-3,6×), reduzir latência em aplicações em tempo real ou fazer deploy de modelos com recursos computacionais limitados. Cobre modelos draft, atenção em árvore, iteração de Jacobi, geração paralela de tokens e estratégias de deploy em produção.

日本語の概要は準備中です。原文の説明を表示しています。

[Skill Management] Use when enhancing, compressing, or expanding prompts, docs, or skills with attention anchoring [INTELLIGENT ROUTING]. Flag: --op={compress|expand|enhance} (default enhance); --op=compress strips token bloat, --op=expand reconstructs compressed text.

日本語の概要は準備中です。原文の説明を表示しています。

Assists users in crafting high-impact pitches, presentations, and sales communications using the "STRONG" method and Frame Control. Use when users want to pitch an idea to investors, sell a product to a client, or need to overcome objections and command attention in business meetings.

日本語の概要は準備中です。原文の説明を表示しています。

Create, verify, transfer, and resume compact project handoff packets for long-running Codex work. Use after a second observed automatic context compaction, immediately after a third compaction, when attention or constraints degrade, a major phase ends, the user asks to move work into a fresh task, work must pause, or an existing handoff needs to be imported. Do not interrupt after the first normal compaction. Always ask before creating a new task, transfer the global roadmap only after explicit consent, preserve the old task title when available, then require the fresh task to ask what work matters most. Preserve objectives, constraints, decisions, evidence, approval boundaries, workspace state, validation, and risks without treating an old summary as current truth.

日本語の概要は準備中です。原文の説明を表示しています。

Apply the 90/10 visual-to-text rule when composing a piece on a canvas (poster, card, social post). Use when the deliverable lives on a single fixed surface where each element competes for attention.

日本語の概要は準備中です。原文の説明を表示しています。

Score how much attention a person deserves: classify them (investor, engineer, student, partner, community, noise, personal), estimate the value they can bring in the next 90 days, their temperature, and the next move. Triggers: /worth, how valuable is <who>, who is <who>, should I reply to <who>, score this person, score this lead.

日本語の概要は準備中です。原文の説明を表示しています。

Use when the user asks to "track our share of voice", "what share of the conversation do we own vs competitors", or "trend our SOV this quarter"; computes SOV% = brand mentions ÷ (brand + competitor panel mentions) per platform per period on a LOCKED competitor panel — a panel switch invalidates the trend (restart the series and log the break; the ECHO O3 rule) — plus a sentiment-weighted SOV variant (sentiment labeled Estimated unless human-coded) and a Wikipedia-pageviews attention-share alternative; built from keyless listening connectors, gdelt.py news echo, and user exports — public counts only, closed platforms are never scraped. Not for backlink or offsite SEO signals — use offsite-signal-analyzer. 声量份额/竞品声量对比/提及份额/注意力份额

日本語の概要は準備中です。原文の説明を表示しています。

Generate and send a daily briefing to your owner covering today's meetings, urgent emails, open tasks, and anything that needs attention. Use when: it's the start of the owner's day, when asked for a summary, or on a scheduled cron job.

日本語の概要は準備中です。原文の説明を表示しています。