Browse 181,320 skills across 14 categories.
A skill with triple dashes in the markdown body
Starts working on a task using the TRIPLE protocol, as the impl agent.
Launch three independent AI code reviewers (Opus, Gemini, Codex) to QA/QC code or notebooks. Each reviewer writes findin...
Helps define a TASK.md for the current task using the TRIPLE protocol, as the lead agent.
Reviews a task using the TRIPLE protocol, as the review agent.
Low-ticket tripwire funnel that converts cold leads into buyers with an irresistible $7–$47 offer, then upsells to the c...
Tristian Walker brand design system — warm, literary, adult. Author of "The Quiet Line." Burnt sienna on cream, Merriwea...
NVIDIA Triton Inference Server 배포 및 관리. "triton 서버", "triton 실행", "모델 서빙", "inference server" 요청 시 활성화됩니다.
Configure triton inference config operations. Auto-activating skill for ML Deployment. Triggers on: triton inference con...
Triton Inference Config - Auto-activating skill for ML Deployment.Triggers on: triton inference config, triton inference...
擅长在 Ascend NPU 平台上编写高效 Triton 算子的性能优化专家。 按照严格的顺序逐步优化 Triton 代码，每次只尝试一个优化点， 确保优化前后功能一致、精度一致。 ⚠️ 只能使用本 skill 规定的优化方式，禁止使用任...
在昇腾 NPU 上测量单算子的 MFU（Model FLOPs Utilization，官方 operator_mfu 等价口径）， 并按 kernel 拆解瓶颈，回答"低是低在哪一段、还有没有得优化"。 覆盖目录适配、极限 MFU 的 (...
Triton Ascend 算子代码生成 Skill — 根据算子任务格式任务描述生成高性能 Triton Ascend 内核代码。支持首次生成和基于错误反馈的迭代优化。 触发：当用户需要根据任务描述生成或迭代修复 Triton Ascen...
Triton Ascend 算子算法草图设计 Skill — 根据任务描述设计高质量的算法草图（sketch）， 用于指导后续代码生成。支持首次设计和基于历史上下文的迭代优化。 触发：当用户需要为 Triton Ascend 算子设计算法草...
算子代码验证 Skill — 按照标准验证流程验证生成的内核代码。 创建验证项目文件，调用 scripts/verify.py 运行验证，验证通过后 调用 scripts/benchmark.py 进行性能测试并收集结果。 触发：当用户需要...
Triton-Ascend 算子精度对齐调试专家。当算子精度校验（MERE/MARE）不通过时， 按照系统化的五阶隔离法定位 ULP 级差异根因，并提供修复方案。 尤其擅长处理编译器 scalar/vector 浮点行为差异、常量除法精度偏...
Install Triton + SageAttention to accelerate ComfyUI (the sageattn attention_mode and inductor torch.compile used by Wan...
Setting up Triton servers for multi-framework hosting.
Triton-Ascend 算子的 simulator 流水**采集与诊断**专家。用 msprof op simulator 采集 per-instruction pipe 统计，定位真实瓶颈（而非猜测），产出**诊断报告**：瓶颈类型...
从用户 PyTorch/Python 代码中提取算子实现，构建为算子任务格式的标准化 任务文件。支持两种模式：单 case（单一自包含 .py，get_inputs 返回单组）和 多 case（.py + 同名 .json 配对，get_i...
Scan containers, filesystems, repositories, and infrastructure code with Trivy, then triage CVEs and configure CI thresh...
Scan container images, filesystems, git repos, and existing SBOMs for CVEs, secrets, and license violations using Trivy....
This skill should be used when scanning container images, filesystems, or repositories for vulnerabilities using Trivy....
Runs Trivy's misconfiguration scanner (`trivy config`) against IaC directories to detect security issues across Terrafor...
Configures and runs Trivy for container image scanning: Aqua Security's all-in-one scanner combining vuln + secret + mis...
Scan containers and dependencies for vulnerabilities with Trivy
TRIZ cross-domain analogical reasoning to find solutions from adjacent fields.
