2,872 件 ・ 関連度順
概要と使いどころ
Expert guide for Vercel AI SDK (Core, UI, RSC), streaming structured data, multi-provider model switching, tool calling loops, and React 19/Next.js 15 AI engineering / Panduan ahli Vercel AI SDK, streaming data terstruktur, dan integrasi AI pada React 19/Next.js 15.
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。
Expert guide for type-safe Python AI agent development with Pydantic AI — dependency injection, structured outputs, model-agnostic routing, and graph workflows / Panduan ahli pengembangan agen AI Python type-safe dengan Pydantic AI.
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。
Smart agentic web data extraction with multi-strategy scraping (Crawl4AI v4, Firecrawl), LLM extraction loops, anti-bot bypass, and structured export / Ekstraksi data web cerdas dan agentic dengan scraping multi-strategi (Crawl4AI v4, Firecrawl), ekstraksi LLM, bypass anti-bot, dan ekspor terstruktur.
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。
Expert guidelines to refactor legacy PHP codebases into clean, modern, and scalable MVC-structured projects / Pedoman ahli untuk merefaktor codebase PHP lama menjadi proyek terstruktur MVC yang bersih, modern, dan skalabel.
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。
Expert guide for structured logging (Pino, Winston), error tracking (Sentry), log aggregation (Axiom, Datadog), request correlation, and GDPR-compliant log management / Panduan ahli untuk logging terstruktur (Pino, Winston), pelacakan error (Sentry), agregasi log, korelasi request, dan manajemen log sesuai GDPR.
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。
Expert guide for Prompt Engineering, Chain-of-Thought, few-shot prompting, structured output, prompt injection defense, and automated AI evaluations & regression benchmarking (Promptfoo, DeepEval) / Panduan ahli rekayasa prompt dan evaluasi otomatis AI.
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。
Reads and analyzes academic papers (arXiv preprints, conference / journal PDFs, Zotero items) at three configurable depths: quick skim (2 min), standard read (10 min), or deep analysis (30 min). Produces structured digests covering problem, method, key innovation, results, limitations, reproducibility, hidden assumptions, and connections to the user's other work. Use when the user shares an arXiv link, PDF, or paper title and asks to read / summarize / digest / TL;DR / analyze / review / critique / explain / break down a paper, asks about a paper's contributions / methods / results / equations / figures, wants to compare two papers side by side, or needs a reading note for their records.
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。
Manages a Zotero academic reference library through both the local API (localhost:23119, read-only) and the Web API (api.zotero.org, read-write), using a structured collection hierarchy (Inbox / Active Projects / Background / Reading Queue / Archive / Meta) plus project, status, priority, and type tags. Handles adding papers with full metadata, deduplication, attaching provenance notes, moving items between collections, updating tags after reading, listing the prioritized reading queue, and setting up the literature scaffold for a new project. Use when the user asks to add / save / file / organize a paper in Zotero, check / list / clean up the reading queue, move papers between collections, tag papers for a project, query their library ("what do I have on X?"), or set up Zotero for a new research project.
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。
Conducts a systematic related-work / literature-survey / state-of-the-art review for a research question by defining survey dimensions, searching each axis, building a taxonomy of prior work, identifying the gap, and producing a positioning narrative for a paper's Related Work section. Goes beyond a flat paper list to deliver structured analysis. Use when the user is starting a new research project and needs to map the landscape, asks "what's been done on X?" or "how does my idea compare to existing work?", needs to write or revise a Related Work / Background / Prior Art section, wants to identify a research gap or position their contribution, or asks to build a taxonomy of approaches in a research area.
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。
Aural skills development covering interval recognition, chord quality identification, rhythmic and melodic dictation, sight-singing, and progressive pedagogy. Covers the Kodaly method (hand signs, relative solmization, singing-first approach), interval identification strategies, chord quality and inversion recognition, harmonic dictation, solfege systems (fixed-do vs. movable-do), Gordon's Music Learning Theory, Suzuki method principles, and structured difficulty sequencing. Use when developing listening skills, practicing dictation, preparing sight-singing, or designing ear training curricula.
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。
Structured approaches to decisions under uncertainty and complexity. Covers expected value, decision trees, multi-criteria decision analysis, System 1 vs System 2 allocation, pre-mortems, reversible vs irreversible decisions, and the distinction between good decisions and good outcomes. Use when choosing among alternatives with uncertain or multi-dimensional consequences, especially when the stakes justify a deliberate rather than intuitive process.
