new-example
Generates new agent instruction examples from a template and validates them with repository audits.
Install
mkdir -p .claude/skills/new-example && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17286" && unzip -o skill.zip -d .claude/skills/new-example && rm skill.zipInstalls to .claude/skills/new-example
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Create a complete deployable domain example under examples/ from TEMPLATE.md, with README sync, license classification, and preflight validation.Key capabilities
- →Check for overlap with existing examples.
- →Create a new domain-specific example file in kebab-case.
- →Fill `[UPPER_SNAKE_CASE]` placeholders with concrete domain values.
- →Add README sync triangle entries (Repository Structure, License scope, Version History).
- →Run `python .codex/scripts/repo_audit.py preflight .` for validation.
- →Classify license as MIT by default unless specified otherwise.
How it works
The skill creates a new domain example by copying `TEMPLATE.md`, filling placeholders, syncing README entries, classifying the license, and running a preflight audit script.
Inputs & outputs
When to use new-example
- →Create a new example agent for a specific domain
- →Sync new example files with the repository README
- →Validate new examples using the internal repository audit script
- →Classify license scopes for new agent examples
About this skill
New Example
Use this when adding a new domain-specific agent instruction file.
Steps
- Check for overlap with existing
examples/*.md; extend an existing example only if the owner asks. - Read
TEMPLATE.md,README.md, andAGENTS.md. - Create
examples/<domain>.mdin kebab-case. - Fill every
[UPPER_SNAKE_CASE]placeholder with concrete domain values. - Keep real-product claims verifiable against official docs; otherwise use clearly fictional products.
- Add the README sync triangle in the same commit:
- Repository Structure entry
- License scope classification
- Version History entry
- Run:
python .codex/scripts/repo_audit.py preflight .
Guardrails
- Do not edit
TEMPLATE.mdfor a new example. - Do not add real-looking secrets.
- Default license classification is MIT unless the example is vendor-proprietary or ambiguous; ask when ambiguous.
When not to use it
- →When editing `TEMPLATE.md` for a new example.
- →When adding real-looking secrets to the example.
- →When the task is not about creating a complete deployable domain example.
Limitations
- →The skill does not allow editing `TEMPLATE.md` for a new example.
- →It prohibits adding real-looking secrets.
- →The default license classification is MIT, requiring explicit instruction for other types.
How it compares
This skill automates the creation of new domain examples, ensuring they adhere to repository structure, licensing, and validation standards, which is more consistent than manual example creation.
Compared to similar skills
new-example side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| new-example (this skill) | 0 | 18d | Review | Beginner |
| codex-cli-bridge | 9 | 9mo | Review | Intermediate |
| droidrun-docs | 1 | 1mo | Review | Intermediate |
| mflux-release | 1 | 4mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by cgfixit
View all by cgfixit →You might also like
codex-cli-bridge
alirezarezvani
Bridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both tools
droidrun-docs
droidrun
DroidRun documentation reference. Use when users ask about DroidRun setup, configuration, SDK usage, CLI commands, device setup, agents, architecture, app cards, credentials, tracing, Docker, migration, structured output, or any DroidRun "how do I..." questions.
mflux-release
filipstrand
Prepare a release in mflux (version bump, changelog, uv lock) without tagging/publishing.
code-changelog
bear2u
AI가 만든 모든 코드 변경사항을 reviews 폴더에 기록하고 간단한 HTML 뷰어로 웹 브라우저에서 실시간 확인할 수 있습니다. 매 수정마다 문서가 생성되고 Python 서버로 즉시 확인 가능합니다.
skills
emergencescience
Instructions for AI coding agents (Claude Code, Hermes, Cursor, etc.) contributing to this project.
project-maintenance
Dilaansg
Use when changing the Farmadil System project, especially when adding new libraries, updating requirements.txt, or making major changes that require updating DESCRIPCION_SISTEMA.md.