В каталоге 182 820 навыков в 14 категориях.
Batch Inference Pipeline - Auto-activating skill for ML Deployment. Triggers on: batch inference pipeline, batch inferen...
Parallel multi-user processing using Claude Code native teams. Leader spawns workers per user, each runs /ingest-dm, lea...
Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations...
Message Batches API for Claude with 50% cost savings on bulk processing. Activate for batch jobs, JSONL processing, bulk...
Computational workflows for battery electrode characterization: voltage profiles, ion transport, and electrochemical sta...
Prüfung der Baugenehmigung: bauplanungsrechtliche Zulässigkeit (§§ 30–35 BauGB; faktisches Gebiet § 34 II BauGB iVm BauN...
Bayesian approach to statistical inference and decision-making. Covers prior specification, likelihood functions, poster...
八字命理 + 玄学相关数术 (子平派 / 盲派 / 新派 / 紫微斗数边界) (八字命理 / 中华玄学算命 (从业者 + 学习者视角)) Master OS — automated mastery of 八字命理 / 中华玄学算命 (从业者...
Use at the START of any bug bounty hunting session, when switching targets, or when feeling lost about what to do next....
10-agent parallel orchestration for EPIC 9 atomic cycle (fan-out → construction → collision → convergence).
Shared Bulletin Board System (BBS) coordination protocol for web-research swarm subagents. Covers posting and reading fr...
Ablation variant of bbs-coordination-web with the idle peer-review protocol ("When Idle") removed (GATE 2 OFF — no board...
This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belie...
Extract structured domain knowledge from AI models in-session or from local open-source models via Ollama. No API key ne...
Track issues with bd/br, triage with bv, and convert plans to beads.
Git-friendly, crash-recoverable state persistence for the Gastown orchestration chipset. Manages agent identities, work...
Beatoven.ai royalty-free music generation: compose tracks, poll tasks, download audio, fetch individual stems. Trigger p...
Render Mermaid diagrams as ASCII/Unicode art for terminal display or as SVG files. Use when visualizing flowcharts, stat...
Extended thinking mode. USE WHEN be creative, deep thinking, deep thinking, extended reasoning. SkillSearch('becreative'...
AWS Bedrock foundation models for generative AI. Use when invoking foundation models, building AI applications, creating...
Amazon Bedrock AgentCore platform for building, deploying, and operating production AI agents. Covers Runtime, Gateway,...
Amazon Bedrock AgentCore Memory for persistent agent knowledge across sessions. Episodic memory for learning from intera...
Amazon Bedrock AgentCore multi-agent orchestration with Agent-to-Agent (A2A) protocol. Supervisor-worker patterns, agent...
Amazon Bedrock Agents for building autonomous AI agents with foundation model orchestration, action groups, knowledge ba...
Amazon Bedrock Automated Reasoning for mathematical verification of AI responses against formal policy rules with up to...
Amazon Bedrock Model Customization with fine-tuning, continued pre-training, reinforcement fine-tuning (NEW 2025 - 66% a...
Amazon Bedrock Prompt Management for creating, versioning, and managing prompt templates with variables, multi-variant A...
Wirksamkeitskontrolle befristeter Arbeitsverträge nach dem TzBfG – Schriftformerfordernis § 14 Abs. 4 TzBfG, Sachgrundbe...
创建一个名为 personal-greeting 的 Skill，它会：
AI operasyonel modları (beyin fırtınası, uygulama, hata ayıklama, inceleme, öğretme, dağıtım, orkestrasyon). Görev türün...
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on ta...
Use when the user wants more human-like AI responses — less robotic, less listy, more authentic. Triggers: 'behuman', 'b...
Talk to Ben Heath Youtuber about their expertise. Ben Heath Youtuber provides authentic advice using their mental models...
Read artifacts from the shared bench — the workspace where desks leave findings, verdicts, and work products for each ot...
Fetch benchmark performance data from 6 leaderboard websites using Playwright MCP and update model manifests with the la...
Standardized compliance QRA benchmarks against candidate LLMs
Quick-start command to run SWE-bench Lite evaluation with sensible defaults.
BentoML skill for model packaging, serving, and containerization.
Prüfung und Strategie der Berufung in Strafsachen – Statthaftigkeit § 312 StPO, Einlegungsfrist § 314 StPO, Berufungsbes...
Berufung im Zivilprozess nach §§ 511 ff. ZPO. Statthaftigkeit und Berufungssumme — Beschwer über 600 EUR oder Zulassung...
Prüfung der Beschuldigtenvernehmung – Belehrung über Schweigerecht und Verteidigerkonsultation § 136 StPO, verbotene Ver...
Reveal and teach one to three interview-canonical complete solutions to a LeetCode-style problem, including derivation,...
Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and prope...
Transforms vague Claude Code prompts into effective ones by applying five principles: add verification criteria, provide...
Best practices for designing and structuring agent skills: SKILL.md frontmatter rules, triggers, progressive disclosure,...
Track predictions vs actuals in production: log bets, compute CLV, monitor ROI, detect edge decay, and run significance...
Prüfung der Voraussetzungen einer rechtlichen Betreuung nach der Reform 2023. Erforderlichkeit und Vorrang anderer Hilfe...
Prüfung und Erstellung der Betriebskostenabrechnung im Wohnraummietrecht – Umlagevereinbarung und Abrechnungspflicht § 5...
