Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nimadorostkar/Claude-Skills-collection --skill structured-outputgit clone --depth 1 https://github.com/nimadorostkar/Claude-Skills-collectionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/structured-output)<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/structured-output"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/structured-output/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/structured-output"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/structured-output.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.01420 |
| Opus 5 | $0.00019 | $0.00710 |
| Sonnet 5 | $0.00008 | $0.00284 |
| Haiku 4.5 | $0.00004 | $0.00142 |
Grade A, and why
structured-output scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured Output
Purpose
Get reliably parseable, correctly typed data out of a language model. The naive approach — asking for JSON in the prompt and calling json.loads — fails often enough to be a production incident.
When to Use
- Extracting fields from unstructured text.
- Classification with a fixed set of labels.
- Any LLM output consumed by code rather than read by a human.
- A pipeline that fails intermittently on parse errors.
Capabilities
- Schema design that models follow reliably.
- Native structured output: JSON schema mode, tool calling, constrained decoding.
- Validation, repair, and retry.
- Confidence and abstention: letting the model say it does not know.
- Extraction from long, messy, or partially irrelevant documents.
Inputs
- The target schema and the semantics of each field.
- The input text and how messy it actually is.
- What should happen when a field is genuinely absent.
Outputs
- Validated, typed objects.
- An explicit representation of absence, distinct from a guess.
- A measured extraction accuracy per field.
Workflow
- Use the API's native mechanism — JSON schema mode or tool calling constrains the decoder so that malformed output is structurally impossible. Asking for JSON in prose does not.
- Design the schema for a model, not a database — Descriptive field names, enums instead of free strings, and a description on every field explaining what belongs in it. The schema is documentation the model reads.
- Make absence representable — A nullable field with a clear meaning. Without one, the model will invent a plausible value rather than leave it out, because that is what the schema demanded.
- Validate, then repair, then fail — Parse against the schema. On a semantic failure (a valid date that is in the future when it must be past), send the error back for one repair attempt, then give up cleanly.
- Measure per field — Aggregate extraction accuracy hides the one field that is wrong 40% of the time.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 138 lines · 38 tokens per session scan A 41fbd6d0e07c
structured-output is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (26 stars, last pushed 23d ago), licensed MIT. It adds 38 tokens to every session and 1,420 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
prompt-engineer
Expert prompt engineering for AI systems. Use when the user wants to write or review prompts for AI, create instructions for AI systems, build system prompts, review or improve existing prompts, optimize AI instructions, or create any form of written communication intended for AI consumption (Claude, GPT, or other…
few-shot-quality-prompting
Master guide for crafting prompts that make AI models produce professional-quality code and UI consistently. Trigger whenever the user asks about prompt engineering, improving AI output quality, building system prompts, few-shot examples, making AI write better code, prompt optimization, or says "how to prompt"…
huashu-prompt-save
Automatically identifies the prompt type and saves it to the appropriate category (Technical / Content / Teaching / Product / General). Use when the user mentions "save prompt", "record prompt", or "organise prompts".
agent-orchestration-improve-agent
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
prompt-optimizer
A guide for reviewing and rewriting prompts intended for Claude, an AI assistant, including Claude Code. It focuses on making instructions clearer and more specific.
agent-platform-prompt-management
Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform prompts.