'scoring' 검색 결과

Scoring rubrics for all 5 pipeline layers (Vision, Architecture, IA, BE, FE). Use when auditing specs, running self-checks, or remediating ambiguity gaps.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Orchestrate ambiguity auditing across selected layers with rubric-driven scoring, remediation flow, and next-step gating

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Execute ambiguity audit document-by-document with implementer simulation, rubric scoring, cross-layer checks, remediation, and verdicting

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Evaluate everything the PA agent manages — tasks, skills, PA network health, billing, calendar connections, and memory quality. Use when: owner asks for an evaluation, wants to know what's working and what isn't, or requests a performance report. Combines supervisor status with quality scoring.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when working with Codescene — codeScene behavioral code analysis including code health scoring, hotspot detection, change coupling analysis, and PR integration for code quality gates. Use when configuring CodeScene for codebase visualization, technical debt prioritization, and automated code review feedback.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when working with Codeclimate — code Climate quality management. Covers maintainability analysis, test coverage tracking, issue detection, GPA scoring, and repository configuration. Use when managing Code Climate projects, reviewing maintainability ratings, tracking test coverage trends, or configuring analysis engines.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when working with Codeball — codeBall AI-powered pull request risk assessment including automatic PR quality scoring, risk classification, and auto-approval for low-risk changes. Use when configuring CodeBall for automated PR triage, risk-based review routing, and review workload optimization.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when working with Adyen — adyen payment platform management including merchant accounts, payment methods, terminal configuration, risk management, settlement reports, and webhook notifications. Covers authorization rates, payment method performance, fraud scoring, and payout reconciliation.

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.

NVIDIA RAG Blueprint evaluation guidance for measuring retrieval and answer quality with stable datasets, baselines, and reproducible scoring workflows.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generate read-only MongoDB queries (find) or aggregation pipelines using natural language, with collection schema context and sample documents. Use this skill whenever the user asks to write, create, or generate MongoDB queries, wants to filter/query/aggregate data in MongoDB, asks "how do I query...", needs help with query syntax, or discusses finding/filtering/grouping MongoDB documents. Also use for translating SQL-like requests to MongoDB syntax. Does NOT handle Atlas Search ($search operator), vector/semantic search ($vectorSearch operator), fuzzy matching, autocomplete indexes, or relevance scoring - use search-and-ai for those. Does NOT analyze or optimize existing queries - use mongodb-query-optimizer for that. Does NOT handle aggregation pipelines that involve write operations. Requires MongoDB MCP server.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert en bug bounty (HackerOne, Bugcrowd, scope, PII, CVSS scoring, responsible disclosure)

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Frontend design blueprints with craftsmanship scoring, self-critique loops, and engineering handoff. Aesthetic intelligence against AI homogeneity. Use for: UI/UX design specs, design system creation, visual direction exploration, component design review, design-to-engineering handoff.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Shared foundation for all human-voice writing skills. Load before any profession-specific skill. Contains: burstiness principle, perplexity principle, soul injection techniques, community-discovered AI patterns with sources, additional core patterns, banned AI vocabulary, and scoring rubric.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Implement API Security Posture Management to continuously discover, classify, and score APIs based on risk while enforcing security policies across the API lifecycle.

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.

Run a Busabase-backed sales prospecting and first-touch outreach desk with a bundled Hono App-in-Skill deployable to AirApp. Use whenever the user invokes $kelly-sales-outreach or /kelly-sales-outreach, wants to enter a product or service and discover its ideal customers, asks to continuously find target accounts or public business contacts, needs evidence-based ICP scoring and personalized outreach drafts, or wants to review and send cold outreach safely. Four subcommands - setup, profile, research, send - plus the desk itself. Every first-touch message requires human approval; one company receives one initial email; guessed addresses, purchased lists, secret exposure, automated spam, and unreviewed external sends are forbidden.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Run a Busabase-backed sandbox desk for scoring and triaging course-instructor ("讲师") candidates found on a recruiting-style platform. Use whenever the user invokes $kelly-instructor-sourcing or /kelly-instructor-sourcing, wants a lightweight instructor candidate tracker, needs to score sourcing-platform leads against a three-axis rubric (background endorsement, expertise depth/breadth, teaching-service ability) before reaching out, or wants to log a WeChat add without building a live-connected outreach tool. Three subcommands - setup, criteria, review - plus the desk itself. v1 is sandbox-only — every dataset is deterministic mock data, it never connects to a real sourcing-platform or messaging account, and it never sends a message or automates a WeChat add - that stays entirely human-performed outside the app.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Influencer/creator marketing command desk (Busabase App-in-Skill) — the agent sweeps and fit-scores creator candidates, drafts outreach and briefs, and gates content before it ships; the human reviews creator cards, approves outreach/briefs/contracts, and tracks campaign ROI. Use when the user invokes $kelly-creators or /kelly-creators, mentions influencer or creator marketing, creator discovery, fit scoring, outreach DMs, campaign briefs, UGC, sponsorship or partnership deals, content review / FTC disclosure gating, or campaign ROI, or wants to review/approve agent-drafted creator outreach before it is sent through other channels.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Busabase-backed App-in-Skill control panel / kanban board for a BD or sourcing team triaging merchant and business financing leads for a lender or investment fund. Use when the user invokes $kelly-lead-funnel or /kelly-lead-funnel, wants to review the deal sourcing pipeline, funnel, lead board, or asks to move a lead's stage, reject a lead, add a note, score a lead, or see funnel conversion rates. Deterministic rule-based lead scoring only — never an LLM call — and never sends outreach, signs term sheets, or moves money.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Detects 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 detector 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-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.