'compression' 검색 결과

Use Tokenless for large files and noisy tool outputs before they enter context. Must be used when commands, Read output, diffs, logs, or search results are large.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AI internal coordination using stigmergic signals — managing information freshness in context and memory, decay rates for assumption staleness, and emergent coherent behavior from simple local protocols. Use during complex tasks where multiple sub-tasks must coordinate, when context has grown long and information freshness is uncertain, after context compression when information may have been lost, or when sub-task outputs need to feed into each other cleanly without degradation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Token-range severity zones (Green/Yellow/Orange/Red/Critical) with detection checklist, early warning indicators, and corrective routing actions for context window degradation

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user says "simplify this diff" or asks for a compression pass over a change-set. Not for dead-code sweeps: use deslop.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

当用户直接要求进行数据集压缩测评，或在量化调优过程中需要使用 AISBench 评测工具输出数据集精度等场景时使用。 本 Skill 负责：使用 AISBench 数据集压缩代码、用 RBF Kernel Herding 算法生成压缩后的数据子集（coreset），并按用户目标交付两种产物之一： ① 接入量化调优主流程：产出独立的 coreset 数据集配置（不覆盖原始数据），回传「全集 config_name + coreset config_name」给编排层，供 evaluation.yaml 切换； ② 仅数据集压缩测评（不做量化调优）：基于 example 模板生成「全集测试脚本」和「子集测试脚本」两份 shell 脚本。 暂时支持 AIME 2025 和 GPQA，其他数据集需要再结合 aisbench tools目录下 herding_coreset_selector 源码进行分析。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Manage AI context windows with compression. TRIGGERS - Use when user needs help with ai-context-window-manager related tasks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when loading glTF/GLB models or textures in PlayCanvas, choosing Draco or Basis/KTX2 compression, or setting up decoders and preloading.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Integrate an external, licensed Itasca PFC 5.0 fistPkg26 tree as a reproducible material-generation and compression/diametral/tension test baseline; use to validate its PFC5.0 layout, copy a private working case, preserve provenance, and audit ck/ct/dc/tt/ft extension points for asphalt workflows.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plan, audit, and post-process PFC 5.0 asphalt calibration tests, including compression, diametral loading, direct tension, creep-recovery, test geometry, histories, peak metrics, stiffness, and fistPkg handoff.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Master FFmpeg for video/audio conversion, compression, trimming, subtitles, streaming, and batch processing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Client-side image handling - preview generation, Canvas API resizing, compression, EXIF orientation, format conversion, memory management with object URL cleanup

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Section-by-section media planning and generation. Image generation (GPT Image 2 primary, built-in fallback), logo/icon generation (Ideogram v3 → favicon set), video generation (Veo 3.1), social preview images (OG 1200x630 + AI search optimization), stock photo curation (Pexels, Pixabay), critique/remix loops (max 3 rounds), asset compression pipeline, and media performance budgets.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

HTTP/2 protocol-specific attack playbook. Use when the target supports HTTP/2 and you need to exploit binary framing, HPACK compression, h2c upgrade smuggling, pseudo-header injection, stream multiplexing abuse, or H2→H1 downgrade translation flaws.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Detects packing and encryption by measuring Shannon entropy across a binary's sections and regions: flagging high-entropy executable sections, entropy spikes, and size/raw-vs-virtual anomalies that indicate compression or encryption. Activates for requests to measure entropy, detect packing, or assess whether a sample is compressed/encrypted.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Hunts for pre-exfiltration data staging and archiving by detecting archive-tool execution (rar, 7z, zip, tar), large compressed files written to staging directories, and collection into a single location before transfer. Activates for requests to hunt data staging, detect pre-exfil archiving, or find collection and compression before exfiltration.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when a task needs the judgment of a Commercial Diver — planning a surface-supplied or SCUBA-mode dive against no-decompression limits, sizing a bailout/reserve gas supply before descent, choosing wet vs. dry (habitat) underwater welding for a repair, scoping an underwater NDT inspection, or deciding whether to abort a dive against a safety threshold.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Transform reference photographs and visually dense images into sparse, recognizable, high-saturation flat-vector-style illustrations through semantic compression rather than literal tracing. Use when the user asks for photo-to-flat illustration, photo-to-vector-style redraw, 照片转扁平插画, 无渐变高饱和插画, iconification, visual simplification, composition-preserving abstraction, a consistent minimal illustration set, or revisions that remove gradients, glow, texture, blur, clutter, text, logos, numbers, or UI. Default to human-perceived semantic complexity 6 out of 10 or lower, fixed-HSB solid fills, crisp boundaries, and no gradients or light-halo effects.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Persistent token-compression mode (~75% reduction) — now always-on by default. Strips filler while keeping code exact.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Configure a CDN with optimized caching, SSL/TLS, security headers, and cache invalidation — auto-detects hosting provider and app type, generates CloudFront, Cloudflare, or Vercel config with per-content-type cache rules, edge functions, and compression. Use when deploying a static site, SPA, SSR app, or adding a CDN layer to an existing API.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audits and implements mandatory image resizing and compression for all uploaded user images to reduce storage costs while preserving visual quality.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

**WORKFLOW SKILL** — Persist analysis so it survives context compression and chains between tasks. USE FOR: any task whose decisions affect future work — features, refactors, architecture changes, integrations. Produces a lightweight Task Analysis Map that externalizes intent, decisions, and chain context. Use to document decisions, create continuity, prevent context loss, bridge tasks, externalize reasoning. DO NOT USE FOR: quick intent validation (use task-intent), deep structured analysis (use contextação).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit the fold.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.