// Stable structured JSON output for agents using strict schemas. Use when you need deterministic JSON responses, schema validation, or streaming JSON object assembly (generateObject/streamObject-style) with retry-and-repair loops.
Context-aware caption translation skill for SRT/VTT/ASS with bilingual output and optional Gemini CLI fallback.
CRITICAL: Skill composition engine for automatic workflow generation from skill metadata. Triggers: compose skills, orchestrate, workflow, combine skills, skill pipeline, multi-skill, 技能组合, 工作流编排, 技能发现, 自动编排, skill discovery, semantic matching, StateGraph generation
Intelligent content optimization framework for preparing data and content for AI/ML training pipelines with quality analysis, dataset optimization, and hyperparameter suggestions.
CRITICAL: Multi-agent consensus engine for parallel LLM analysis, cross-validation, and collective decision-making. Triggers: consensus, multi-agent, voting, cross-validate, hallucination reduction, 多模型共识, 交叉验证, 集体决策
CRITICAL: You are an expert in multi-agent negotiation, game theory, and automated settlement protocols. Use this skill for designing and implementing agent-to-agent negotiation workflows with x402 payment settlement. Triggers on: negotiation, bargaining, agent trade, service agreement, SLA, price negotiation, x402 settlement, agent economy, "agents negotiate", "how do agents negotiate prices", "implement agent bargaining", "multi-round negotiation", "automated deal-making", "自动谈判", "智能体协商", "服务协议", "价格谈判", "多轮协商", "agent 经济"
Query Solodit audit knowledge to review smart contracts with evidence-backed findings, severity summaries, and remediation guidance. Use for contract audit prep, vulnerability triage, and secure coding reviews.
| name | structured-output |
| description | Stable structured JSON output for agents using strict schemas. Use when you need deterministic JSON responses, schema validation, or streaming JSON object assembly (generateObject/streamObject-style) with retry-and-repair loops. |
Implement stable, schema-validated JSON outputs for agents. Use this when responses must be valid JSON, match a schema exactly, and be reliable under retries/streaming.
Use a strict system instruction and a minimal user prompt. Always require JSON only. Input can be empty; output must still match the schema.
Template:
SYSTEM:
You are a JSON generator. Output ONLY valid JSON that matches the given schema.
Do not include Markdown, comments, or trailing text.
If a field is unknown, use null (unless schema disallows it).
USER:
Return JSON that matches this schema:
<SCHEMA>
Input:
<INPUT>
Use the same schema but ensure the model emits a single JSON object and nothing else. Stream tokens and buffer until a valid JSON parse succeeds.
references/json_schema_patterns.mdreferences/pydantic_patterns.mdscripts/generate_object.py, scripts/stream_object.pyadditionalProperties is explicitly true.