Agent skill

Add Crate

by y5-snowies in y5-snowies/nourish

Add a new member crate to a Cargo workspace in this repo using the y5-template binary.

Apache-2.0Auto-check passed

Install Add Crate

skills CLI
$ npx skills add y5-snowies/nourish --skill add-crate -a claude-code

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

GitHub CLI
$ gh skill install y5-snowies/nourish add-crate --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/y5-snowies/nourish.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/add-crate .claude/skills/add-crate && 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
add-crate
GitHub stars
233
Token cost
~1.5k tokens
SKILL.md length
576 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

Add a new member crate to a Cargo workspace in this repo using the y5-template binary.

  • Works in 6 steps: Find valid targets (the L1 dirs you can… → Create the crate non-interactively. The… → Need a new L0 or L1 first? The + L0/L1… → …
  • The user asks to add/create/scaffold a new crate
  • SKILL.md covers The naming convention…, Steps, Template variables (for… and Notes
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Add Crate is an agent skill from y5-snowies/nourish. Add a new member crate to a Cargo workspace in this repo using the y5-template binary. Use whenever the user asks to add/create/scaffold a new crate, module, or workspace member (e.g. "add a crate under compositor.window", "scaffold action.foo"). Handles the chain-prefix naming convention and non-interactive invocation.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with Linux. The repository describes itself as: Nourish OS. The modern way of using a computer. The licence is Apache-2.0.

When your agent uses it

  • The user asks to add/create/scaffold a new crate
  • Workspace member (e.g

Example prompts

  • “add a crate under compositor.window”
  • “scaffold action.foo”
  • “/add-crate”

Workflow steps

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

  1. Find valid targets (the L1 dirs you can add into)
  2. Create the crate non-interactively. The picker needs a TTY, so use --dir
  3. Need a new L0 or L1 first? The + L0/L1 bootstrap only works through the
  4. Verify: confirm {L1}.{Name}/ exists with the template files, and that the
  5. Write its crate.json. Cargo.toml is a GENERATED artifact — gitignored, and
  6. Regenerate. environment/build.sh and environment/check.sh do this for you

What it can do on your machine

Read from SKILL.md and the folder at commit d6893ce. 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 (its code samples are jsonc).

    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

Add Crate loads about 1.5k tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 576 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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 y5-snowies/nourish at commit d6893ce, republished under its Apache-2.0 licence (© y5-snowies). 576 words, ~1,488 tokens.

Download SKILL.mdSave it as .claude/skills/add-crate/SKILL.md (or your agent's skills folder).
name
add-crate
description
Add a new member crate to a Cargo workspace in this repo using the `y5-template` binary. Use whenever the user asks to add/create/scaffold a new crate, module, or workspace member (e.g. "add a crate under compositor.window", "scaffold action.foo"). Handles the chain-prefix naming convention and non-interactive invocation.

add-crate

Scaffold a new member crate into a Cargo workspace using y5-template (on PATH at ~/.cargo/bin/y5-template; source in environment/toolkit/y5-template/). Do NOT hand-create Cargo.toml/lib.rs by hand — use the tool so naming and the template stay correct.

ALWAYS run compositor.workspace/link.all.sh from the repo root after creating a crate (step 5) — the crate is not wired into the workspaces until you do.

The naming convention (chain-prefix)

A crate is created exactly two levels below a workspace root, and each level's directory name chains off its parent: {parent_tail}.{own_segment}.

compositor/                  workspace root  (Cargo.toml [workspace] members glob has ≥2 `*`)
  compositor.action/         L0   (root_tail "compositor" + "action")
    action.window/           L1 = the target directory
      window.{Name}/         L2 = what the tool CREATES
  • root_tail = last dot-segment of the workspace dir name (compositor → compositor).
  • A valid L0 is {root_tail}.{seg}, a valid L1 is {seg}.{sub}.
  • The created dir is {L1_own_segment}.{Name} and must not already exist.

