「fal」の検索結果

When writing a commit message, branch name or squash title — measure the repo's own convention first, Conventional Commits as fallback — even on a bare 'commit this'.

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。

When running discovery interviews — question-bank build, bias audit, insight extraction. Triggers on 'audit my guide', 'extract insights from transcript', 'is my hypothesis falsifiable'.

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 defining or auditing the activation event — aha-moment selection, retention correlation, falsifiable definition. Triggers on 'what is our aha moment', 'redefine activation'.

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。

Escreva código Elixir idiomático com padrões OTP, árvores de supervisão e Phoenix LiveView. Domine concorrência, tolerância a falhas e sistemas distribuídos.

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。

Extraia dados estruturados de respostas de LLM com validação Pydantic, tente novamente automaticamente extrações que falharem, analise JSON complexo com segurança de tipo e transmita resultados parciais com Instructor - biblioteca de saída estruturada testada em batalha

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 quando o usuário pergunta como construir com produtos ou APIs da OpenAI e precisa de documentação oficial atualizada com citações (por exemplo: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, capacidades ou limites de modelos); priorize ferramentas MCP de docs da OpenAI e restrinja qualquer fallback de navegação a domínios oficiais da OpenAI.

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。

Modelo de reconhecimento de fala de propósito geral da OpenAI. Suporta 99 idiomas, transcrição, tradução para inglês e identificação de idioma. Seis tamanhos de modelo, de tiny (39M parâmetros) a large (1550M parâmetros). Use para speech-to-text, transcrição de podcasts ou processamento de áudio multilíngue. Melhor para ASR robusto e multilíngue.

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。

Agentes autônomos são sistemas de IA que conseguem decompor objetivos, planejar ações, executar ferramentas e se auto-corrigir sem orientação humana constante. O desafio não é torná-los capazes - é torná-los confiáveis. Cada decisão extra multiplica a probabilidade de falha. Esta habilidade cobre loops de agentes (ReAct, Plan-Execute), decomposição de objetivos, padrões de reflexão e confiabilidade em produção. Insight-chave: taxas de erro compostas matam agentes autônomos. Uma taxa de sucesso de 95% por passo cai para 60% b

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。

Orquestração de treinamento distribuído em clusters. Escala PyTorch/TensorFlow/HuggingFace do laptop para milhares de nós. Ajuste de hiperparâmetros integrado com Ray Tune, tolerância a falhas, escalabilidade elástica. Use ao treinar modelos massivos em múltiplas máquinas ou executar varreduras distribuídas de hiperparâmetros.

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。

Ferramentas são como agentes de IA interagem com o mundo. Uma ferramenta bem projetada é a diferença entre um agente que funciona e um que alucina, falha silenciosamente ou custa 10x mais tokens do que o necessário. Esta skill cobre design de ferramentas desde schema até tratamento de erros. Melhores práticas em JSON Schema, escrita de descrições que realmente ajudam o LLM, validação e o emerging padrão MCP que está se tornando a língua franca para ferramentas de IA. Insight-chave: Descrições de ferramentas são mais importantes que implementação

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。

Search the Canvas Notebook workspace with qmd. Use when the user asks to find files, search workspace content, or locate related notes/documents. Default to mode=search (BM25), use vsearch (vector) only as fallback, avoid query (hybrid) by default as it is expensive. Triggers: find files, search workspace, locate notes, Finde, suche, workspace search, content search, qmd.

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 integrating an app with local AI models through Ollama — connection checks, model listing/selection, local-only mode, cloud-fallback consent, visible run states, and recovering from Ollama errors.

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 the user needs to update, improve, audit, or maintain documentation in a project. Covers READMEs, changelogs, API docs, inline comments, missing docs, and overall documentation quality. Works well before releases or when documentation has fallen behind the code.

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, reviewing, or implementing an Inspector panel for an Apple-platform app — contextual selected-item details and safe editable properties, grouped sections, ⌘I toggle, and a compact-width fallback.

