「profiling」の検索結果

Interactively gather parameters for `python -m cli.inference.text_generate`, generate a concrete text generation simulation command, explain assumptions, ask for execution confirmation, then run the command and summarize performance metrics. Use when the user wants to validate a specific model, hardware profile, batch/query size, prefill or decode scenario, TP/DP/EP/MOE parallel strategy, profiling database, chrome trace, empirical metrics export, or a best row produced by throughput_optimizer.

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。

MindStudio Profiler Analyze（msprof-analyze）是面向 AI 训练与推理场景的性能分析工具，基于采集得到的 profiling 数据进行统计、比对和诊断，帮助定位计算、通信、调度及集群场景下的性能瓶颈。

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。

Analyze Ascend NPU computation-side profiling data for single-card runs or a selected rank from multi-card runs. Use this skill when the user asks to diagnose computation bottlenecks, AI Core / AI Vector / AICPU hotspots, dynamic shape overhead, block dim issues, redundant TransData/Transpose/Cast, cross-stream waits, frequency/runtime-state issues, or fusion opportunities.

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。

Analyze Ascend NPU collective communication profiling data with a DB-first workflow. Use when the user provides `cluster_analysis_output/cluster_analysis.db`, rank-level `analysis.db`, rank-level `ascend_pytorch_profiler_{rank_id}.db`, together with `profiler_info.json`, and asks about HCCL or hcom communication cost, collective communication TOP ops, wait time, slow rank/straggler, Notify Wait, bandwidth, retry, relay, SDMA/RDMA/HCCS links, communication matrix, or Ascend communication fault patterns.

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。

专门用于 Ascend 集群 Profiling 性能数据的“快慢卡”诊断专家技能。当用户提供【集群性能数据目录/路径】并要求分析【快慢卡】、【慢节点】、【负载不均衡】或【集群瓶颈】时，必须触发此技能。该技能会自动接收集群路径，调度相关工具输出快慢卡的宏观定性与微观根因（如 Host 下发瓶颈、算子计算劣化）。

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。

RL 强化学习训练与推理（rollout）路径的算子差异性扫描。当用户提供训练启动脚本路径，要求对比 Megatron 训练路径与 vLLM 推理路径的算子差异（尤其是融合算子 vs 单算子不一致）时使用此 skill。典型触发词包括"训推算子扫描"、"训推差异性"、"算子差异报告"、"融合算子对比"、"train vs infer op diff"。注意：本 skill 通过运行完整 RL 训练脚本（集成 profiling）来采集真实运行时算子（非静态源码扫描，非独立分离运行）。当训练、推理使用不同脚本时禁止触发。

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。

运行程序采集 Profiling 数据，再用 msprof-analyze 分析TFLOPS 与 MFU。

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。

Iterative measurement-driven improvement loop. Measure, profile, mutate, re-measure, commit. Works for performance, bundle size, complexity, test coverage — anything quantifiable. Use when the user wants to systematically improve a metric through repeated cycles of profiling and targeted changes.

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 you need to know where a piece of reporting actually came from — the user gives an article URL and asks "where does this come from?", "who is the original source?", "is this just a rewrite?", or another skill needs the provenance chain before grading or citing a report. Follows an article's links and named attributions back to the originating vendor, government, victim or actor document and returns the chain, the primary's stated access and confidence language, publication dates, and every hop it could not resolve. Deterministic — a script or the Liberty91 platform resolves the chain; the model does not reconstruct it from memory. Invoked by /quality-of-information-check, /threat-actor-profiling, /campaign-tracking and /intelligence-writing. Works on any URL with no API key.

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 build or update a threat-actor profile, "tell me about actor X" / "profile actor Y", or another skill needs the canonical profile template (attribution, TTPs, campaigns, infrastructure patterns, intelligence gaps).

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 you need to check whether an organisation/domain has been claimed by a ransomware group, profile a specific ransomware group (TTPs, leak-site infra, IOCs, YARA), or aggregate ransomware victim claims by country/sector/timeframe. Backed by ransomware.live's leak-site scrapes — 27k+ victims across 330+ groups. Commonly invoked by /domain-investigation, /ransomware-ecosystem, /threat-actor-profiling, and detection-engineering workflows. Reads $RANSOMWARE_LIVE.

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 you need CrowdStrike Falcon Intelligence on an indicator (IOC reputation for an IP, domain, hash, or URL — malicious confidence, linked actors, malware families, reports) OR on an adversary (threat-actor profile, origin/target search, MITRE ATT&CK TTPs, finished intel reports). Answers questions like "look up 1.1.1.1", "what TTPs does Charming Kitten use?", "which threat actors operate from Russia?", and "latest report on Mustang Panda". Commonly invoked by the four /*-investigation skills, /ioc-enrichment-workflow, /threat-actor-profiling, and the regional espionage cells. Other agents/skills can chain this for vendor-authoritative actor and finished-intel context. Requires a Falcon Intelligence subscription.

