Agent skill

Moon Development

by moonbitlang in moonbitlang/moon

Route implementation, design, review, diagnosis, and testing work on the Moon CLI and MoonBuild to canonical glossary, ADR, design, behavioral-reference, and testing documents.

Apache-2.0Auto-check passedDevelopment

Install Moon Development

skills CLI
$ npx skills add moonbitlang/moon --skill moon-development -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install moonbitlang/moon moon-development --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/moonbitlang/moon.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/moon-development .claude/skills/moon-development && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
moon-development
GitHub stars
423
Token cost
~1.1k tokens
SKILL.md length
496 words
Files
2
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

Route implementation, design, review, diagnosis, and testing work on the Moon CLI and MoonBuild to canonical glossary, ADR, design, behavioral-reference, and testing documents.

  • Works in 6 steps: Read CONTEXT.md before naming, changing,… → Open docs/dev/README.md. Use its task… → Read the selected documents together… → …
  • Work touches crates/moon
  • SKILL.md covers Route the work, Deepen before layering, Keep each fact in one home and Validate proportionally
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Moon Development is an agent skill from moonbitlang/moon. Route implementation, design, review, diagnosis, and testing work on the Moon CLI and MoonBuild to canonical glossary, ADR, design, behavioral-reference, and testing documents. Use when work touches crates/moon, crates/moonbuild-rupes-recta, crates/moonbuild, crates/moonbuild-debug, crates/mooncake, crates/moonutil, xtask, or docs for moon commands, package discovery, dependency resolution, workspaces, build planning and lowering, targets and toolchains, native builds, command output, caching, moon run, moon…

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Development, covering Architecture decision records, Design review and critique and Caching. The repository describes itself as: The build system and package manager for MoonBit. The licence is Apache-2.0.

When your agent uses it

  • Work touches crates/moon
  • Crates/moonbuild-rupes-recta
  • Crates/moonbuild
  • Crates/moonbuild-debug

Example prompts

  • “/moon-development”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Read CONTEXT.md before naming, changing, or reviewing MoonBuild concepts,
  2. Open docs/dev/README.md. Use its task table to select the relevant ADRs,
  3. Read the selected documents together with the affected source and tests.
  4. Establish which build engine owns the changed path. Rupes Recta is the
  5. Surface conflicts with an ADR or behavioral reference explicitly. Do not
  6. Route crates/moonrun runtime-internal work through its own CONTEXT.md and

What it can do on your machine

Read from SKILL.md and the folder at commit 0a3f0d4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Moon Development loads about 1.1k tokens when it runs. Until then it costs about 151 tokens; SKILL.md has 496 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~151
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from moonbitlang/moon at commit 0a3f0d4, republished under its Apache-2.0 licence (© moonbitlang). 496 words, ~1,051 tokens.

Download SKILL.mdSave it as .claude/skills/moon-development/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
moon-development
description
Route implementation, design, review, diagnosis, and testing work on the Moon CLI and MoonBuild to canonical glossary, ADR, design, behavioral-reference, and testing documents. Use when work touches crates/moon, crates/moonbuild-rupes-recta, crates/moonbuild, crates/moonbuild-debug, crates/mooncake, crates/moonutil, xtask, or docs for moon commands, package discovery, dependency resolution, workspaces, build planning and lowering, targets and toolchains, native builds, command output, caching, moon run, moon test, moonx, or runwasm. Do not use for crates/moonrun runtime internals.

Moon Development

Use progressive disclosure to load only the Moon and MoonBuild context relevant to the change. Do not read or reproduce the entire developer-document corpus.

Route the work

  1. Read CONTEXT.md before naming, changing, or reviewing MoonBuild concepts, command communication, package execution, or native-build behavior. Use its canonical terms and respect its avoided synonyms.
  2. Open docs/dev/README.md. Use its task table to select the relevant ADRs, designs, implemented-behavior references, migration notes, and testing guidance.
  3. Read the selected documents together with the affected source and tests. Do not assume a design or migration document describes implemented behavior.
  4. Establish which build engine owns the changed path. Rupes Recta is the default; inspect legacy moonbuild only when the path still uses it or the requirement includes compatibility.
  5. Surface conflicts with an ADR or behavioral reference explicitly. Do not silently replace an existing decision or leave an implemented-behavior reference stale.
  6. Route crates/moonrun runtime-internal work through its own CONTEXT.md and developer index rather than treating it as MoonBuild implementation.

Deepen before layering

Before adding a MoonBuild planning or lowering type, projection, or seam:

  • Identify the closest existing module and prefer deepening, moving, or extending it over adding a parallel representation.
  • Apply the deletion test to the proposed module. If deleting it would concentrate its rules in an existing owner instead of scattering them among callers, do not introduce it.
  • State the unique invariant owned by a new representation and why a real seam needs it. Overlapping fields or a single fixed adapter do not justify one.
  • Design the merged end state before splitting the work. Intermediate commits may carry compatibility code, but the PR should replace or materially shrink the old model rather than merge two peer models into the default branch.
  • Mark every intentionally retained compatibility representation, known seam violation, or deferred deletion in source with a searchable FIXME or TODO that states the removal condition. Ordinary comments, design documents, and PR descriptions do not replace the source marker.
  • Separate semantic changes from optional terminology cleanup. A rename is not an architectural benefit.
Show full SKILL.md (152 more words)Show less

Keep each fact in one home

  • Put domain vocabulary in CONTEXT.md.
  • Put accepted, hard-to-reverse trade-off decisions in docs/adr/.
  • Put cross-cutting designs and invariants in docs/dev/design/.
  • Put implemented MoonBuild behavior in docs/dev/reference/ and update it with the implementation.
  • Put migration sequencing in its named migration document.
  • Put user-facing command behavior in docs/manual/ and docs/manual-zh/.
  • Treat source and tests as the final evidence for the current revision.
  • Update docs/dev/README.md when adding, renaming, superseding, or changing the required audience of a developer document.