Applies TRIZ cross-domain analogical reasoning to find solutions from adjacent fields. Use when stuck on a problem and n...
Raises and scores a software Technology Readiness Level (TRL 1–9) in a loop. Each cycle collects facts-only evidence, ha...
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Lea...
Use and modify TRL, the Hugging Face Transformers Reinforcement Learning library for post-training, CLI workflows, data/...
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRP...
Setup and installation of TRL (Transformer Reinforcement Learning) library with compatible torch/transformers versions....
Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO...
Guides trlX LLM post-training, RLHF, Accelerate, configuration, sweeps, and optional NeMo/Megatron workflows.
End-to-end Topic Research Mining (TRM) closed-loop pipeline across all registered NotebookLM notebooks in trm-vault. Run...
Use when inspecting, claiming, investigating, annotating, or resolving operational defects in the TRM DevOps triage queu...
Post-ingest-batch feedback pass for TRM — classifier/extraction quality, OCR latency vs. budget, candidate new-topic sur...
DevOps self-healing triage, research escalation, and Sigil biometric guard skills
Instant status table across all TRM research topics — counts, staging backlog, extract lag, staleness, uncommitted files...
Autonomous task card triage engine applying YAGNI evaluation, reversibility classification, and GitHub Issue promotion p...
Assist with TRON TRX transactions, bandwidth, energy, and TRC-20 token transfers.
Create production-ready Grafana dashboards for TRON team services including consumer dashboards, task metadata, RQ rules...
Investigate runtime or production issues from logs, errors, or unexpected behavior (Marcus + Alex workflow)
Use when Forge needs deep bug diagnosis instead of a quick patch. Trigger on intermittent bugs, unclear root cause, mult...
Diagnose common cqs issues — stale index, model download, schema mismatch, connection issues.
Isolate root causes and propose targeted fixes with clear validation steps.
Read-only diagnostics and troubleshooting for SignalRoom. Use when debugging issues, checking system health, analyzing l...
Diagnose No Johns setup issues. Checks Python, Dolphin, ISO, arena connectivity, and common problems.
Systematic debugging with 5-step loop for issues in spaces/[project]/. Use when encountering bugs, test failures, or une...
프로젝트 실행 중 발생하는 오류를 진단하고 해결하는 스킬. "/troubleshoot"를 입력하거나, 에러 메시지를 붙여넣거나, "안 돼요", "오류가 나요", "서버가 안 떠요" 같은 요청에 트리거된다. 기존 트러...
Diagnoses Kubernetes pod issues automatically. Use when pods are in CrashLoopBackOff, ImagePullBackOff, Pending, or Erro...
Troubleshooting protocol with MiniMax subagent delegation - NEVER stop early, use all resources before asking user
Diagnose dotnet-msbuild binlog MCP startup failures. USE FOR: CONNECTION_CLOSED, binlog server won't connect, missing bi...
Diagnose and fix common Algorand errors including smart contract failures, transaction rejections, and SDK exceptions. U...
Diagnose and fix common local development environment issues
Debugging, error diagnosis, and problem resolution. USE WHEN user mentions bugs, errors, crashes, exceptions, not workin...
Proactively detect and diagnose DAPR runtime issues based on error patterns, log analysis, and common misconfigurations....
Diagnose and fix common issues in the flight-path project: build failures, test failures, port conflicts, Docker problem...
Debugging and problem-solving workflow. Use when stuck on an issue for more than 30 minutes, encountering cryptic errors...
Common ComfyUI errors and fixes — OOM, missing nodes, dtype mismatches, black images, and debugging strategies
A robust troubleshooting framework. Use this skill anytime the user reports something isn't working, is buggy, or is thr...
Use when LibreChat has errors, containers won't start, API calls fail, file uploads break, models return errors, or some...
Kubernetes 故障排查
Troubleshooting guide for The Fold - daemon issues, session corruption, file locations, and common problems. Use when ./...