Ordnungsgemäße Anhörung des Betriebsrats vor jeder Kündigung nach § 102 BetrVG – Entwurf des Anhörungsschreibens, Grunds...
Betriebsübergang nach § 613a BGB – Tatbestand des Übergangs einer wirtschaftlichen Einheit durch Rechtsgeschäft, Eintrit...
当用户明确要求"优化 prompt"、"改进提示词"、"润色指令"或"将简陋 prompt 转换为最佳实践版本"时使用。基于 OpenAI 和 Anthropic 官方最佳实践，对用户提供的简陋 prompt 进行结构化优化，输出符合社区标...
Best practices for AI-driven English-to-Chinese translation. This skill should be used when the user asks to "translate...
Darlegungs- und Beweislast im Zivilprozess nach §§ 138, 286 ff. ZPO. Freie Beweiswürdigung (§ 286 ZPO), gerichtliches Ge...
Prüfung von Beweisverwertungsverboten im Strafprozess – verbotene Vernehmungsmethoden § 136a Abs. 3 StPO, körperliche Un...
Position an AI product when everyone claims AI and skeptics call it "just a wrapper." Find the real wedge (data, workflo...
为视频添加背景音乐。支持免版权音乐来源、音量混合、淡入淡出效果。当需要为视频添加背景音乐、调整音乐与配音音量平衡时使用。
Audit pilot data, models, and workflows for bias and inclusivity issues. Use when evaluating fairness across demographic...
Get the Bible.com Verse of the Day with shareable image.
Load the operations codex that governs everyone acting as or for the owner (the owner, human assistants and AI agents) b...
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when ben...
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to...
Generates Python code using BigQuery DataFrames (BigFrames), the pandas/scikit-learn-style API over BigQuery. Use when w...
Bill Gates - Tecnologia, pensamento sistêmico e filantropia estratégica
Agente que simula Bill Gates — cofundador da Microsoft, arquiteto da industria de software comercial, estrategista tecno...
跨版本符号迁移与二进制差分。当你有旧版本的符号/逆向结果，需要快速迁移到新版本时使用。 适用场景：内核缺 PDB 用旧版符号推导、程序更新后批量迁移函数名、应用更新后快速定位新偏移。 核心方法：用 LLM 做结构化差异比对，程序化输入输出，...
End-to-end binder design using BindCraft hallucination. Use this skill when: (1) Designing protein binders with built-in...
Predicts ADMET properties using ADMETlab 3.0 (119 endpoints with uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D...
Trains and applies base-resolution deep learning models on ChIP-seq / ChIP-nexus / CUT&RUN data. Uses BPNet (Avsec 2021...
Generates 3D conformer ensembles using RDKit ETKDGv3 with knowledge-enhanced distance geometry, MMFF94/UFF force-field o...
Designs novel molecules using REINVENT 4 (de novo, scaffold decoration, linker design, R-group, molecular optimization),...
Predict B-cell and T-cell epitopes for vaccine antigen design and epitope mapping with BepiPred-3.0, DiscoTope-3.0, the...
Basecalls raw Oxford Nanopore signal (POD5/FAST5) into reads with Dorado, choosing the chemistry-matched model and accur...
Aligns Oxford Nanopore and PacBio long reads (and assemblies) to a reference with minimap2 using the error-rate-matched...
Validates predictive models on omics and biomedical data with nested cross-validation, group/batch/temporal-aware splits...
Explains ML predictions on omics data with SHAP, LIME, and permutation importance, handling the correlated-feature trap,...
Builds and validates predictive time-to-event models on clinical and omics data with penalized Cox, random survival fore...
Decision-grade statistical analysis for metabolomics intensity tables. Covers transformation and scaling (Pareto vs unit...
Meta-agent that routes bioinformatics requests to specialised sub-skills. Handles file type detection, analysis planning...
Validates docked / generated protein-ligand poses using PoseBusters physical-validity tests, strain energy quantificatio...
End-to-end biomarker discovery workflow from expression data to validated biomarker panels. Covers feature selection wit...
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular...
Biomolecular molecular dynamics simulations using OpenMM for proteins, solvated molecular systems, drug-protein interact...
Time average of observable along trajectory
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited,...
指导如何创建符合渐进式披露架构的 skill 文档
Use for "are we advertising products about to sell out in our store", "which product ads should we pause for low stock",...
PAI (Personal AI Infrastructure) - Your AI system core. AUTO-LOADS at session start. USE WHEN any session begins OR user...
Evaluates the correlation between automatic text generation scores and human quality ratings. Probes a model's ability t...
Work this site's BlinkPages queue — "blinkpages", "process the queue", "work my queued edits", "apply the edits I queued...
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visu...
This skill should be used when parallelizing multi-issue sprints using git worktrees and parallel agents. Use when tackl...
This skill should be used when parallelizing multi-issue sprints using git worktrees and parallel Claude agents. Use whe...
Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests extern...
BlockRun works with Claude Code and Google Antigravity.
Use when user needs capabilities Codex lacks (image generation, real-time X/Twitter data) or explicitly requests externa...
**v00.33.0**: Ingested from antigravity-awesome-skills community repo
AI citation readiness audit ONLY (does not touch Google rankings, use blog-rewrite for combined Google+AI work). Use whe...
Write a blog post about an ML library or technique for a technical audience
Generates engineering-standard drawings (P&ID, SLD, floor plans, isometric) with ISA-5.1 and IEEE symbol libraries in SV...