Stats
Actions
Tags
From ballerina
Writes, runs, and tests Ballerina programs and integrations. Use when the user asks to write, create, implement, update, or fix Ballerina code; build an HTTP service or integration in Ballerina; run, test, or build a Ballerina project; or when the user does not have Ballerina installed and needs help setting it up.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ballerina:ballerinaThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Step 1 — Read existing code**: Read `.bal` files to understand the project structure. Prefer modifying existing files over creating new ones.
Step 1 — Read existing code: Read .bal files to understand the project structure. Prefer modifying existing files over creating new ones.
Step 2 — Write the code: Follow all rules in code-rules.md. Key rules:
json or map<json> directlyStep 3 — Validate: Run bal build. Fix errors and re-run. Repeat until clean. If unresolvable after multiple attempts, report what remains.
For langlib API quick reference: langlib-reference.md
bal test; otherwise → bal runbal build first — if errors, stop and report each one with file and line numberIf a bal command fails because Ballerina is not installed, read setup.md for installation instructions.
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub rnviththagan/ballerina-claude-plugins --plugin ballerina