Gets machine-parseable JSON out of an LLM reliably — prefer provider-enforced grammar (OpenAI responseformat:{type:"jsonschema",strict:true}, Anthropic tool-calling / toolchoice:{type:"tool"}, Gemini responseSchema) over a "respond in JSON" prompt, define the contract once as a Pydantic/Zod model and validate every response (never trust the string), use constrained decoding / grammars for open weights (Outlines, llguidance, llama.cpp GBNF, vLLM guidedjson), keep schemas SHALLOW with required fields + enums + additionalProperties:false, and build a repair-and-retry loop that handles refusals, length/maxtokens truncation, and streaming partial JSON (partial-json-parser). Schema-guided generation eliminates parse-error retries; validate-and-repair is the backstop, not the primary mechanism.
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryGeneralStars0
About this skill
Gets machine-parseable JSON out of an LLM reliably — prefer provider-enforced grammar (OpenAI responseformat:{type:"jsonschema",strict:true}, Anthropic tool-calling / toolchoice:{type:"tool"}, Gemini responseSchema) over a "respond in JSON" prompt, define the contract once as a Pydantic/Zod model and validate every response (never trust the string), use constrained decoding / grammars for open weights (Outlines, llguidance, llama.cpp GBNF, vLLM guidedjson), keep schemas SHALLOW with required fields + enums + additionalProperties:false, and build a repair-and-retry loop that handles refusals, length/maxtokens truncation, and streaming partial JSON (partial-json-parser). Schema-guided generation eliminates parse-error retries; validate-and-repair is the backstop, not the primary mechanism.
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Gets machine-parseable JSON out of an LLM reliably — prefer provider-enforced grammar (OpenAI `response_format:{type:"json_schema",strict:true}`, Anthropic tool-calling / `tool_choice:{type:"tool"}`, Gemini `responseSchema`) over a "respond in JSON" prompt, define the contract once as a Pydantic/Zod model and validate every response (never trust the string), use constrained decoding / grammars for open weights (Outlines, llguidance, llama.cpp GBNF, vLLM `guided_json`), keep schemas SHALLOW with required fields + enums + `additionalProperties:false`, and build a repair-and-retry loop that handles refusals, `length`/`max_tokens` truncation, and streaming partial JSON (`partial-json-parser`). Schema-guided generation eliminates parse-error retries; validate-and-repair is the backstop, not the primary mechanism.
About this listing
Category
General
Reported license
Apache-2.0
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLI