Agent skill

Assembly Quality

by LunCoSim in LunCoSim/lunco-sim

Build or review a componentized LunCoSim USD assembly with a realistic, dimensionally checkable presentation.

Apache-2.0Auto-check passedTesting & QA

Install Assembly Quality

skills CLI
$ npx skills add LunCoSim/lunco-sim --skill assembly-quality -a claude-code

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

GitHub CLI
$ gh skill install LunCoSim/lunco-sim assembly-quality --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/LunCoSim/lunco-sim.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/assembly-quality .claude/skills/assembly-quality && 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
assembly-quality
GitHub stars
107
Token cost
~1.6k tokens
SKILL.md length
741 words
Files
1
Skills in repo
40
Repo updated
First seen
Licence
Apache-2.0

At a glance

Build or review a componentized LunCoSim USD assembly with a realistic, dimensionally checkable presentation.

  • Works in 5 steps: Define the contract in SI metres (Y-up,… → Reuse the nearest existing component or… → Use named mount sockets/plugs and frame… → …
  • Articulated part looks disconnected
  • SKILL.md covers Non-negotiable boundaries, Plan a believable assembly…, The live edit loop and Make the result visually…, plus 2 more sections
  • Calls git

What it does

Assembly Quality is an agent skill from LunCoSim/lunco-sim. Build or review a componentized LunCoSim USD assembly with a realistic, dimensionally checkable presentation. Use when a rover, lander, payload, or articulated part looks disconnected, is in the wrong frame, or needs an Editor-first visual and requirements review.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA. The repository describes itself as: Collaborative Multiphysics Cosimulator For Space Missions 🌎🚀🌚. The licence is Apache-2.0.

When your agent uses it

  • Articulated part looks disconnected
  • Is in the wrong frame
  • Needs an Editor-first visual and requirements review

Example prompts

  • “/assembly-quality”

Workflow steps

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

  1. Define the contract in SI metres (Y-up, right-handed, -Z-forward): root
  2. Reuse the nearest existing component or assembly. One reusable or
  3. Use named mount sockets/plugs and frame relationships. Place a part with
  4. Prefer standard USD schemas and primitive geometry for silhouette,
  5. Keep independent visual and physical roles explicit. A visual proxy may be

What it can do on your machine

Read from SKILL.md and the folder at commit 43f1301. 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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Assembly Quality loads about 1.6k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 741 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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 LunCoSim/lunco-sim at commit 43f1301, republished under its Apache-2.0 licence (© LunCoSim). 741 words, ~1,649 tokens.

Download SKILL.mdSave it as .claude/skills/assembly-quality/SKILL.md (or your agent's skills folder).
name
assembly-quality
description
Build or review a componentized LunCoSim USD assembly with a realistic, dimensionally checkable presentation. Use when a rover, lander, payload, or articulated part looks disconnected, is in the wrong frame, or needs an Editor-first visual and requirements review.

Assembly quality gate

This is the generic guardrail for assembly work. It complements edit-usd-assembly and build-vehicle; it does not create a second USD authoring path.

For a mission or operations-facing assembly, use the mission and engineering quality gates as the system-level companion: ConOps, interface control, model-fidelity limits, fault cases, progressive verification/validation, deterministic replay, and configuration baselines are part of assembly readiness, not post-hoc documentation.

Non-negotiable boundaries

  • Never hand-edit .usd/.usda text, paste a generated USDA replacement, or mutate ECS entities to make a preview look right. USD is authored through the document owner and its journal; ECS is only the projection.
  • Use Editor Perspective for component and assembly edits. Build/View are for composing or operating the mounted Twin. Activate the editor with the typed ActivatePerspective { id: "editor" } command and keep the focused preview visible while iterating.
  • Use exact DocumentId, UsdPreviewId, UsdPreviewViewId, edit target, USD paths, and generation returned by discovery. Never infer an id or target from a display name, a screenshot, or a stale file.
  • Keep identity/topology/facts in USD, mission policy and requirements in Twin-owned Rhai/SysML, equations in Modelica, and generic substrate in Rust. A missing generic capability is a small typed-tool feature request, not a vehicle-specific Rust implementation.

Plan a believable assembly before adding detail

  1. Define the contract in SI metres (Y-up, right-handed, -Z-forward): root datum, envelope, mass/collision owner, attachment frames, interfaces, supported variants, and the evidence that will prove it.
  2. Reuse the nearest existing component or assembly. One reusable or articulated component gets one explicit root and a separate Twin asset; the assembly owns references, instances, sockets, joints, placement and cross-component wiring.
  3. Use named mount sockets/plugs and frame relationships. Place a part with assembly_builder::place_or_attach_plan, align_frames_plan, or the mount realignment planner. Do not copy guessed translations between parts.
  4. Prefer standard USD schemas and primitive geometry for silhouette, mounting envelopes, collision and visible identity. Add detail only when it changes a contract, interface, physical envelope or recognizable shape.
  5. Keep independent visual and physical roles explicit. A visual proxy may be visual-only, but never hide a missing body, joint, collider or reference.

