609건 · 관련도순
Implements data classification labels and tagging systems including metadata tagging, DLP integration, automated label propagation, user-applied labels, and label inheritance rules. Covers Microsoft Purview sensitivity labels and enterprise labeling architecture. Keywords: data labeling, sensitivity labels, metadata tagging, DLP integration, label propagation, Purview, classification.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Implements automated PII discovery and classification using tools like Microsoft Purview, BigID, OneTrust DataDiscovery, and AWS Macie. Covers scanning schedules, accuracy tuning, false positive management, and integration patterns. Keywords: data discovery, PII scanning, Purview, BigID, Macie, OneTrust, automated classification, data cataloging.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Hybrid fingerprint + LLM pipeline for bug classification, deduplication, and ticket generation. Normalizes CI logs, creates stable fingerprints, clusters near-duplicates, then uses LLM for severity classification and ticket writing. Includes bug reporting templates and severity/priority matrix. Use when: "bug triage," "classify bugs," "failure analysis," "auto-classify," "CI failures," "bug report," "defect template." Not for: runtime self-healing of one flaky locator — use test-reliability. Not for: designing new tests from production telemetry — use observability-driven-testing. Related: qa-metrics, qa-dashboard, ci-cd-integration, qa-project-context.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Classify product approach into one of six types (Clone, Unbundle, Undercut, Slice, Wrapper, Innovation) based on competitive landscape. Triggers on PRD v0.2 work after competitive analysis, or when user asks "what type of product should we build?", "should we clone or innovate?", "is this a fast-follow opportunity?", "how should we position against competitors?", "clone vs undercut", "unbundle vs slice", or requests help choosing product strategy. Outputs BR- entries for product type classification and inherited GTM constraints.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Query patent bibliographic (catalog) information from the Nexscope patent database by patent ID or publication number. Triggered when users mention patent bibliographic info queries, patent catalog information, patent applicant queries, patent inventor queries, patent classification codes, patent abstract retrieval, patent citation analysis, patent priority claims, patent application citations, patent examiner information, patent bibliographic data, inventor lookup, applicant lookup, patent classification, patent metadata, Nexscope, or patent citations. Even if the user does not explicitly mention "bibliographic info," this skill should be triggered whenever their need involves querying detailed metadata for a specific patent by patent ID or publication number.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design a Montessori three-period lesson for introducing concepts through concrete materials and naming. Use when teaching vocabulary, classifications, or concepts through hands-on materials.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
MTProto-over-WebSocket tunnel for Telegram: DC classification, obfuscated2 detection, TLS backend choice, and the relay loop. Use when touching Telegram DC routing, MTProto classification, or ripdpi-ws-tunnel.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Advises on setting up LLM-based text classification as a validated measurement design. Covers codebook construction, learning-regime and model choice, prompt construction, validation against human coding with kappa and F1, hybrid human-LLM review, downstream measurement error, and reporting, plus a short resumable batch pattern with a rule-based baseline for repeated free text against a closed codebook. Use when the user wants to classify, code, or label text at scale. Category discovery goes to topic-modeling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Advises on setting up and validating LLM text classification: codebook, learning regime and model choice, prompts, validation against human coding (kappa, F1), hybrid review, measurement error, and reporting, plus a short resumable batch pattern with a rule-based baseline. Use to classify, code, or label text at scale; category discovery goes to topic-modeling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Probe the runtime state of a named feature flag in a CLI binary. Covers the four-pronged evidence protocol (binary strings, live invocation, on-disk state, platform cache), the four-state classification (LIVE / DARK / INDETERMINATE / UNKNOWN), gate-vs-event disambiguation, conjunction-gate handling, and skill-substitution scenarios where a flag appears DARK but the capability is delivered by other means. Use when verifying whether a documented or inferred capability has rolled out, when auditing dark-launched features, or when a prior probe's conclusions need refreshing against a new binary version.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Catalog and classify materials using standard library systems. Covers descriptive cataloging, subject headings, call number assignment using Dewey Decimal and Library of Congress Classification, MARC record basics, shelf organization, and authority control for consistent access points. Use when organizing a personal, institutional, or community library from scratch, assigning call numbers and subject headings to new acquisitions, reclassifying a collection that has outgrown its original system, or establishing authority control for authors, series, or subjects.