“structured output”的搜索结果

Translate natural-language requirements or structured specification documents into formal temporal logic properties (LTL, CTL, safety/liveness properties). Use when users need to formalize requirements for model checking, formal verification, or property specification. Handles embedded/real-time systems, hardware verification, concurrent systems, and reactive systems. Resolves ambiguities, asks clarifying questions when needed, and outputs machine-checkable formulas with explanations. Supports multiple output formats (SPIN, NuSMV, Uppaal, TLA+, Maude).

中文简介正在准备中。当前显示原文说明。

Transforms natural language requirements (user stories, verbal descriptions, business rules) into formal specifications and constraints. Use when converting informal requirements into structured, testable specifications with explicit constraints. Outputs in multiple formats including BDD-style Given-When-Then, JSON Schema, and structured plain text requirements documents.

中文简介正在准备中。当前显示原文说明。

Assign items to a CLOSED label vocabulary that is too large to put in a prompt — product taxonomies, category hierarchies, tag vocabularies, routing tables, ICD/SIC-style code lists. A cheap model writes the label it thinks the vocabulary would use, and an embedder snaps that writing onto the nearest legal value, so the schema is never transmitted and the output is always in-vocabulary. Use for "classify these into our taxonomy", "tag these against the existing tag list", "map these queries to categories", "the enum is too big to send", or a Literal/enum that hits a provider cap. NOT for a vocabulary that fits in a prompt — structured output measured 0.701 acc@1 there against this pattern's 0.564. NOT for open-ended labelling with no fixed vocabulary, and not for ranked retrieval over documents (bm25).

中文简介正在准备中。当前显示原文说明。

Captures and organizes chaotic brain dumps into a structured, actionable system with zero information loss. Use this skill whenever the user says 'capture this', 'brain dump', 'let me dump some ideas', 'I've got a bunch of thoughts', 'here's everything on my mind', 'idea dump', 'let me get this out of my head', 'I need to organize my thoughts', 'here's what I'm thinking', or any variation where someone is unloading a messy stream of ideas, tasks, thoughts, and plans wanting them turned into something coherent. Also trigger when the user pastes or dictates a long, unstructured block of mixed ideas — even without the exact phrase — the intent is the same. Fast-to-action by design: no upfront intake. Output is four sections (Projects/Ideas, Tasks, Connections, How I Can Help) ending with a directive question. Asks at most one mid-organization clarifying question when a single item is genuinely ambiguous between task and project.

中文简介正在准备中。当前显示原文说明。

Central authority for Claude Agent SDK (TypeScript and Python SDKs). Covers SDK installation, authentication (Anthropic key, Bedrock, Vertex), sessions and resumption, forking sessions, streaming vs single mode, custom tools, permissions (allowedTools, disallowedTools, permissionMode), MCP integration, system prompts (CLAUDE.md, appendSystemPrompt, outputStyle), cost tracking, todo tracking, structured outputs, hosting patterns, plugins, and SDK branding guidelines. Assists with building custom agents, configuring SDK options, and troubleshooting SDK issues. Delegates 100% to docs-management skill for official documentation.

中文简介正在准备中。当前显示原文说明。

Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydantic_ai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents from YAML, or test agent behavior.

中文简介正在准备中。当前显示原文说明。

Prepares Go applications to work effectively with AI coding agents. Use when setting up a new Go project or retrofitting an existing one to ensure: structured JSON logging (slog/Zap/ZeroLog/Logrus), machine-readable command output, thorough golangci-lint configuration, non-interactive CLI design with --yes flags, structured error handling with meaningful exit codes, proper context.Context propagation, graceful shutdown, health check endpoints, and a standardized Makefile. Triggers when a user asks to make their Go app "agent-ready," "AI-friendly," wants to improve agent tooling/observability in a Go project, or needs to audit an existing Go project against agent-readiness best practices.