DevOps troubleshooting runbooks for Docker, Kubernetes CrashLoopBackOff/OOMKilled/ImagePullBackOff, GitHub Actions, DNS,...
Maintains the ansible/roles/troubleshooting_tools Ansible role that installs a baseline set of diagnostic packages and o...
Diagnoses and resolves MCP server registration failures, GPU detection, BigQuery authentication, index build failures, i...
Troubleshoot Astronomer production deployments with Astro CLI. Use when investigating deployment issues, viewing product...
Standard protocol for debugging and fixing issues across the stack. Use when encountering errors or unexpected behavior.
Diagnose and fix third-party library loading failures in Vite, Webpack, or other bundlers. Use when encountering "Failed...
Troubleshoots infrastructure and application configuration items in Mission Control by diagnosing health issues, analyzi...
Diagnoses common datavault4dbt failures — satellites capturing too many or too few rows, multi-source high-water-mark is...
Use when SSH connection fails, host key mismatch, NixOS issues, or verifying devbox is properly configured
Use when execute command encounters errors - diagnostic guide for phase failures, parallel agent failures, merge conflic...
Use when diagnosing openai_harmony.HarmonyError or gpt-oss tool calling issues with vLLM. Identifies error sources (vLLM...
Эксперт по troubleshooting гайдам. Используй для создания диагностических процедур, FAQ и решения проблем.
Troubleshooting Guide Creator - Auto-activating skill for Technical Documentation.Triggers on: troubleshooting guide cre...
問題解決を効率化するトラブルシューティングガイドの設計スキル。診断フロー、問題分類、解決手順書を体系的に設計します。Anchors:• 『Don't Make Me Think』（Steve Krug）/ 適用: ユーザビリティ設計 / 目...
Use when creating troubleshooting guides and diagnostic procedures for operational issues. Covers problem diagnosis, roo...
Debugs and troubleshoots Mission Control health checks by analyzing check configurations, reviewing failure patterns, an...
Investigates Mission Control notifications to identify root causes and provide remediation. Use when users mention notif...
tRPC end-to-end type safety, procedures, routers, middleware, and React integration.
tRPC v11 API layer with Zod and Ed25519 auth. Use when working on files in src/server/.
tRPC end-to-end type-safe APIs for TypeScript with React Query integration and full-stack type safety
tRPC for type-safe APIs. Covers routers, procedures, and React Query integration. Use for end-to-end type-safe APIs. US...
Builds type-safe APIs with tRPC including routers, procedures, context, and client integration. Use when creating end-to...
Guidelines for writing Next.js apps with tRPC v11 for end-to-end typesafe APIs
Expert guidance for tRPC v11 type-safe APIs, procedures, middleware, error handling, and TanStack Query integration. Use...
Auto-activates when user mentions tRPC, type-safe APIs, procedures, or tRPC routers. Expert in tRPC including router set...
tRPC — end-to-end type-safe APIs with routers, procedures, middleware, context, React Query.
You are an expert in tRPC, the framework for building type-safe APIs without schemas or code generation. You help develo...
End-to-end type-safe API testing with tRPC covering router testing, middleware testing, subscription testing, and client...
Build end-to-end typesafe APIs with tRPC. Covers routers, procedures, Zod validation, React Query integration, and Next....
tRPC end-to-end type-safe API patterns. Router setup, procedures, middleware, context, client configuration. Use when bu...
tRPC router patterns for Otaku Odyssey. Use when creating or modifying tRPC routers, procedures, or API endpoints.
Query and manage local tRPC documentation mirror (25 docs). Search tRPC topics for end-to-end typesafe APIs, routers, pr...
Build end-to-end type-safe APIs with tRPC — routers, procedures, middleware, subscriptions, and Next.js/React integratio...
tRPC v11 patterns for T3 Turbo App Router — queryOptions/mutationOptions, type inference with RouterOutputs/RouterInputs...
tRPC API patterns using Vertical Slice Architecture. Use when building tRPC procedures, routers, and handling API concer...