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 starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

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。

中国药品权威数据库查询 — NMPA(国家药监局) + CDE(药品审评中心) + DrugBank(英文名/ATC) + PubChem(化学结构) 多源融合,提供(通用名 ↔ 商品名 ↔ 英文名 ↔ 适应症 ↔ NMPA 批文号 ↔ 上市日期)精确映射。Make sure to use this skill whenever the user mentions 药品名 / 通用名 / 商品名 / NMPA / 国药准字 / 药监局 / CDE / drug brand name / generic name / drug registry / pharmaceutical lookup / drug verification / 药物核验 / 商品名对应 / drug cross-check / drug authority lookup. 在任何 medical / market-sizing / clinical / disease-research 报告生成阶段,**所有药品提及必须先调 lookup_drug() 验证**,严禁 LLM 凭训练记忆拼凑通用名↔商品名↔英文名对应关系。LLM 训练截止后药企会更换商品名、新药持续上市,记忆完全不可信。Iron Law:lookup 返回 None → 调用方必须 raise UnverifiedDrugError,不允许 fallback 到记忆。免费公开数据源,跨平台:Claude Code / Codex / Gemini CLI 三端均可 auto-trigger,实现仅依赖 httpx + beautifulsoup4 标准生态,不绑定任何厂商 SDK。

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 adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new note for superseded active records, classifies implemented notes by future decision value, deletes rejected notes that no longer prevent a tempting fallacy, and applies the frozen archived/{kind} triplet and manifest rules.

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。

Run evidence-disciplined Xiaohongshu social listening for foreign pharma employee pain points. Use when the user asks to collect and analyze notes/comments about pharma companies, aliases, roles, compliance, medical affairs, or AI topics, then produce a cited and scored sampled-insight report. Includes independent-evidence counting, MediaCrawler batch collection, and CAPTCHA/461 fallback to Agent Reach/OpenCLI.

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。

Cite-or-Block 架构下的药名 cross-check 原子 skill。给定报告文本与 .cache/<slug>/sources/,扫描每个药品提及 → 找最近 citation 锚点 → 核对锚点指向的源里是否真的提到了此药(通用名 + 商品名)。无字典、无 fallback、源里没 = critical。

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。

提议并执行 rubric 或 bucket 升级。两种模式：**完整 rubric bump**（最高风险动作，5 步强制 + 跨模型审核）和 **--bucket-only 轻量重校**（只换 bucket 边界，不动 rubric 公式）。**Phase 2 强制走 cheat-score-blind sub-agent 给校准池重打分**——不接受 self-scored fallback。触发词："升级 rubric"/"bump rubric"/"更新公式"/"我想加一个维度"/"调整权重"/"重校桶"/"recalibrate bucket"。

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。

Run authorized Xiaohongshu browser workflows for login checks, creator preview fill, publish blockers, final posting, search, export, or approved engagement. Prefer native signed-in Chrome; keep Python/CDP for deterministic batch fallback.

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。

Propose a UI change for human sign-off before building it. The default path deploys a rough live staging preview (with NUXT_PUBLIC_CROUTON_REVIEW=true) so the reviewer pins comments on the real running page. Use --static for the offline HTML/CSS mockup fallback (no deploy available, or speed over fidelity). Invoke for any task that adds/changes a .vue component, a layout, a page, or a theme.

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。

Stress-test plans before committing by imagining they've already failed. Three modes. Diagnostic mode runs a full pre-mortem session — vivid failure scene-setting, six failure categories, the monkey test, and concrete plan adjustments. Review mode checks previous findings monthly for changed probabilities and new failure modes. Alert Triggers mode defines and monitors early warning signals across four trigger categories. Use before any major commitment — strategy, investment, product launch, partnership — or regularly to keep assumptions honest. The planning fallacy is real. The spreadsheet looked great so everyone stopped thinking. This is the antidote. Based on practice by Eterdis (eterdis.com).

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。

Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability to an existing Convex app.

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。