483건 · 관련도순
"Design hybrid recommendation systems combining multiple strategies for improved accuracy. Use this skill when the user needs to overcome single-method limitations, combine collaborative and content-based filtering, or build a production recommendation pipeline — even if they say 'combine recommendation approaches', 'best recommendation architecture', or 'cold start plus personalization'.".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Evaluate LLM agents and tool-using workflows—task success, tool accuracy, latency/cost, safety, and regression suites. Use when shipping agent features, comparing prompts/models, or debugging agent failures.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Performs a hallucination check on machine_readable sections by verifying every element traces back to the original legal text. Use this skill proactively when: machine_readable sections have been generated or modified, after /law-generate completes, when reviewing corpus YAML files for legal accuracy, or when user mentions "validate", "verify", or "hallucination check" for law YAML files. Activate automatically after editing machine_readable sections in corpus regulation YAML files.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Evaluating diagnostic tests — sensitivity, specificity, ROC analysis, likelihood ratios, and study design.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Elicit step-by-step reasoning from language models to boost accuracy on math, logic, and multi-step problems.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Analyzing behavioral experiment data — RT/accuracy preprocessing, mixed-effects models, and robust inference.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use this agent when you need to review UniProt annotation rules (ARBA, UniRule) for quality, biological accuracy, and GO annotation appropriateness. This agent performs comprehensive analysis of rule condition sets, evaluates literature support, assesses taxonomic scope, and recommends curation actions.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Identify and simulate Data Poisoning attacks aimed at degrading or skewing an AI model's accuracy. This skill focuses on Adversarial Machine Learning concepts where attackers inject malicious or mislabelled data points into training or fine-tuning datasets (e.g., feedback loops) to bias the AI.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
This skill provides guidance for maintaining documentation consistency with implementation in the vscode-sidebar-terminal project. Use this skill when creating or updating documentation, verifying documentation accuracy, preparing releases, or when the codebase has changed and documentation may need updates. This skill should be used proactively after implementing features or bug fixes.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a task needs the judgment of an Etcher/Engraver — compensating a resist pattern for expected undercut before etching fine detail, calculating etch time from a known etch rate rather than judging completion visually, verifying a functional engraving's line width/depth against its actual accuracy requirement, or re-validating process parameters on a new material batch before production.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a task needs the judgment of a Data Entry Keyer — resolving an illegible or ambiguous source-document field before keying it, running key-verification (double-key) reconciliation on a batch, deciding whether a production-speed quota is compromising accuracy, or sampling a completed batch for a quality-control audit.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a task needs the judgment of a Molder, Shaper, or Caster (ceramics, concrete, and similar non-metal, non-plastic materials) — calculating mold/pattern dimensions from a material's actual characterized shrinkage rate, deciding whether a demolding decision should follow a fixed time or a material readiness signal, controlling drying/curing rate to avoid cracking on uneven-thickness parts, or verifying mold dimensional accuracy after extended use.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Detect documentation drift, stale references, and cross-document inconsistencies in any project. Scans for code-doc drift (API/function changes not reflected in docs), cross-doc drift (conflicting information across documents), and stale references (broken links, deleted files, outdated versions). Use when checking "doc freshness", "stale docs", "documentation drift", "broken links", "outdated documentation", "doc accuracy", "docs out of date", "doc audit", "doc health", or "verify documentation".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when testing, evaluating, or building regression suites for Agentforce agents: conversation testing in Agent Builder, topic (now subagent) coverage and utterance testing, Testing API and AiEvaluationDefinition metadata, Agentforce DX CLI test runs (sf agent generate test-spec, sf agent test create/run/resume/results/list), evaluation metrics (containment rate, escalation rate, CSAT, topic activation accuracy), and post-deploy analytics via Enhanced Event Logs. Triggers: 'how do I test my Agentforce agent', 'agent routes to wrong subagent', 'write utterance tests', 'regression test after topic change', 'measure agent quality', 'agent containment rate', 'run agent tests from the CLI'. NOT for agent creation, topic design, or action contract design — use agentforce/agentforce-agent-creation, agentforce/agent-topic-design, or agentforce/agent-actions respectively.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Revenue Intelligence setup: activating the RI app and its CRM Analytics assets, Einstein deal insights, the opportunity-change waterfall, and forecast-accuracy analytics for sales leaders. NOT for configuring the Pipeline Inspection view, its metrics and review cadence - use admin/pipeline-review-design. NOT for forecast types, categories, rollups and quotas - use admin/collaborative-forecasts.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Configuring and running Pipeline Inspection in Sales Cloud: enabling the feature, mapping forecast categories into the inspection view, Days in Stage and other deal-change metrics, and pipeline review cadence for sales managers. Use when designing or improving how a team monitors deal health and pipeline movement. NOT for the Revenue Intelligence app, Einstein deal insights, or forecast-accuracy dashboards — use admin/revenue-intelligence-setup. NOT for forecast types, quotas, or forecast hierarchy setup — use admin/collaborative-forecasts. Keywords: pipeline review, coverage ratio, stage conversion, slippage, stale deals, days in stage, LastStageChangeInDays, LastStageChangeDate, AgeInDays, PushCount, ForecastCategoryName, enablePipelineInspection, PipelineInspMetricConfig, OpportunitySettings, review cadence, commit call.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Compound fields (Name, Address, Geolocation): SOQL access rules, DML semantics, component access in Apex/LWC, reporting column behavior, formula field restrictions. NOT for creating a new custom field — use admin/custom-field-creation. NOT for formula syntax and functions — use admin/formula-fields. Trigger keywords: BillingAddress, MailingAddress, ShippingAddress, StateCode, CountryCode, GeocodeAccuracy, Location field type, displayLocationInDecimal, __Latitude__s, __Longitude__s, DISTANCE, GEOLOCATION, Custom Address Fields, AddressSettings, System.Address, System.Location, Person Account name.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Code comment accuracy verification, documentation completeness assessment, comment rot detection.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Firmware development for the WeAct Studio "Black Pill" (STM32F411CEU6) and its clones such as the DFRobot DFR0864 — the 25 MHz HSE and 32.768 kHz LSE crystals, PC13 LED, K1 button, USB-C wired straight to USB_OTG_FS, ROM DFU flashing, the SPI-flash footprint, and the STM32Cube HAL + PlatformIO setup around them. Use when working on this board or any STM32F411CE/F401CC Black Pill: project setup, platformio.ini, clock and PLL configuration for 96 MHz plus 48 MHz USB, pin mapping on the 48-pin package, USB CDC console, RTC on the LSE crystal, the internal temperature sensor, ADC accuracy, DFU flashing and recovery, or debugging why something on the board does not work.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.