The live edit loop

Use this sequence for every component and then for the composed assembly:

text
discover document + preview + generation
  -> inspect exact composed paths and target ownership
  -> pure Rhai *_plan (typed USD ops only)
  -> review/apply with assembly_edit::batch or proposal flow
  -> wait for projection_ready and matching projected_generation
  -> QueryUsdPrim / InspectUsdDocument / lint readback
  -> Editor screenshot and image inspection
  -> component test, then assembly integration test
  -> explicit save through the Editor document owner

Use RegisterToolLibrary to hot-reload a Rhai tool in the running process; verify a real namespaced call, not just ListToolLibraries. Restart only when the Rust binary changed. Every plan must be dry, generation-aware and idempotent or reject a completed contract; applying a plan must never silently flatten a referenced source.

Show full SKILL.md (330 more words)Show less

Make the result visually checkable

  • Open one preview for the assembly and use separate preview views or FrameUsdPreviewSelection to inspect the body, landing gear, ramps, wheels, panels and engine/nozzle clusters independently. Do not judge placement from an overview in which one vehicle is clipped or occluded.
  • Wait for InspectUsdViewport.projection_ready == true before framing or selecting. Correlate every screenshot with the exact document/view and projected generation; use view_image to inspect the saved PNG.
  • Check silhouette first (body polygon, wheel count/orientation, legs, ramps, panels, engine skirt), then interfaces (no gaps, overlaps or floating mounts), then materials/colour and camera composition. A screenshot is evidence, not the model or a substitute for typed readback.
  • For view-only presentation changes use SetUsdPreviewProjection, Frame, Pan, Zoom, and camera presets. These never author USD transforms.

Requirements and dimensions

Store reusable facts and requirements in SysML files owned by the Twin; keep requirements separated by owning subsystem when ownership differs. Use the dedicated sysml-requirements runbook for source-set configuration, qualified names, validation and verification selection. Write generic Rhai tests with sysml_requirements::evaluate and checks such as exists, children, attribute, attribute_component, extent_component, bounds_component, and relationship. Tests must fail closed on missing, stale or unavailable evidence and should cover both structure and presentation (for example the declared wheel stations, named mount sockets, ramp frame relationships, symmetry and metric units).

Use QueryUsdPrim/InspectUsdDocument for authoritative dimensions and authoring_measurements::requirement_report for repeatable reports. Convert standard primitive size plus local scale into full extents; do not trust extent, a screenshot, or a hand-measured display box. Record the source, units, path and generation for every dimensional result.

Before handoff

Run the Twin's --validate and production luncosim test checks, inspect the focused Editor screenshots, and save only after the visual and typed gates agree. Capture the exact report and screenshot paths, run git diff --check, and stage only the authored Twin/tool/docs changes. Preserve unrelated dirty worktree files. If a standard USD operation is missing, document the smallest generic typed operation needed and keep the workaround in Rhai until it is implemented.

© LunCoSim, 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

Just SKILL.md in skills/assembly-quality of LunCoSim/lunco-sim.

Open the folder on GitHubat commit 43f1301

Compare with similar skills

Assembly Quality 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.

Assembly Quality compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Assembly Quality this skillLunCoSim/lunco-sim107—~1.6kAutomated safety check: PassApache-2.0
Web Application Testinganthropics/skills180k51 repos~966Automated safety check: PassApache-2.0
Diagnosing Bugsfossasia/eventyay-interpretation1.6k32 repos~2.1kAutomated safety check: PassApache-2.0
TDDpietheinstrengholt/rssmonster56430 repos~906Automated safety check: PassMIT
TDD WorkflowhellangleZ/burn-in-cceverywhere-ralph11211 repos~2.4kAutomated safety check: PassNone
TDDsanity-io/sanity6.4k20 repos~1kAutomated safety check: PassMIT

Similar skills

  • Web Application Testing

    anthropics/skills

    Official

    Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.

    180k GitHub starsUsed in 51 repos~966 tokens
    Testing & QAAuto-check passed
  • Diagnosing Bugs

    fossasia/eventyay-interpretation

    Diagnosis loop for hard bugs and performance regressions. An agent skill from fossasia/eventyay-interpretation.