Steps

  1. Find valid targets (the L1 dirs you can add into):

    y5-template --scan /workspace --list

    This prints every valid <workspace> › <L0> › <L1> with its absolute path.

  2. Create the crate non-interactively. The picker needs a TTY, so use --dir (which skips the picker when the dir validates) and pipe the Name to stdin:

    printf 'NAME\n' | y5-template --dir /workspace/compositor/compositor.action/action.window
    • NAME becomes the crate suffix → creates window.NAME/.
    • Batch: printf 'a, b, c\n' | y5-template --dir <L1_DIR> creates window.a, window.b, window.c atomically (aborts if any already exists).
    • Extra template vars: if the chosen template declares vars beyond Name, they are prompted after Name — feed them as additional lines: printf 'NAME\nval1\nval2\n' | y5-template --dir <L1_DIR>. Check first with: y5-template --template <NAME> --help is not enough — inspect the template under <workspace>/y5.template/<tpl>/ for $${var}$$ placeholders.
    • --template <NAME> selects a non-default template (default is default).
  3. Need a new L0 or L1 first? The + L0/L1 bootstrap only works through the interactive picker, so non-interactively just create the chain-prefixed dirs yourself, then run step 2:

    mkdir -p /workspace/compositor/compositor.<L0>/<L0>.<L1>
    printf 'NAME\n' | y5-template --dir /workspace/compositor/compositor.<L0>/<L0>.<L1>
  4. Verify: confirm {L1}.{Name}/ exists with the template files, and that the workspace Cargo.toml member glob already covers it (it does if the glob is compositor.<L0>/*/*-style — no manual members edit needed).

    The template's lib.rs is already SHELL-conforming (extern crate + pub mod) — keep it that way. Code goes in the generated <module>.rs beside it; a fn, struct, impl or const written into lib.rs fails the lint, and that rule has no allowlist. Re-export from lib.rs with pub use <module>::… if callers should see an item at the crate root.

  5. Write its crate.json. Cargo.toml is a GENERATED artifact — gitignored, and overwritten on every build — so a crate declares its dependencies in crate.json beside lib.rs. It is JSONC, so a // comment above a dependency is kept and re-emitted above that line in the generated manifest:

    jsonc
    {
      "deps": [
        // Developer logging — provides error!/warn!/info!/trace!/abort!.
        "compositor_model_debug_instance_record",
        "smithay"
      ]
    }

    Names only. A crate never states a version, a feature or a manifest shape — those live in compositor.workspace/vendor.catalog.json (external versions/features) and compositor.workspace/workspace.catalog.json (per-crate features, [[bin]], build scripts, …).

    Only add what the crate actually uses: an unused dependency FAILS the lint (deps-unused), and a dependency that is genuinely needed but never named in the source — e.g. spliced in by tonic::include_proto! — goes in keep with a reason.

  6. Regenerate. environment/build.sh and environment/check.sh do this for you before invoking cargo, so usually there is nothing to run. To refresh the tree for an editor without building: compositor.workspace/link.all.sh (which now just generates + lints).

Show full SKILL.md (73 more words)Show less

Template variables (for reference)

For compositor/compositor.action/action.window + Name = handle:

variablevalue
workspace_namecompositor
L0 / L1action / window
Namehandle
fully_qualified_crate_namecompositor_action_window_handle
fully_qualified_module_namehandle

Notes

  • --scan defaults to $ZED_WORKTREE_ROOT then cwd; pass --scan /workspace explicitly when running from elsewhere.
  • In Zed, humans use the picker via alt-n (default template) / alt-shift-n (named); that path also pins the L1 of the currently-open file. The CLI --dir flow above is the equivalent for non-interactive/agent use.
  • Full reference: environment/toolkit/y5-template/.

© y5-snowies, 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 .claude/skills/add-crate of y5-snowies/nourish.

Open the folder on GitHubat commit d6893ce

Compare with similar skills

Add Crate 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.

