ponylang/llm-skills/pony-examples-readme
Claude Code and agent skill by ponylang/llm-skills
- community
Checking that the SKILL.md file is still in the repository.
Conventions for Pony examples/README.md files. Load when adding, updating, or reorganizing examples in a ponylang project.
Install
npx vskill@latest install ponylang/llm-skills/pony-examples-readmeSKILL.md
Pony Examples README Conventions
These conventions are derived from existing ponylang examples/README.md files (postgres, redis, lori, crdt, uri, web_link). Follow them when writing or updating an examples/README.md.
Load pony-prose for how the prose reads. This skill says what an examples README holds; pony-prose says how to write it plainly.
Structure
- Title — Always
# Examples.
- Intro paragraph (no heading) — 1-3 sentences describing what the examples are and any useful context. Standard phrasing for library examples: "Each subdirectory is a self-contained Pony program demonstrating a different part of the X library." If examples are ordered by complexity or grouped by category, state that here.
- Example entries — One
##heading per example, using the directory name as the heading text. Optionally link to the directory:## [example-name](example-name/).
- Category grouping (when applicable) — If examples fall into natural categories, use
##for category headings and###for individual examples within each category.
- Start-here marker — When one example is clearly the simplest entry point, end its description with: "Start here if you're new to the library."
Example Descriptions
Each example gets a paragraph of 2-4 sentences covering:
- What it does: The concrete workflow in present tense, third person ("Connects to Redis, executes SET, prints the response, and closes the session.")
- What it demonstrates: The specific APIs, interfaces, or patterns exercised, named with backtick formatting (e.g., "
Session.prepare()andNamedPreparedQuery") - Key concepts: Any non-obvious behavior, design pattern, or protocol detail the example illustrates
Ordering
Choose one strategy and make it clear from the intro paragraph or the order itself:
- By complexity (simplest first) — Best when examples build on each other conceptually. State the ordering in the intro: "Ordered from simplest to most involved."
- By category — Best when examples cover distinct feature areas. Use
##categories with###examples. - By directory name — Acceptable when no natural ordering exists.
What to Omit
- Build instructions — Build commands belong in the project's top-level README or Makefile. Exception: if examples have a separate build target (e.g.,
make build-examples), a one-line note in the intro is acceptable. - Source code snippets — The README describes what each example does; the code speaks for itself.
- Detailed setup instructions — If an example needs external services (a database, Redis server, TLS certificates), mention it briefly in that example's description. Detailed setup belongs in the example's own directory.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpony-examples-readme/SKILL.md
Popularity
- Repository stars
- 10
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ponylang/llm-skills/pony-examples-readme)