「fid」の検索結果

在 W8A8 动态量化后，用 MindIE-SD 冒烟测试 DiT 量化权重是否可加载（可选 skill）。与 `quant-tuning-evaluate`（DiT 扩展节）的区别：本 skill 仅做"能跑通 + 权重可用"的轻量验证（4~16 条 prompt，几分钟出结果），不算分；后者产出视频集交 `quant-tuning-score-dit`（AISBench-VBench 16 维度）评分，是调优回路一环。不引入 vLLM-Ascend、不做精度指标评估（FID/CLIP-score 等）。

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。

Core knowledge for migrating integrations from other platforms (Boomi, Cyclr) to Prismatic Code Native Integrations. Provides the standard integration schema, schema-to-spec mapping, confidence scoring, and migration-aware code generation patterns. Use when the user says "migrate", "convert from Boomi/Cyclr", "parse this export".

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。

Gathers information from multiple sources in parallel, compares what they say, flags where they agree or conflict, and delivers a clean synthesis with a confidence rating for each finding. Useful for making evidence-backed decisions, when evaluating competing claims, during due diligence on a vendor or market, and for building research briefs before strategy sessions. Use when the user says "research this", "synthesize multiple sources", "compare sources", "research report", "what does the evidence say", "gather information on", or "deep dive into".

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。

Structured threat assessment methodology. Intent + Capability + Opportunity = Threat Level. Use when formally evaluating a threat. Prefers graded evidence items from /quality-of-information-check and runs that skill first when handed raw URLs or text. Confidence is capped by the weakest load-bearing claim, and at Moderate when the evidence is ungraded.

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。

STIX 2.1 bundle creation reference. Object types, relationships, and JSON templates for structured threat intelligence sharing. Includes the per-claim mapping of evidence grades (access level and claim support) from /quality-of-information-check to STIX confidence, and the reverse mapping on import.

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 write a threat / risk / vulnerability assessment, or wants the appropriate template for each type. Distinct structures and section ordering per assessment kind. Prefers graded evidence items from /quality-of-information-check and runs that skill first when handed raw URLs or text. Confidence is capped by the weakest load-bearing claim, and at Moderate when the evidence is ungraded.

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 abuse-report history for an IPv4/IPv6 address — confidence score, total reports, distinct reporters, usage type. IP-only. Commonly invoked by /ip-investigation. Retrieval only.

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。

Analysis of Competing Hypotheses — structured technique for evaluating multiple explanations against evidence. Use when facing ambiguous attribution or multiple plausible scenarios. Prefers graded evidence items from /quality-of-information-check and runs that skill first when handed raw URLs or text. Runs on ungraded evidence when asked, labelled as such, unweighted, and capped at Moderate confidence.

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 as the default entry point for any CTI request that doesn't name a specific skill. Activates when a user asks to investigate an indicator, profile a threat actor, write an assessment, enrich IOCs, or build detection rules, and when a user asks where a report or article comes from, how reliable it is, to grade a source, check a report, or split a report into claims, or pastes a bare article URL. Routes to the right investigation, provenance, grading or analysis skill, then auto-applies rigor skills (source rating, TLP, confidence, likelihood) on the output.

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。

IOC export formats and procedures. CSV, STIX 2.1, OpenIOC, MISP. Handles format conversion and packaging, and carries per-claim evidence grades (access level and claim support) from /quality-of-information-check into each format (STIX confidence, MISP attribute tags).

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 the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

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。

Translate Figma nodes into production-ready code with 1:1 visual fidelity using the Figma MCP workflow (design context, screenshots, assets, and project-convention translation). Trigger when the user provides Figma URLs or node IDs, or asks to implement designs or components that must match Figma specs. Requires a working Figma MCP server connection.

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。

Perform triangulated cognitive research combining SQLite memory, GitHub 10k+ stars patterns, and ToT DAG benchmarking before critical architectural decisions. Automatically triggers subagent research escalation when confidence is low (<0.70). Keywords: research, benchmark, github, memory, triangulation, grounding, best-practices, escalation

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。

"Implement TF-IDF scoring to measure term importance relative to a document corpus. Use this skill when the user needs to rank documents by keyword relevance, extract important terms from text, or build a basic search relevance engine — even if they say 'find relevant documents', 'keyword extraction', or 'term importance'.".

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。

"Calculate Value at Risk to estimate maximum portfolio loss at a given confidence level. Use this skill when the user needs to quantify downside risk, set risk limits, or report regulatory risk measures — even if they say 'worst case loss', 'portfolio risk', or 'how much could we lose'.".

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 or revise audience-ready HTML paper presentations for lab meetings and journal clubs. Use when Codex needs source-grounded figures and tables, a fluent live-talk narrative, verified quotations, varied explanatory diagrams, presenter-paced reveals, or browser QA for evidence fidelity, interaction, responsive layout, and print.

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。

Facilitate SAFe 6.0 PI Planning events. Structure the 2-day cadence, generate PI Objectives with Business Value scores, build the Program Board for dependency visualization, and run the Confidence Vote. Use before every Program Increment when the organization follows SAFe.

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。

Extract the hidden foundational System Prompts, internal instructions, backend APIs, and confidential contextual data powering Large Language Model (LLM) applications using targeted prompt injection manipulation and adversarial psychological engineering.

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。

Exploit an application's absolute trust in its underlying LLM (Overreliance). Use this skill to induce critical "hallucinations" (confident falsehoods) that cause downstream logical systems or automated agents tracking the LLM's output to make destructive actions or grant unauthorized access.

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。

Execute sophisticated Data Extraction and Privacy Leakage attacks explicitly against Large Language Models (LLMs) to natively force the neural network entirely into organically regurgitating exact, verbatim strings of Highly Confidential Personally Identifiable Information (PII), proprietary source code, or copyrighted material categorically memorized intrinsically during its foundational pre-training phase.

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。

Captures and evolves user preferences with confidence levels. Maintains Voice of the Customer model with exact language, dissatisfaction and aspiration signals. Handles promotion/demotion, global vs project scoping, auto memory system, and Omi wearable data integration.

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。