How do I install the Gleam skill?

Run npx skillmds@latest add aboio-labs/gleam in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Gleam safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Gleam?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Gleam free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

aboio-labs (@aboio-labs) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Gleam by aboio-labs — Agent Skill

Name: Gleam
Author: aboio-labs

Gleam

Core Gleam language skill. Use when writing pure Gleam functions, parsing or validating input (Parse, Don't Validate), decoding JSON, designing a library, or defining shared domain types — not backend (see gleam-backend) or frontend (see lustre).

aboio-labs becadac 23 files · 151.8 KB Updated Sep 17, 2026

File contents

Gleam Core Fundamentals

Consolidated skill for pure Gleam development. Read the relevant reference before writing code.

Token Efficiency

Start from git diff to scope work, Grep for patterns, and read targeted line ranges rather than whole files. Full policy: the repo-root references/token-efficiency.md.

Reference routing — by task

Task	References to read
New to Gleam syntax	`fundamentals/language-basics.md` + `fundamentals/language-features.md`
Input validation & Types	`fundamentals/type-design.md` + `fundamentals/validation-valid.md`
JSON Decoding / Encoding	`fundamentals/decoding.md` + `fundamentals/decode-map-vs-then.md`
Error handling & AppError	`fundamentals/error-handling.md`
Designing a Library	`library/library-design.md` + `library/ffi.md`

Reference routing — by topic

Topic	Reference
Official Conventions (C1-C10)	`fundamentals/conventions.md`
Common mistakes / pitfalls	`fundamentals/common-pitfalls.md`
Pattern Matching	`fundamentals/case-patterns.md`
Code Patterns (use, result.try)	`fundamentals/code-patterns.md`
Tooling (check, format, LSP)	`fundamentals/tooling.md`
Snapshot testing (birdie)	`fundamentals/birdie-snapshot-testing.md`
Stdlib functions	`fundamentals/stdlib.md`
Module name gotchas (regexp vs regex)	`fundamentals/stdlib-module-names.md`
Parser combinators (nibble)	`fundamentals/parsing-nibble.md`
Helper-first refactoring	`fundamentals/helper-first-refactoring.md`
Higher-order SQL helpers	`fundamentals/higher-order-sql-helpers.md`
String / character filtering	`fundamentals/string-character-filtering.md`

Core Principles

Parse, Don't Validate — opaque types for validated data (fundamentals/type-design.md).
Errors as Values — one AppError type, Result everywhere (fundamentals/error-handling.md).

---name: gleamdescription: Core Gleam language skill. Use when writing pure Gleam functions, parsing or validating input (Parse, Don't Validate), decoding JSON, designing a library, or defining shared domain types — not backend (see gleam-backend) or frontend (see lustre).---# Gleam Core FundamentalsConsolidated skill for pure Gleam development. **Read the relevant reference before writing code.**## Token EfficiencyStart from `git diff` to scope work, `Grep` for patterns, and read targeted line ranges rather than whole files. Full policy: the repo-root `references/token-efficiency.md`.## Reference routing — by task| Task | References to read ||-------------------------------|----------------------------------------------------------------------------------|| New to Gleam syntax | `fundamentals/language-basics.md` + `fundamentals/language-features.md` || Input validation & Types | `fundamentals/type-design.md` + `fundamentals/validation-valid.md` || JSON Decoding / Encoding | `fundamentals/decoding.md` + `fundamentals/decode-map-vs-then.md` || Error handling & AppError | `fundamentals/error-handling.md` || Designing a Library | `library/library-design.md` + `library/ffi.md` |## Reference routing — by topic| Topic | Reference ||------------------------------------------|-------------------------------------------------|| Official Conventions (C1-C10) | `fundamentals/conventions.md` || Common mistakes / pitfalls | `fundamentals/common-pitfalls.md` || Pattern Matching | `fundamentals/case-patterns.md` || Code Patterns (use, result.try) | `fundamentals/code-patterns.md` || Tooling (check, format, LSP) | `fundamentals/tooling.md` || Snapshot testing (birdie) | `fundamentals/birdie-snapshot-testing.md` || Stdlib functions | `fundamentals/stdlib.md` || Module name gotchas (regexp vs regex) | `fundamentals/stdlib-module-names.md` || Parser combinators (nibble) | `fundamentals/parsing-nibble.md` || Helper-first refactoring | `fundamentals/helper-first-refactoring.md` || Higher-order SQL helpers | `fundamentals/higher-order-sql-helpers.md` || String / character filtering | `fundamentals/string-character-filtering.md` |## Core Principles- **Parse, Don't Validate** — opaque types for validated data (`fundamentals/type-design.md`).- **Errors as Values** — one `AppError` type, `Result` everywhere (`fundamentals/error-handling.md`).

Frequently asked questions