Add Crate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Add Crate this skilly5-snowies/nourish233—~1.5kAutomated safety check: PassApache-2.0
Configuring Horizoncoollabsio/coolify63k4 repos~898Automated safety check: PassMIT
Model Usageopenclaw/openclaw392k1 repos~637Automated safety check: PassMIT
Engine Whats Newflutter/flutter180k—~978Automated safety check: PassBSD-3-Clause
Openclaw Live Updateropenclaw/openclaw392k—~3.7kAutomated safety check: PassMIT
Upgrade Browserflutter/flutter180k—~1.1kAutomated safety check: PassBSD-3-Clause

Similar skills

  • Configuring Horizon

    coollabsio/coolify

    A skill your agent uses whenever the user mentions Horizon by name in a Laravel context.

    63k GitHub starsUsed in 4 repos~898 tokens
    Backend & APIsAuto-check passed
  • Model Usage

    openclaw/openclaw

    Summarize CodexBar local cost logs by model for Codex or Claude, including current or full breakdowns.

    392k GitHub starsUsed in 1 repo~637 tokens
    Auto-check passed
  • Engine Whats New

    flutter/flutter

    Generates the "what's new" release summary and diff file for changes in the Flutter engine (//engine/src/flutter) between two releases (e.g., 3.47 vs 3.44).

    180k GitHub stars~978 tokensUpdated today
    MobileAuto-check passed
  • Openclaw Live Updater

    openclaw/openclaw

    Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation.

    392k GitHub stars~3.7k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Upgrade Browser

    flutter/flutter

    Upgrade browser versions (Chrome or Firefox) in the Flutter Web Engine and/or Framework tests.

    180k GitHub stars~1.1k tokensUpdated today
    MobileAuto-check passed
  • K8s Security Policies

    Cybereason-Public/owLSM

    Comprehensive guide for implementing NetworkPolicy, PodSecurityPolicy, RBAC, and Pod Security Standards in Kubernetes.

    280 GitHub starsUsed in 12 repos~2k tokens
    Backend & APIsAuto-check passed

More from y5-snowies/nourish

  • Logging

    y5-snowies/nourish

    How to log in the y5 compositor. An agent skill from y5-snowies/nourish.

    233 GitHub stars~753 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Add Crate

What does Add Crate do?

Add a new member crate to a Cargo workspace in this repo using the y5-template binary. Add Crate is an agent skill from y5-snowies/nourish. Add a new member crate to a Cargo workspace in this repo using the y5-template binary.

When should I use Add Crate?

Add Crate fits situations like: the user asks to add/create/scaffold a new crate; workspace member (e.g.

How do I install Add Crate in Claude Code?

Run `npx skills add y5-snowies/nourish --skill add-crate -a claude-code`. Or copy the skill folder (.claude/skills/add-crate in y5-snowies/nourish) into .claude/skills/add-crate in your project. Claude Code loads it when a task matches its description.

How do I install Add Crate in Codex?

Run `npx skills add y5-snowies/nourish --skill add-crate -a codex`. Or copy the skill folder (.claude/skills/add-crate in y5-snowies/nourish) into .agents/skills/add-crate in your project. Codex loads it when a task matches its description.

Can I use Add Crate 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 y5-snowies/nourish --skill add-crate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/add-crate, .gemini/skills/add-crate, .github/skills/add-crate and .opencode/skills/add-crate in your project.

What does Add Crate need to run?

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

Does Add Crate 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 Add Crate 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 Add Crate use?

Add Crate 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 Add Crate use?

About 1.5k tokens (SKILL.md is roughly 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 Add Crate?

Skills that share tags, products or a category with Add Crate: Configuring Horizon (coollabsio/coolify, 63k stars), Model Usage (openclaw/openclaw, 392k stars), Engine Whats New (flutter/flutter, 180k stars) and Openclaw Live Updater (openclaw/openclaw, 392k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Add Crate?

y5-snowies (a GitHub organization) maintains it in y5-snowies/nourish, which has 233 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 4, 2026.

Source: y5-snowies/nourish on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.