中文简介正在准备中。当前显示原文说明。

Convert unstructured documents into LLM-ready structured data. Supports PDF, Word, PPT, and images; extracts paragraphs, formulas, tables, charts, and other elements in one step; generates up to 8 levels of headings; and outputs Markdown organized in reading order. Useful for field extraction, comparison and validation, knowledge retrieval, and intelligent Q&A.

中文简介正在准备中。当前显示原文说明。

Protocol for agents to write structured outputs that survive session resets and are findable by the orchestrator.

中文简介正在准备中。当前显示原文说明。

An infographic skill for AI agents — works inside Claude Code, Codex, Hermes, OpenClaw, Cursor, and any agent host that loads skills. Create professional infographics as self-contained HTML files with PNG exports. Use when the user asks to create, design, generate, build, or make an infographic, data visualization, visual explainer, chart poster, cheatsheet, or pocket guide. Trigger phrases include "make this visual", "turn this into a graphic", "visualize this data", "infographic for X", "cheatsheet for X", or when the user provides structured data (tokenomics allocations, ecosystem/partner lists, timelines, comparisons, step-by-step processes) AND asks for a visual output. Covers tokenomics, ecosystem overviews, game overviews, cheatsheets, airdrop guides, comparisons, and process flows. Do NOT trigger for plain text answers, markdown tables, bulleted summaries, questions asking for advice or explanations about a topic (even when the topic is tokenomics, ecosystem, vesting, etc.), inline chat diagrams, or data processing with no visual output requested. The signal is "asks for a visual", not "mentions a keyword".

中文简介正在准备中。当前显示原文说明。

Use when spawning an agent()/workpool() subagent with an outputSchema, or a task agent whose frontmatter sets structured: true, to reduce yield retry failures by stating the exact result envelope and required fields in the prompt.

中文简介正在准备中。当前显示原文说明。

Senior Kotlin specialist code review — framework-agnostic. Use whenever the user asks to review, audit, critique, or get feedback on Kotlin code, a file, a class, a function, a module, a diff, a branch, a commit, or a pull request. Judges Kotlin language idioms, logic correctness, architecture and layering, concurrency (coroutines, Flow, structured concurrency, cancellation, race conditions), null safety, exception safety, testability, performance, and security. Detects force-unwraps, unchecked casts, GlobalScope, leaked mutability, broken structured concurrency, hidden side effects, weak abstractions, untestable seams, allocation hot spots, weak crypto, input-validation gaps, and PII logging. Outputs prioritized findings with file:line anchors and minimal-diff fixes. No assumptions about DI framework, UI framework, or build system.

中文简介正在准备中。当前显示原文说明。

Choose OpenRouter models and routers, query live catalog data, use structured outputs and batch inference, and debug routing with metadata. Use when working with OpenRouter APIs, openrouter/auto, openrouter/free, model discovery, pricing, providers, batch jobs, or structured JSON responses.

中文简介正在准备中。当前显示原文说明。

Transform transcripts, conversations, or raw notes into shareable content — either multiple social posts OR a single long-form article. Learns style from user's published content. Handles transcripts of any length (tested up to 5500+ lines / 90+ min). Use when user: (1) provides transcript/conversation/recording and wants social content, (2) asks to "turn recording/notes into posts", (3) mentions generating content from recordings/notes, (4) needs multiple publishable pieces from single source, (5) asks to write an article from a transcript — e.g. "write an article/long-form", "organize into an article", "write up this session", "turn this talk into a blog post", "deep dive". Social mode outputs 2-15 ready-to-publish pieces. Article mode outputs a structured long-form piece (3000-10000+ chars) written section-by-section.

