В каталоге 182 092 навыков в 14 категориях.
流量分析与抓包
When the user wants to analyze website traffic sources, attribution, or dark traffic. Also use when the user mentions "t...
Analyze network traffic patterns, identify top applications and bandwidth usage, and optimize traffic management. Perfor...
Use when analyzing Xiaohongshu traffic sources, understanding where views and engagement come from, optimizing traffic a...
Analyze website traffic, global rank, engagement metrics, and traffic sources for any domain. Use this skill to evaluate...
Use for API-key health checks, rotation, and monitoring.
Find pages losing clicks, impressions, CTR, or rankings using GSC/GA4 when available or from pasted data. Use when Codex...
Research and compile effective organic traffic and customer acquisition methods for new websites with zero ad spend. Inc...
Report the brand's organic performance from fb.ai — Search Console clicks/impressions/positions plus AI-engine visibilit...
This skill should be used when need prioritize what changed code in repository human must review.
Investigating git history, analyzing regression root causes, and performing code archaeology. Time-travels through commi...
Interactive trail review and update process for Obsidian vault at ~/Brains/brain. Lists available Trails, lets you selec...
Trail renderer skill for motion trails.
Plan and generate trailer-specific pickup plates, title cards, voiceover, music, SFX, and other marketing assets while p...
Build an executable trailer timeline from approved movie material and trailer pickups with deliberate pacing, spoiler co...
Render, QC, approve, and package each trailer, teaser, or vertical trailer using the common executable timeline, audio m...
Design official trailers, teasers, and vertical cutdowns as separate spoiler-aware short-form narratives with target dur...
Trailing stop strategies to lock in profits on NSE/BSE equity positions. Covers ATR trail, structure trail, MA trail, ch...
Trailing-stop plans that lock in profit on NSE/BSE positions: the R-multiple ladder (hold → breakeven at 1R → ATR trail...
Builds and queries multi-language source and binary code graphs for security analysis. Includes pre-analysis passes for...
Builds and queries multi-language source code graphs for security analysis. Includes pre-analysis passes for blast radiu...
Performs graph-assisted triage of a single security finding, SARIF result, weAudit annotation, suspicious function, or r...
Runs a Trailmark structural review gate over a branch, pull request, fix commit, release diff, or git ref range to detec...
Runs full Trailmark structural analysis by building a graph, running `preanalysis()`, and reporting hotspots, taint, bla...
Runs a Trailmark summary analysis on a codebase. Returns auto-detected languages, entry point count, and dependency list...
Expands one confirmed or suspected vulnerability into a Trailmark graph neighborhood of variant candidates by finding si...
Security-focused static analysis and code auditing skills from Trail of Bits. Includes CodeQL deep analysis, Semgrep sca...
Query a user's TrailSnap photo library through scoped MCP tools to find photos, reconstruct memories, build person timel...
Query photos, albums, locations, tags, and people from a TrailSnap instance through its command-line client. Use when Tr...
TrailSnap 仓库提交、推送、需求平台与 PR 工作流规则。Use when preparing commits, pushing branches, managing the corresponding platform requi...
为 TrailSnap（行影集）制作新版本宣传与日常运营内容，包括选题、推广计划、海报、小红书和抖音图文/plog、公众号文章及数据复盘。适用于产品曝光与开源 Star 增长；技术发版、代码交付不属于本技能。
逐步检索并理解用户相册，适合回答照片、人物、地点和时间相关问题。
基于 TrailSnap（行影集）现有设计系统设计、实现和审查前端 UI。适用于 package/website 的新页面、组件、布局、主题、移动端适配与界面改版；纯后端任务和其他项目不适用。
Teaches celis the person's taste for one kind of thing, such as a logo, an error message or a commit message, from 4 var...
Auto-generate custom agents and skills for remaining capability gaps after assembly. Creates definitions based on projec...
Nechá agenta nastudovat zadaný vstup a zapsat si z něj do vlastní trvalé paměti zobecněný poznatek, který se týká jeho r...
Train a character/identity LoRA locally on FLUX.1-dev via the comfyui-mcp train_* tools (GPU Docker + ostris ai-toolkit)...
Voice-first runtime steering + nightly deep analysis to learn per-user conversation steering priors.
Use this skill when selecting a TPR-registered Training Provider for behind-the-wheel ELDT training. Covers the registry...
Guidance for training FastText text classification models with constraints on model size and accuracy. This skill should...
RL 强化学习训练与推理（rollout）路径的算子差异性扫描。当用户提供训练启动脚本路径，要求对比 Megatron 训练路径与 vLLM 推理路径的算子差异（尤其是融合算子 vs 单算子不一致）时使用此 skill。典型触发词包括"训推...
Entrainer le modele ML AML
Execute model training with optimization algorithms. Use when running training loops on datasets.
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding mode...
Train Test Splitter - Auto-activating skill for ML Training.Triggers on: train test splitter, train test splitterPart of...
Design lawful training, rehearsal, and evaluation packages for readiness and mission-support teams. Use when preparing c...
Mandatory training archive with model gating (APPROVED/REVIEW/DROP). Trigger when: (1) training run completes, (2) need...
