「haiku」の検索結果

PostToolUse hook that compresses Playwright MCP tool output using Haiku summarization — Layer 4 of the token defense stack

日本語の概要は準備中です。原文の説明を表示しています。

Construa, depure e otimize aplicativos com Claude API / SDK Anthropic. Aplicativos construídos com esta skill devem incluir cache de prompt. Também lida com migração de código Claude API existente entre versões de modelo (4.5 → 4.6, 4.6 → 4.7, substituições de modelo descontinuado). TRIGGER quando: código importa `anthropic`/`@anthropic-ai/sdk`; usuário solicita Claude API, SDK Anthropic ou Managed Agents; usuário adiciona/modifica/afina um recurso Claude (cache, thinking, compaction, tool use, batch, files, citations, memory) ou modelo (Opus/Sonnet/Haiku) em um arquivo; dúvidas sobre prompt caching / cache hit rate em um projeto SDK Anthropic. SKIP: arquivo importa `openai`/SDK de outro provedor, nome de arquivo como `*-openai.py`/`*-generic.py`, código agnóstico de provedor, programação geral/ML.

日本語の概要は準備中です。原文の説明を表示しています。

Migre prompts e código de Claude Sonnet 4.0, Sonnet 4.5 ou Opus 4.1 para Opus 4.5. Use quando o usuário quiser atualizar sua base de código, prompts ou chamadas de API para usar Opus 4.5. Lida com atualizações de string de modelo e ajustes de prompt para diferenças comportamentais conhecidas de Opus 4.5. NÃO migra Haiku 4.5.

日本語の概要は準備中です。原文の説明を表示しています。

Audit BMAD source files for file-reference convention violations using parallel Haiku subagents. Use when users requests an "audit file references" for a skill, workflow or task.

日本語の概要は準備中です。原文の説明を表示しています。

Use when designing, running, or judging an experiment on a Syntropic137 workflow - comparing prompt variants, fan-out vs single agent, adversarial cross-model review, model selection (can Haiku do this job), phase splits, or tool grants. Trigger phrases include "run a workflow experiment", "A/B the workflow", "does fan-out help", "which model for this phase", "is this prompt better", "measure review quality", "why did the workflow do that". Do NOT use for a one-off workflow run that is just doing work, for authoring a workflow that is not being compared against anything, or for debugging a single failed execution (that is ordinary debugging).

日本語の概要は準備中です。原文の説明を表示しています。

Decomposes a large implementation plan into small-model-sized tasks executed by supervised worker agents (e.g. Haiku) in dependency-ordered parallel waves, with a plan-first approval gate inside every task, file-based state for context compaction, and a hard escalation ladder. Use when a master plan or multi-workstream feature is too large for one session and should be executed cheaply by many small agents under frontier-model supervision.

日本語の概要は準備中です。原文の説明を表示しています。

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

日本語の概要は準備中です。原文の説明を表示しています。