Code Sample Documentation
Documentscode-sample-documentationCode Sample Documentation is an Agent Skill for documents published in the hashgraph-online/awesome-codex-plugins repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Design, write, review, and test code samples in developer documentation, including executable examples, explanatory snippets, request and response pairs, placeholders, outputs, language choice, sandboxing, and autogenerated samples. Use when docs include API examples, SDK snippets, CLI commands, config examples, tutorials, or code blocks readers may copy.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/hashgraph-online/awesome-codex-plugins/blob/HEAD/plugins/LVTD-LLC/skills/skills/code-sample-documentation/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/code-sample-documentation, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Code Sample Documentation
Use this skill to create and review code samples that are useful, accurate, copyable, and maintainable. It applies to executable examples, explanatory snippets, API request/response pairs, CLI commands, config files, and generated references.
This skill is derived from Docs for Developers: An Engineer's Field Guide to Technical Writing, especially Chapter 5, "Integrating code samples." The guidance is transformed and paraphrased; do not copy book prose into user outputs. Source: https://link.springer.com/book/10.1007/978-1-4842-7217-6
Quick Start
- Load
guidelines.mdto choose the smallest useful reference set. - Classify the sample as executable, explanatory, or paired request/response.
- Check whether the sample is explained, concise, clear, usable, and trustworthy.
- Use
workflows/review-code-sample.mdfor a full sample review. - Prefer running or testing samples when feasible; otherwise mark what remains unverified.
Default Output
When reviewing or designing code samples, return:
- Sample purpose - what the reader should learn or accomplish.
- Sample type - executable, explanatory, request/response, CLI, config, or generated.
- Issues or design notes - ordered by reader risk.
- Revised sample - concise and copyable when requested.
- Testing plan - how to verify runtime behavior, outputs, and version assumptions.
- Maintenance notes - source of truth, owner, and generated/manual boundary.
Contents
| Need | Start Here |
|---|---|
| Understand sample types | references/core/knowledge.md |
| Apply sample rules | references/core/knowledge.md |
| See before/after examples | references/core/knowledge.md |
| Review or design a sample | workflows/review-code-sample.md |
| Route by task | guidelines.md |
Core Posture
- A sample is documentation and software; treat it as both.
- Match sample complexity to the reader's stage.
- Make placeholders, inputs, outputs, and limitations explicit.
- Do not imply a sample is production-ready unless it has been reviewed and tested for that use.