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。
Recognition and mitigation of systematic reasoning errors documented in the heuristics and biases tradition. Covers confirmation bias, availability, anchoring, representativeness, framing effects, hindsight bias, overconfidence, and motivated reasoning. Each bias is presented with its mechanism, diagnostic signal, and structured mitigation. Use when you suspect your own or another reasoner's conclusions may be shaped by systematic cognitive distortion rather than evidence.
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。
Classify the information-need of a query and dispatch it to the appropriate retrieval or reasoning strategy. Use before read-side memory access, before multi-strategy retrieval, or any time you'd otherwise default to "one retriever for everything". Returns a strategy label, a token budget, and a retrieval depth so downstream handlers can be specialised. Backed by Pre-Route (arxiv 2605.10235v2) and MemFlow (arxiv 2605.03312v1), which together show LLMs possess latent routing ability elicitable via a structured prompt — and that externalising the routing decision improves small-model performance by ~2x. Triggers: "route this", "what strategy", "before retrieving", "intent classification", or any query whose ideal handling depends on what KIND of question it is.
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 you have captured session evidence — session-retro / session- observatory-live traces in .planning/patterns/, tool logs, correction records — and want to induce a reusable skill from it. Segments the traces into candidate skill units (an LLM judgment, not a deterministic parse) and decomposes each candidate into a four-part structured spec: workflow structure, execution semantics, and runtime attachments (verification, safety, rollback, state). It emits a spec object, NOT a finished SKILL.md, and hands that spec to skill-forge. It sits between skill-integration (upstream frequency detector) and skill-forge (downstream author). Backed by Agent-Trace-to-Skill Induction (arxiv 2606.06893v1). Triggers on inducing a skill from captured traces, turning a repeated pattern into a skill spec, and preparing evidence for skill-forge.
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。
Transform a user's builder vision into a complete, executable GSD mission package. Use this skill whenever a user has described what they want to BUILD (a product, tool, feature, system, educational pack, or ecosystem component) and wants it structured for GSD execution. Triggers include: 'structure this for GSD', 'make this into a milestone', 'turn this vision into a mission', 'package this up for Claude Code', 'create the mission files', 'I want to hand this to GSD', 'make me a mission package', or any request to decompose a described system into wave-based executable tasks. Also trigger when the user has a vision doc already written and needs mission decomposition. Prefer this skill over generic document creation whenever the GSD ecosystem is mentioned alongside building something.
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。
Token budget tracking and enforcement for Gastown convoy-level execution. Hard limits with pre-execution checking, per-convoy and per-agent tracking, structured stop reasons.
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。
Load, validate, and use DACP bundles as structured execution context. Detects .bundle/ companion directories, validates integrity (manifest schema, fidelity, provenance), loads typed data, and builds ExecutionContext for receiving agents. Scripts are NEVER auto-executed. Use when processing incoming DACP bundles, interpreting .bundle/ directories alongside .msg files, validating bundle integrity, or building execution context from bundle payloads.
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。
Classify an image and describe its contents with a local vision LLM. Wraps kuzco's tool_llm_image_classification() ellmer tool. Use when the task needs image classification, object identification, or a structured description of what an image contains.
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。
Optimize for search engine visibility and ranking. Use when the task involves `improve SEO`, `optimize for search`, `fix meta tags`, `add structured data`, `sitemap optimization`, or `search engine optimization`.
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。
Structured code review covering style, readability, and security concerns with actionable feedback. Use when reviewing pull requests or merge requests to identify issues and suggest improvements.
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。
Query and explore the 2600: The Hacker Quarterly magazine archive (1984-present) via DuckDB. Provides structured access to 168+ issues covering hacker culture, security, privacy, telephony, and digital rights without loading full content into context.
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 debugging software, investigating incidents, diagnosing flaky tests, or analyzing performance regressions — enforces structured observation recording with evidence IDs, causality validation, and verification gates to prevent correlation-causation pollution. Use when an agent might otherwise summarize or speculate instead of reporting observed evidence.
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。
Generates professional PyPI-compliant README files in Markdown or reStructuredText. Use when creating a Python package README for PyPI publication, converting between README.md and README.rst formats, validating markup with twine check before publishing, configuring the readme field in pyproject.toml, integrating sphinx-readme to generate PyPI-compatible RST from Sphinx docs, troubleshooting rendering errors on PyPI, or previewing README rendering locally with grip or docutils.
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 creating a new feature development task — scaffolds a structured task file at .claude/tasks/{feature-name}.md with phased breakdown (Design, Implementation, Testing, Documentation), acceptance criteria, context preservation, and TaskCreate tracking. Activates on "create a feature task", "set up development tracking", "plan a feature implementation", or when preparing work for python-cli-architect or python-pytest-architect agents.
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。