Explorar skills

Coverage-aware agent workflow tool. Use PROACTIVELY before modifying files, making architecture decisions, debugging, or reviewing code. Reports which symbols Claude has read (Seen%) vs read in full (Full%). Use MCP tools mcp__ambit__coverage or mcp__ambit__coverage_file when available; fall back to bash.

This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches. NOT for evaluating agent quality or building evaluation rubrics (use agent-evaluation), NOT for multi-agent coordinat

PTrade/SimTradeLab strategy development guardrails. Auto-loads PTrade API reference, enforces platform constraints (no f-string, no import io/sys), validates lifecycle function usage, and prevents common API misuse. Use when writing, editing, or reviewing any PTrade strategy code or SimTradeLab backtest code. TRIGGER: when editing files in strategies/, src/simtradelab/ptrade/, or any .py file that

Use when the user asks to create, refine, evaluate, or optimize an LLM prompt. Do NOT trigger for Claude Code skills (use skill-creator) or when rewriting an existing skill (use transformer). Example triggers - "write a prompt for my summarizer", "tighten this system prompt", "evaluate this agent prompt".

Um wrapper CAD com foco em diagnósticos para Build123d, oferecendo asserções de interferência/folga em nível de montagem e verificações opcionais de imprimibilidade por peça. Carregue-o antes de editar um `assembly.py` que usa o wrapper ou interpretar seu JSON de diagnóstico; ele é acionado ao executar `khana check`/`build`/`view`/`draw` ou editar um arquivo que importa `cad_kha`.

Design, evaluate, and iteratively improve prompts for LLMs — system prompts, few-shot examples, reasoning structures, and instruction templates. Use when the user asks to improve a prompt, write a system prompt, optimize LLM instructions, reduce hallucinations through prompt structure, test prompt variants, or apply prompting techniques (structured reasoning, ReAct, few-shot, structured output). N

Funnel-with-gate workflow for reducing LLM costs without degrading quality. Starts with diagnosing the cost surface using cloud-finops (specifically the finops-for-ai and finops-anthropic references), then applies context-optimization to reduce context per call, context-compression to compress what can't be reduced, prompt-engineering for shorter prompts and better model selection, and uses agent-

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Keywords: 创建技能, 技能开发, 构建claude技能, 技能设计, 技能模板, create skill, build skill, develop skill, skill creation, skill development, skill template, skill design, skill builder, skill

Arnês de navegador autorreparável que permite que LLMs completem qualquer tarefa. Esta é a versão em Rust.

Guidelines for creating unbiased test fixtures that integrate with project infrastructure. Use when creating fixtures for manual testing, setting up E2E test scenarios, or building code samples with deliberate issues for LLM review. Ensures fixtures work with hook automation and pass Phase 1 checks.

Background knowledge about how hashtags work on the Fediverse, including at the ActivityPub wire-format level. Load when the user asks about implementing hashtags, detecting hashtag support in a codebase, how hashtag federation works, why hashtag search returns incomplete results, how to follow hashtags, the Hashtag type in ActivityPub, the tag property on Note objects, case sensitivity in hashtag

Background knowledge about WriteFreely, the open-source federated blogging platform written in Go (AGPL-3.0) by Matt Baer / Musing Studio. Covers the origin story (Write.as anonymous writing platform launched 2014, open-sourced as WriteFreely November 2018 after adding ActivityPub), the write-only/broadcast federation model (blogs can be followed but cannot follow others, no incoming comments/repl