    1.6k GitHub starsUsed in 32 repos~2.1k tokens
    Testing & QAAuto-check passed
  • TDD

    pietheinstrengholt/rssmonster

    Test-driven development. An agent skill from pietheinstrengholt/rssmonster.

    564 GitHub starsUsed in 30 repos~906 tokens
    Testing & QAAuto-check passed
  • TDD Workflow

    hellangleZ/burn-in-cceverywhere-ralph

    A skill your agent uses when writing new features, fixing bugs, or refactoring code.

    112 GitHub starsUsed in 11 repos~2.4k tokens
    Testing & QAAuto-check passed
  • TDD

    sanity-io/sanity

    Official

    Test-driven development with red-green-refactor loop. An agent skill from sanity-io/sanity.

    6.4k GitHub starsUsed in 20 repos~1k tokens
    Testing & QAAuto-check passed
  • Context Driven Development

    Ibrahim-3d/orchestrator-supaconductor

    A skill your agent uses when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md…

    381 GitHub starsUsed in 9 repos~2.9k tokens
    Testing & QAAuto-check passed

More from LunCoSim/lunco-sim

All 40 skills in this repo
  • Nightly Changelog

    LunCoSim/lunco-sim

    Generate concise LunCoSim nightly GitHub release notes with platform downloads, installation guidance, an AI-agent mission prompt, and a changelog link.

    107 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Build or repair a reusable scene component through a live LunCoSim Editor session.

    107 GitHub stars~4.4k tokensUpdated today
    Auto-check passed
  • Author Rhai Tests

    LunCoSim/lunco-sim

    Author and review LunCoSim behavioral, asset-backed, component, mission, visual, and requirements-verification tests.

    107 GitHub stars~3.5k tokensUpdated today
    Auto-check passed
  • Author Rhai Tool

    LunCoSim/lunco-sim

    Create, extend, register, or debug a reusable LunCoSim Rhai tool library for live USD authoring, component linting, inspection, or test support.

    107 GitHub stars~5.2k tokensUpdated today
    Auto-check passed
  • Author Tutorial

    LunCoSim/lunco-sim

    Author an interactive tutorial, guided lesson, onboarding flow, coach-mark tour, or objectives checklist in LunCoSim.

    107 GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Capability Discovery

    LunCoSim/lunco-sim

    Find existing LunCoSim capabilities before declaring a feature missing, unsupported, or impossible.

    107 GitHub stars~2.9k tokensUpdated today
    Auto-check passed

Categories

Questions about Assembly Quality

What does Assembly Quality do?

Build or review a componentized LunCoSim USD assembly with a realistic, dimensionally checkable presentation. Assembly Quality is an agent skill from LunCoSim/lunco-sim. Build or review a componentized LunCoSim USD assembly with a realistic, dimensionally checkable presentation.

When should I use Assembly Quality?

Assembly Quality fits situations like: articulated part looks disconnected; is in the wrong frame; needs an Editor-first visual and requirements review.

How do I install Assembly Quality in Claude Code?

Run `npx skills add LunCoSim/lunco-sim --skill assembly-quality -a claude-code`. Or copy the skill folder (skills/assembly-quality in LunCoSim/lunco-sim) into .claude/skills/assembly-quality in your project. Claude Code loads it when a task matches its description.

How do I install Assembly Quality in Codex?

Run `npx skills add LunCoSim/lunco-sim --skill assembly-quality -a codex`. Or copy the skill folder (skills/assembly-quality in LunCoSim/lunco-sim) into .agents/skills/assembly-quality in your project. Codex loads it when a task matches its description.

Can I use Assembly Quality 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 LunCoSim/lunco-sim --skill assembly-quality -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/assembly-quality, .gemini/skills/assembly-quality, .github/skills/assembly-quality and .opencode/skills/assembly-quality in your project.

What does Assembly Quality need to run?

Going by SKILL.md and its folder, Assembly Quality needs the command-line tools its instructions call (git).

Does Assembly Quality access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Assembly Quality 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 Assembly Quality use?

Assembly Quality 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 Assembly Quality use?

About 1.6k tokens (SKILL.md is roughly 6.6k 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 Assembly Quality?

Skills that share tags, products or a category with Assembly Quality: Web Application Testing (anthropics/skills, 180k stars), Diagnosing Bugs (fossasia/eventyay-interpretation, 1.6k stars), TDD (pietheinstrengholt/rssmonster, 564 stars) and TDD Workflow (hellangleZ/burn-in-cceverywhere-ralph, 112 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Assembly Quality?

LunCoSim (a GitHub organization) maintains it in LunCoSim/lunco-sim, which has 107 GitHub stars. The repository holds 40 skills in this directory. The repository was last updated on October 10, 2026.

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