Monitors running spatial experiments. Checks output files, log files, and process status. Categorizes results as OK, STA...
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasti...
Checklist for editing training code. Trigger when: (1) modifying training notebook, (2) changing GPUEnvConfig, (3) chang...
This skill should be used when generating actual training content including learner workbooks, facilitator guides, pract...
Generate a comprehensive HTML training dashboard showing progress toward half marathon training goals. Outputs a single...
Review training datasets for backdoor triggers, label flipping attacks, targeted behavioral modification, and data colle...
Detects training and fine-tuning pipelines that ingest external data without integrity gating. Use when writing fine-tun...
Validate ML training datasets for quality, bias, completeness, label consistency, and distribution coverage.
This skill should be used when designing training programs, individual workshop sessions, or learning modules using evid...
Internal /ace:run step — Write the LLO/FLW training FAQ from the PDD and apps.
Internal /ace:run step — Grade the training FAQ.
Internal /ace:run step — Write the step-by-step FLW guide to the apps.
Improve LLM outputs without parameter updates using learned token priors that guide inference. Trigger: optimize agent b...
Training improvements: LR warmup, validation intervals, reward weights. Trigger when: (1) training unstable in early epo...
Analyze training patterns, performance, and physiological data using advanced computational models.AUTO-ACTIVATES when u...
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use w...
Internal /ace:run step — Write the LLO operations guide.
Build train machine learning models with automated workflows. Analyzes datasets, selects model types (classification, re...
Train machine learning models with automated workflows. Analyzes datasets, selects model types (classification, regressi...
Extracts specific training metrics from experiment logs at regular intervals and saves them to a CSV file for analysis....
This skill should be used when designing measurement plans and evaluation strategies for training programs. Use this ski...
Navigate web-based trainings that gate progress via timers/videos/disabled Next buttons.
Advanced techniques for optimizing LLM fine-tuning. Covers learning rates, LoRA configuration, batch sizes, gradient str...
Templates and patterns for common ML training scenarios including text classification, text generation, fine-tuning, and...
Design legal compliance training program for the team
Create personalized training plans for 5K, 10K, Half Marathon, and Marathon races. Use when the user requests a training...
Use to design non-clinical training programs for healthcare workers, including AI literacy, onboarding, department works...
Produce a professional training/workshop report as a .docx file. Use this skill whenever the user mentions "training rep...
Fix PPO training early-stop issues. Trigger when: (1) impossible drawdown values (>100%), (2) training stops too early,...
This skill should be used when reviewing and validating training materials, workshop designs, facilitator guides, or lea...
Audits a project for mock data, placeholder content, hardcoded shortcuts, and anything else that's "not the real thing"...
This prompt specifies a cinematic, photochemically inspired video scene on an urban commuter platform at dawn, detailing...
Master Rust traits, generics, and type system. Use when defining traits, generic functions/structs, trait objects, assoc...
Use when working with trait extraction, place enrichment, or the learning loop. Load for understanding how the system le...
Orchestrate complete TraitorSim workflows from persona generation to game execution and analysis. Use when starting new...
This skill should be used when the user asks about "Effect Equal", "Effect Hash", "Equivalence", "Order", "structural eq...
Reusable behaviour shared across multiple unrelated classes. Traits provide shared Eloquent scopes, accessors, lifecycle...
고유한 저자 페르소나를 구성하기 위한 특성 DNA 라이브러리. 목소리 패턴(격식체, 대화체, 서사체, 기술체), 전문성 영역(아키텍처, 구현, 산업, 교육), 관점 스타일(분석적, 경험적, 비판적, 비전적), 어조...
Path traced by solution through phase space
Schema, grounding rules, outcome status and cost ledgers for agent trajectories. Use when an agent must record, replay o...
Workflow for pseudotime, lineage branching, and state-transition analysis in single-cell data.
Review how an agent reached its result, not only whether the result passed, covering tools called, detours, unverified a...
Classify task traces, detect risky engineering trajectories, score advisory bad-state risk, and route to the least disru...
Track and view your watched movies and TV shows via trakt.tv. Use when user asks about their watch history, what they've...
Discover and compare Trakt.tv trending, popular, and anticipated movies and shows, and manage user-scoped history and wa...
Complete autonomous DJ system for Traktor Pro 3 with MIDI control, intelligent track selection, energy flow management,...
Traktor Pro QML modding handbook
电车站.skill：去AI味的实证方法论。核心判断来自一次可复现的对照实验：AI味分四层（词汇<句式<结构<经验），病灶在结构层和经验层，人味不是删出来的，是用真实素材换出来的。两种模式：(1)诊断——给文稿做AI味分层报告；(2)改写——...
Analyze Ethereum transactions including details, status, gas usage, and internal transfers
How WAL mechanics, checkpointing, concurrency rules, recovery work in tursodb
Transaction 경계 전문가. TransactionManager(단일 Port persist), ReadManager(단일 Query Port findBy/get), CommandFacade(2+ Manager...
Transaction 경계 전문가. TransactionManager(단일 Port persist), ReadManager(단일 Query Port findBy/get),CommandFacade(2+ Manager...
Use when submitting transactions to Midnight contracts, tracking transaction status, implementing retry logic, building...