Thread Dump Analyzer - Auto-activating skill for Performance Testing. Triggers on: thread dump analyzer, thread dump analyzer Part of the Performance Testing skill category.
Expert guidance for Three.js and React Three Fiber development with modern React, TypeScript, and performance best practices
ALWAYS use when writing code importing "three". Consult for debugging, best practices, or modifying three, three.js.
Comprehensive procedures for implementing and managing Myco's three-tier configuration architecture with Machine/Grove/Project scope hierarchy.
Throughput Calculator - Auto-activating skill for Performance Testing. Triggers on: throughput calculator, throughput calculator Part of the Performance Testing skill category.
Systematic debugging with persistent state across context resets
清华大学毕业论文 Word → PDF 一键格式规范化工具。输入任意 Word (.docx) 格式的清华毕业论文，自动转换为符合清华 thuthesis 官方 LaTeX 模板规范的高质量 PDF。适用于所有清华学位论文（MBA/学硕/专硕），一条命令搞定。功能：自动提取章节结构、中英文摘要、参考文献（自动生成 BibTeX）、图片（含…
Pre-action checks for AI coding agents — capture thumbs-up/down feedback, generate prevention rules, and block known-bad patterns before they execute.
Generate YouTube thumbnails (1280×720 JPEG) from a video. Picks frames via scene detection, overlays caption text using HTML/CSS rendered by headless Chrome, outputs multiple…
Recognize the common pattern of thyrotoxicosis and organize the focused differential and testing plan.
Internal reference skill — do NOT load directly from user queries. Loaded automatically by tia-openness-roadmap at the start of every C# Openness implementation path.
Fetch structured context from Jira issues, Confluence pages, and GitHub issues/PRs. Auto-loads when a prompt or argument references a ticket key (e.g.
使用 Python CLI 与 Dida365 Open API 交互以管理滴答清单任务/项目，适用于需要通过脚本或命令行调用滴答清单接口的场景（如项目/任务的查询、创建、更新、完成、删除）。
Navigate the Tidal API specification (23,000+ lines OpenAPI spec). Use when implementing Tidal API integrations, adding new endpoints, or understanding API structure.
Add checkpoint/resume, durable queues and cron schedules, cancellation, human approval gates, live progress state, subagent fanout, and per-run cost tracking to AI agent workflows…
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
Invoked by /tidy-code. Reviews source code for structural quality violations (hidden dependencies, god functions, silent failures, deep nesting) across any language.
Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in cod — from…
Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization.
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning.
Record an execution once and replay it deterministically so you can step backward to the moment a value went wrong.
Wraps timecop (github.com/travisjeffery/timecop), the Ruby time-mocking gem: Timecop.freeze, Timecop.travel, Timecop.scale (time-speedup), Timecop.return (cleanup), and…
TimescaleDB - PostgreSQL extension for high-performance time-series and event data analytics, hypertables, continuous aggregates, compression, and real-time analytics
Use when writing Python code that calls datetime.now() or datetime.utcnow() and compares the result against a datetime that came from outside the process (HTTP API, database, JWT…
Use when developing application modules or microservices with the tinystruct Java framework. Covers routing, context management, JSON handling with Builder, and CLI/HTTP dual-mode…
Use when the user works with the `tissue` CLI (shikorism.net / Tissue). Triggers on requests to check in, list/search checkins, manage collections or collection items, view tag…
Extrai texto de PDFs (OCR) e devolve Markdown, usando a CLI `tjocr` da TecJustiça com o binário já EMBUTIDO para Windows e Linux/WSL — não precisa de Go, Python, curl nem compilar…
Explain programming language syntax in Korean with concise examples. Use when user asks about syntax like "python list comprehension", "go goroutine", "rust ownership", or any…
Run full 5-layer analysis (AST, call graph, CFG, DFG, slice) on a specific function for deep debugging or understanding.
Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows — from…
Read the requirement, testing plan, and current codebase, then produce a plan-mode-style implementation plan — backend APIs with full specs and types, data models, frontend pages…
Generate structured AI agent skills (SKILL.md) and llms.txt from your TypeScript API documentation — from pradeepmouli/to-skills
Documentation conventions for generating high-quality AI agent skills from TypeScript source. Use when preparing a library for skill generation, auditing JSDoc quality, f — from…
TypeDoc plugin that generates AI agent skills (SKILL.md) from TypeScript API documentation Use when working with agent-skills, ai, documentation, llm, skill-md, typedoc — from…
PostgreSQL's TOAST (The Oversized-Attribute Storage Technique) — out-of-line + compressed storage for large `varlena` values (text, bytea, jsonb, arrays, xml, tsvector).
OpenTofu infrastructure-as-code reference for HCL syntax, state management, module design, and provider configuration.
Together AI ci integration for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together ci integration".
Together AI common errors for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together common errors".
Together AI core workflow a for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together core workflow a".
Together AI core workflow b for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together core workflow b".
Together AI cost tuning for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together cost tuning".
Together AI debug bundle for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together debug bundle".
Together AI deploy integration for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together deploy integration".
Run inference with Together AI -- chat completions, streaming, and model selection. Use when testing open-source models, comparing model performance, or learning the Together AI…
Install Together AI SDK and configure API key for inference and fine-tuning. Use when setting up Together AI, configuring the OpenAI-compatible API, or initializing the together…
Together AI local dev loop for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together local dev loop".
Together AI performance tuning for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together performance tuning".
Together AI prod checklist for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together prod checklist".
Together AI rate limits for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together rate limits".
Together AI reference architecture for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API.
Together AI upgrade migration for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together upgrade migration".
Together AI webhooks events for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together webhooks events".
Track, optimize, and control token consumption across multi-agent systems. Covers budget allocation, real-time monitoring, cost attribution, per-agent limits, and proactive cost…
Context window coach. Proactive guidance for token-efficient Claude Code projects, multi-agent systems, and skill architecture.
Audit and eliminate token waste from cognitive architecture memory files -- instructions, prompts, skills, and agents
Reviews tokio async runtime usage for task management, sync primitives, channel patterns, and runtime configuration.
Debugging and troubleshooting Tokio applications using tokio-console, detecting deadlocks, memory leaks, and performance issues. Use when diagnosing async runtime problems.
Use when when you need to deploy a Java web application packaged in a Tomcat Docker container to a specified HTTP endpoint, and must verify that the container starts successfully,…
Game audio generation agent. Produces code (Python/JS/TS/Shell) for SFX, BGM, Voice, Ambient, and UI sounds using ElevenLabs/Stable Audio/MusicGen/Suno/OpenAI TTS/JSFXR.
Use when reasoning about the protocol-level cycle by which a language model uses external tools: the four phases (declaration, request, execution, continuation), the…