中文简介正在准备中。当前显示原文说明。

Central authority for Claude Agent SDK (TypeScript and Python SDKs). Covers SDK installation, authentication (Anthropic key, Bedrock, Vertex), sessions and resumption, forking sessions, streaming vs single mode, custom tools, permissions (allowedTools, disallowedTools, permissionMode), MCP integration, system prompts (CLAUDE.md, appendSystemPrompt, outputStyle), cost tracking, todo tracking, structured outputs, hosting patterns, plugins, and SDK branding guidelines. Assists with building custom agents, configuring SDK options, and troubleshooting SDK issues. Delegates 100% to docs-management skill for official documentation.

中文简介正在准备中。当前显示原文说明。

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

中文简介正在准备中。当前显示原文说明。

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

中文简介正在准备中。当前显示原文说明。

Analyze a set of design samples (HTML mockups + website URLs) and produce a structured style guide that anchors the rest of the stardust redesign pipeline. Use when the user supplies reference designs ("design samples", "mockups", "inspiration sites", "style references") and wants to extract a consistent visual language — type system, color palette, spacing, motion, and reusable component patterns — before redesigning a target site. Triggers on phrases like "distill these samples", "extract a style guide from these examples", "use these as design references", or "analyze these mockups". Outputs a `trait-matrix.json` (structured per-sample + cross-sample design tokens) and a `SAMPLES.md` narrative brief that `stardust:direct` reads under Mode B (anchor-reference precedence) when picking a redesign direction.

中文简介正在准备中。当前显示原文说明。

Design structured evaluation rubrics for scoring LLM and agent outputs — defining quality dimensions, scoring scales, hard gates, score descriptions, and edge cases. Load when the user asks to create an eval rubric, define evaluation criteria, design scoring dimensions, write an eval spec, or says "what should I evaluate", "design a rubric", "create eval criteria", "define quality dimensions", "evaluation rubric for", "how do I measure quality of". Sub-skill of eval-output orchestrator.

中文简介正在准备中。当前显示原文说明。

Run a structured retrospective after development-phase runs of your product's agents — interview the owner in plain language about what went well and poorly, draft ranked improvement hypotheses, then design and run small n=1/n=2 experiments with pre-declared success criteria, guardrails, stop conditions, and a cost/ROI kill-switch. Load when the user says how did that run go, retro this run, the agent output was bad, what should we improve, draft hypotheses, run a small experiment, or after repeated dev runs of an agentic system produce uneven quality. Priority: output quality over performance over cost, each with diminishing-returns stops. NOT a product A/B test (experimentation), NOT coding-agent harness repair (harness-evolution), NOT production-scale learning (runtime-learning-loop).

中文简介正在准备中。当前显示原文说明。

The Shape System — the content_ir kind registry for structured content. Use when adding, activating, or rendering a kind/shape, writing `__kind` JSON, kind schemas or samples, XML-tag/fence detection surfaces, kind components, workflow node input_kind/output_kind, or binding agent output to a kind.

中文简介正在准备中。当前显示原文说明。

Expert GNU awk (gawk) one-liner generation and transformation. Use this skill whenever the user asks to process text fields, extract columns, compute sums or aggregates, filter structured output, reformat CSV/TSV, parse logs, generate reports, or do any record/field processing task. Trigger on keywords like "awk", "extract column", "sum a field", "count occurrences", "print field N", "filter by column", "reformat output", "aggregate log data", "process CSV", "TSV", or any request that maps to a field-oriented text transformation. When in doubt, use this skill — awk is often the right tool when sed isn't enough.

中文简介正在准备中。当前显示原文说明。

根据错误信息和执行环境，分析AI代理反复失败或重复操作的原因。通过小范围、可撤销的恢复操作检验假设，并将结果与依据整理成可供交接的报告。

• 诊断代理连续失败
• 调查重复调用工具的循环
• 检查上下文积累导致的输出退化

让AI智能体按准确性、完整性、清晰度、可操作性和简洁性五个维度自评成果，给出有具体依据的分数、平均分，以及按优先级排列的改进建议。

• 多文件实现完成后的自评
• 检查多个工作阶段的最终成果
• 评估设计文档或分析报告