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 report or article needs to be split into individual claims before it is graded, cited or used as evidence — the user asks "what does this report actually claim?", "split this into claims", "separate the facts from the judgements", or another skill needs a claim list. Turns one document into five to twelve atomic claims, each typed (observation, attribution, assessment, actor claim, victim disclosure) and anchored to the verbatim sentence it rests on, so every extraction can be checked against the source. Preserves the source's own hedging. Does not grade. Invoked by /quality-of-information-check; its output feeds /ach, /key-assumptions-check, /intelligence-writing, /writing-assessments and /threat-actor-profiling.

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 you need to answer "which attacker techniques do our controls actually stop, and how well?", "what controls should I have for this threat?", or "what telemetry should I collect to detect it?" — joining a customer's or your own security control baseline to ATT&CK techniques using a public, versioned evidence base of 9,545 control-to-technique mappings from six sources. Produces four ranked lists (addressed strongly, addressed weakly, real gaps, and techniques no control anywhere addresses). Use for control gap analysis, security programme prioritisation, board reporting on coverage, or the Resistance Strength side of a FAIR risk assessment. Invoke after /threat-actor-profiling or /lookup-liberty91 has produced a technique list.

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 you need Liberty91 platform intelligence — what actually happened (deduplicated Threat Events with every source, Admiralty reliability/credibility and verification stage), whether an IOC is already known to your account, the canonical threat library (actors, malware, vulnerabilities, clusters, ATT&CK TTPs), alert matches, or which of your customer organizations an occurrence affects — or when you need to push intelligence back: ingesting your own report, generating an intelligence package, or uploading an organization document. Also supplies event provenance fields, when the platform returns them, and Threat Library alias resolution to /source-provenance and /quality-of-information-check. Two-way, first-party integration. Commonly invoked by /ip-investigation and friends, /ioc-enrichment-workflow, /threat-actor-profiling, /campaign-tracking and /vulnerability-intelligence. Reads $LIBERTY91_API_KEY.

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。

Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.

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。

Develops comprehensive threat actor profiles for APT groups, criminal organizations, and hacktivist collectives by aggregating TTP documentation, historical campaign data, tooling fingerprints, and attribution indicators from multiple intelligence sources. Use when briefing executives on sector-specific threats, updating threat model assumptions, or prioritizing defensive controls against specific adversaries. Activates for requests involving MITRE ATT&CK Groups, Mandiant APT profiles, CrowdStrike adversary naming, or sector-specific threat briefings.

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。

Audit data quality across six DAMA DMBOK dimensions — Completeness, Accuracy, Consistency, Timeliness, Validity, Uniqueness. Produces a scored data quality report with issue log and remediation plan. Use when profiling datasets, onboarding new data sources, or building data quality gates.

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。

Deep OSINT reconnaissance using the MITRE ATT&CK Reconnaissance framework. Email harvesting with SMTP verification, subdomain takeover detection, certificate transparency mining, Shodan/Censys intelligence, Wayback Machine historical analysis, social media profiling, cloud storage enumeration, document metadata extraction, DNS history, credential leak checks, and passive infrastructure mapping. Uses theHarvester, amass, dnsrecon, fierce, dnstwist, dmitry, whatweb, wafw00f, exiftool, metagoofil, smtp-user-enum, swaks, waybackurls, subfinder, and crt.sh. Pure reconnaissance — no active exploitation. Produces: confidence-scored findings, infrastructure diagram, employee roster, email pattern confirmation, subdomain takeover candidates. Chains into /pentester for active testing.

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。

React Native performance profiling, optimization, and monitoring - JS/UI thread analysis, re-render prevention, list optimization, image performance, bundle size, startup time, memory leaks, React Compiler, New Architecture benefits

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。

Profiles a threat actor by aggregating observed ATT&CK techniques into a TTP profile and comparing it against known-group technique sets to estimate similarity and candidate attribution. Activates for requests to profile a threat actor, compare observed TTPs to known groups, or estimate attribution from technique overlap.

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。

Profiling strategy for audio CPU issues — xruns, spikes, and buffer underruns. Use when the user reports CPU overload, audio glitches under load, or performance regressions. Trigger on phrases like "I'm getting xruns", "my plugin causes CPU spikes", "dropouts under high voice count", "audio thread is too slow", "how do I profile my DSP". References audio-numerics-review for denormal slowdown and audio-dsp-review for lock contention.

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。

Structured performance profiling workflow. Identifies bottlenecks, measures against budgets, and generates optimization recommendations with priority rankings.

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。

Go software engineering skill for designing, implementing, debugging, testing, reviewing, and refactoring Go applications, CLIs, APIs, services, concurrency code, modules, and tooling. Use for .go files, go.mod/go.sum, goroutines/channels, interfaces, error handling, performance profiling, race fixes, and idiomatic Go architecture.

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。