Avoid copying the task-to-document table into this Skill. The developer index owns the route; linked documents own the facts.

Validate proportionally

Use the task route in the developer index instead of prescribing one universal command. Preserve behavior across commands and both build engines when the feature applies to both. Prefer the narrowest test surface that proves the changed phase, and add end-to-end coverage only when the behavior crosses command or process seams.

© moonbitlang, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/moon-development of moonbitlang/moon.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 0a3f0d4

Compare with similar skills

Moon Development next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Moon Development compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Moon Development this skillmoonbitlang/moon423—~1.1kAutomated safety check: PassApache-2.0
302 Frameworks Spring Boot RESTjabrena/plinth4461 repos~1kAutomated safety check: PassApache-2.0
402 Frameworks Quarkus RESTjabrena/plinth4461 repos~965Automated safety check: PassApache-2.0
Native Data FetchingCherryHQ/cherry-studio-app4k6 repos~2.9kAutomated safety check: NotesMIT
Keybase RPC Log Analysiskeybase/client9.3k—~3kAutomated safety check: PassBSD-3-Clause
Performance CheckZeroDeng01/sublinkPro1.7k—~1.8kAutomated safety check: PassMIT

Similar skills

  • A skill your agent uses when you need to design, review, or improve REST APIs with Spring Boot — including HTTP methods, resource URIs, status codes, DTOs, versioning, deprecation and sunset…

    446 GitHub starsUsed in 1 repo~1k tokens
    Backend & APIsAuto-check passed
  • A skill your agent uses when you need to design, review, or improve REST APIs with Quarkus REST (Jakarta REST) — including resource classes, HTTP methods, status codes, request/response DTOs, Bean…

    446 GitHub starsUsed in 1 repo~965 tokens
    Backend & APIsAuto-check passed
  • Native Data Fetching

    CherryHQ/cherry-studio-app

    A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.

    4k GitHub starsUsed in 6 repos~2.9k tokens
    DevelopmentAuto-check: notes
  • Captures a clean Keybase service log and analyzes it for redundant, duplicated or looping RPCs, then checks whether a caching fix reduced the calls.

    9.3k GitHub stars~3k tokensUpdated today
    DevelopmentAuto-check passed
  • Performance Check

    ZeroDeng01/sublinkPro

    Checklist for reviewing code changes that touch queries, APIs, rendering, caching or algorithms for performance, scalability and resource-usage problems.

    1.7k GitHub stars~1.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Wp Rocket Architecture

    wp-media/wp-rocket

    A skill your agent uses when changing service structure, Subscribers, ServiceProviders, Container wiring, bootstrapping, Context classes, or any code that may affect the core caching engine in WP…

    767 GitHub stars~1.8k tokensUpdated today
    DevelopmentAuto-check passed

More from moonbitlang/moon

  • Snapbox Testing

    moonbitlang/moon

    Write and maintain Rust CLI/integration tests with snapbox 0.6+ using command assertions, inline snapshots, and minimal wildcard/redaction patterns.

    423 GitHub stars~595 tokensUpdated today
    Auto-check passed

Questions about Moon Development

What does Moon Development do?

Route implementation, design, review, diagnosis, and testing work on the Moon CLI and MoonBuild to canonical glossary, ADR, design, behavioral-reference, and testing documents. Moon Development is an agent skill from moonbitlang/moon. Route implementation, design, review, diagnosis, and testing work on the Moon CLI and MoonBuild to canonical glossary, ADR, design, behavioral-reference, and testing documents.

When should I use Moon Development?

Moon Development fits situations like: work touches crates/moon; crates/moonbuild-rupes-recta; crates/moonbuild; crates/moonbuild-debug.

How do I install Moon Development in Claude Code?

Run `npx skills add moonbitlang/moon --skill moon-development -a claude-code`. Or copy the skill folder (.agents/skills/moon-development in moonbitlang/moon) into .claude/skills/moon-development in your project. Claude Code loads it when a task matches its description.

How do I install Moon Development in Codex?

Run `npx skills add moonbitlang/moon --skill moon-development -a codex`. Or copy the skill folder (.agents/skills/moon-development in moonbitlang/moon) into .agents/skills/moon-development in your project. Codex loads it when a task matches its description.

Can I use Moon Development in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add moonbitlang/moon --skill moon-development -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/moon-development, .gemini/skills/moon-development, .github/skills/moon-development and .opencode/skills/moon-development in your project.

What does Moon Development need to run?

SKILL.md names no scripts, command-line tools or credentials: Moon Development is instructions for the agent only.

Does Moon Development access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Moon Development safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Moon Development use?

Moon Development is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Moon Development use?

About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Moon Development?

Skills that share tags, products or a category with Moon Development: 302 Frameworks Spring Boot REST (jabrena/plinth, 446 stars), 402 Frameworks Quarkus REST (jabrena/plinth, 446 stars), Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars) and Keybase RPC Log Analysis (keybase/client, 9.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Moon Development?

moonbitlang (a GitHub organization) maintains it in moonbitlang/moon, which has 423 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 8, 2026.

Source: moonbitlang/moon on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.