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Audit customer service triage systems for ticket routing, classification, and SLA compliance. Triggers: you need to evaluate ticket auto-classification accuracy, priority scoring models, skill-based routing logic.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use this skill when configuring Marketing Cloud Engagement (formerly ExactTarget): business units, user roles, sender profiles, delivery profiles, send classifications, and account-level settings. NOT for MCAE / Account Engagement (Pardot) setup — use admin/mcae-pardot-setup. NOT for designing a multi-brand parent/child BU hierarchy — use architect/multi-bu-marketing-architecture.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when building, configuring, or troubleshooting email sends in Marketing Cloud Email Studio and Content Builder. Triggers: 'dynamic content', 'send classification', 'A/B test email', 'Content Builder template', 'triggered send', 'suppression list', 'Commercial vs Transactional'. NOT for MCAE (Pardot) — use admin/mcae-pardot-setup. NOT for Journey Builder orchestration — use admin/journey-builder-administration.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design, implement, or audit a Change Advisory Board (CAB) process for Salesforce deployments: change classification (standard, normal, emergency), required approvals, deployment gate sequencing, and integration with external ITSM tooling. NOT for scoring how risky one release is - use admin/deployment-risk-assessment. NOT for executing or troubleshooting the deployment itself - use admin/change-management-and-deployment. Also covers: the CAB charter (membership, quorum, decision rights), the CAB decision record artefact and its linter, the change classification matrix, the deployOptions a CAB decision pins (checkOnly, testLevel, rollbackOnError, ignoreWarnings, runTests), the 10-day quick-deploy validity window, the deploy-window vs freeze-register check, and the emergency (ECAB) path with its mandatory retrospective.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Drafts a Chapter 11 Plan of Reorganization under 11 U.S.C. §§ 1121–1129 with claim classification, treatment provisions, distribution mechanics, executory contract determinations, and confirmation compliance. Use when preparing reorganization plans, restructuring debts, classifying claims, drafting Chapter 11 plans, or helping debtors emerge from bankruptcy. Trigger keywords: reorganization plan, Chapter 11, plan of reorganization, debt restructuring, cramdown, claim classification, confirmation order.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Drafts U.S. Customs and Border Protection binding ruling requests under 19 CFR Part 177 for tariff classification, valuation, origin, and marking determinations. Trigger when input mentions "binding ruling," "CBP ruling request," "19 CFR Part 177," "classification request," "HTSUS analysis," "transaction value," "country of origin," or "marking for import."
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Ticket/PRD intake: product area classification, completeness scoring, RCA, technical assessment. Works with Jira (via mk:jira-issue / jira-as), Linear (via MCP), GitHub (via gh CLI), or manual paste. Triggers: 'analyze ticket', 'intake PRD', 'triage issue', 'classify ticket', 'check ticket'.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Detects command-and-control (C2) communications tunneled through DNS protocol including DNS tunneling tools (Iodine, dnscat2, dns2tcp, Cobalt Strike DNS beacon), domain generation algorithms (DGA), encoded payload delivery via TXT/CNAME records, and DNS beaconing patterns. Covers Shannon entropy analysis of query subdomains, statistical anomaly detection, ML-based DGA classification, passive DNS correlation, and Zeek/Suricata signature development. Activates for requests involving DNS-based C2 detection, DNS tunnel identification, suspicious DNS traffic investigation, or DGA domain classification.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Reads one export transaction, order or shipment description and returns a DRAFT export review pack: parties to screen with a screening checklist, an item classification worksheet, a red-flag review, licence-determination questions and open items. Use when the user asks to "prepare the export review for this order", "pre-check this shipment for export control", "who do we need to screen on this deal", "build the classification worksheet for this item" or "assemble the trade-compliance file for this technology transfer". Do not use for vendor security or due-diligence screening of a supplier's questionnaire answers; use vendor-risk-screening-brief instead. Never classifies, screens, clears, decides licence need or releases a shipment; trade compliance does. Drafts for human review; never approves, authorises or signs off.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Implement Amazon Macie to automatically discover, classify, and protect sensitive data in S3 buckets using machine learning and pattern matching for PII, financial data, and credentials Tespit.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
tespit etme (s) prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The tespit etme (or) analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-...
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.