Hugging Face transformer model fine-tuning and inference for intent classification
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。 — from c2kaka/my-blog
Strip AI-generated writing patterns from business text to make it read like a real person wrote it. Use when reviewing or editing any text that sounds robotic, generic, or…
Detects and eliminates 40 AI writing tells across vocabulary, structure, formatting, content inflation, and communication artifacts.
Humanize AI-generated text to bypass detection. This humanizer rewrites ChatGPT, Claude, and GPT content to sound natural and pass AI detectors like GPTZero, Turnitin, and…
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. — from general/language-learning
Usuwa ślady pisania AI z polskiego tekstu. Używaj przy edycji lub przeglądaniu tekstu, aby brzmiał bardziej naturalnie i po ludzku.
Remove marcas de texto gerado por IA em português do Brasil, tornando a escrita mais natural e humana.
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。 — from…
去除文字中的 AI 生成痕跡。適用於編輯或審閱文字，使其聽起來更自然、更像人類書寫。 基於維基百科的「AI 寫作特徵」綜合指南。偵測並修復以下模式：誇大的象徵意義、 宣傳性語言、以 -ing 結尾的膚淺分析、模糊的歸因、破折號過度使用、三段式法則、 AI 詞彙、否定式排比、過多的連接性短語。
Drive Hunk, the terminal diff viewer, as a live local review surface in tmux. Use when reviewing changes through Hunk: launching a session, seeding agent notes, collecting inline…
Skill for HVAC system design and analysis per ASHRAE standards including load calculations, equipment selection, and energy efficiency analysis
Explains hybrid search in Qdrant. Use when someone asks 'how do I setup hybrid search?', 'how to combine keyword and semantic search?', 'sparse plus dense vectors?', 'missing…
Hydrologic modeling skill for rainfall-runoff analysis, flood frequency, and watershed analysis
Aspen HYSYS integration skill for dynamic simulation, pressure-flow networks, and process dynamics
Guides porting existing Android 2D apps to Meta Quest and Horizon OS — input adaptation, panel layout, and design requirements. Use when adapting a mobile Android app for Quest.
Upgrades Meta Quest apps to newer Horizon OS SDK versions — migration guides, deprecated API replacements, changelog.
Analyzes Meta Quest and Horizon OS VR performance using Perfetto traces — frame timing, CPU/GPU bottlenecks, render pass analysis.
MANDATORY pre-flight check before answering any question or writing any code related to Meta Quest VR headsets (Quest 2, Quest 3, Quest 3S, Quest Pro) or apps that target them.
Profiles Meta Quest and Horizon OS application CPU performance using simpleperf — workload classification, CPU hotspot recording, kernel overhead measurement.
Guides end-to-end Meta Quest and Horizon OS app submission to the Meta Horizon Store — build validation, VRC compliance, asset preparation, upload, and submission tracking.
Debugs Meta Quest and Horizon OS VR/MR applications using the metavr CLI — view logs, capture screenshots, diagnose common issues.
Implements internationalization (i18n) in React applications. Covers user-facing strings, date/time handling, locale-aware formatting, ICU MessageFormat, and RTL support.
Medical device software lifecycle management skill implementing IEC 62304 requirements
IFC model analysis skill for validation, property extraction, and model comparison
Medical image processing algorithm validation skill for segmentation, detection, and analysis algorithms
Set up image factory pipelines. CI Image Factory migrates Harness CI step images to your private container registry.
Наложить пронумерованную сетку на изображение для определения пропорций колонок
GLAW Immigration — the firm's business and founder immigration seat. Maps and papers the right visa or green-card path for founders, investors, and key employees: treaty investor…
**IMPACT ANALYZER v1.0** - '영향도', '영향 범위', '변경 영향', '리팩토링 영향', '이거 바꾸면', '어디에 영향', '위험도' 요청 시 자동 발동. codebase-graph 기반 변경 전파 분석. 직접/간접 영향, 위험도 점수, 테스트 범위 제안. 코드 수정 전 필수 분석.
Implement features, write code, and build functionality following best practices and language conventions.
Provides step-by-step implementation guide for creating CQRS command or query handlers following project patterns with ServiceResult, dependency injection, and handler…
Implements retry logic with exponential backoff and jitter for async operations. Use when implementing external service calls, database operations, network requests, or any…
Triage and batch-implement Claude-tagged Things todos as PRs for the claude config repo. Use when the user wants to work on their Claude Code improvement backlog, process Things…
Incident management platform integration for PagerDuty, Opsgenie, and related tools
International shipping terms validation and documentation skill ensuring trade compliance
Industry and competitive analysis skill with Porter's Five Forces and market structure analysis
Overzicht van alle internetstandaarden die internet.nl test. Routing naar sub-skills voor web, mail, API en toolbox.
Reproduce the Artificial Analysis (AA) language-model performance workload shapes against an OpenAI-compatible chat endpoint using NVIDIA AIPerf.
Correlate DCGM Prometheus byte-traffic counters with an inference-perf-bench sweep window to compute byte-grounded workload-level Speed-of-Light.
Render cross-model fleet leaderboards from the local perf-report campaigns in ONE command (`perftunereport fleet_leaderboard`): a latency tier (aa-1k/10k/100k tok/s/user + TTFT +…
Diff the compiled FX / Inductor graphs across two vLLM versions or two helm configs to see exactly which fused kernels / passes / partitions changed.
Capture per-kernel CUDA hardware-counter data (occupancy, achieved warps active, regs/thread, smem/block, DRAM throughput, arithmetic intensity, branch divergence %, warp-stall…
Capture per-kernel CUDA profile data from a live vLLM inference pod via an nsys debug sidecar (no production image rebuild).
White-box debug a custom CUDA/CUTLASS kernel producing a WRONG numeric result (over-amplification, NaN, coherence) after black-box bisection is EXHAUSTED: every external lever…
Drive lm-eval-harness quality evals (GPQA, MMLU-Pro) inside model pods plus optional ExternalEval (externally operated).
Bridge between the inference-perf-bench / ai-bench output bundle and the profile-and-optimize perf-baseline registry.
Canonical inference perf-bench skill (formal name. The colloquial alias is `ai-bench` - identical behaviour).
Build a multi-page benchmark report PDF (scatter panels + per-concurrency heatmap tables) from `vllm bench sweep serve_workload` and/or AIPerf outputs, in the GLM-5.1 reference…
Closed-loop speculative-decoding-as-a-service orchestrator -- a self-hosted analog of Fireworks FireOptimizer's adaptive speculative execution.
Tune a speculative-decoding DRAFT head's TRAINING hyperparameters (global batch, learning rate, accumulation, warmup) for a target LLM, optimizing the TRUE serving in-engine…
Search a vLLM serving model's config space for its best inference performance: a `perftunereport campaign_run` matrix sweep over concurrency x max_num_batched_tokens x…
Process audiobooks from the inbox: transcribe to text and organize audio for voice training. Part of Horus's learning pipeline. — from grahama1970/agent-skills
Manage book library via Readarr, search for books, and monitor downloads. Handles service health checks and API interactions. Part of Horus's learning pipeline.
Scan one or more external-content items for prompt injection attempts and return a structured verdict.
Insert urgent work as decimal phase (e.g., 72.1) between existing phases — from NafisRayan/100x-Agent-Toolkit