Agent skill

Cabloy Domain Planning

by cabloy in cabloy/cabloy

A skill your agent uses whenever the user wants to plan a new business domain in this Cabloy repo, such as CRM, OA, training, ERP, or a similar long-lived domain.

MITAuto-check passedDevelopment

Install Cabloy Domain Planning

skills CLI
$ npx skills add cabloy/cabloy --skill cabloy-domain-planning -a claude-code

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

GitHub CLI
$ gh skill install cabloy/cabloy cabloy-domain-planning --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/cabloy/cabloy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cabloy-domain-planning .claude/skills/cabloy-domain-planning && 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
cabloy-domain-planning
GitHub stars
982
Token cost
~2.1k tokens
SKILL.md length
1,060 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses whenever the user wants to plan a new business domain in this Cabloy repo, such as CRM, OA, training, ERP, or a similar long-lived domain.

  • Works in 9 steps: Detect edition first → Confirm that this is a planning request → Default to suite-first planning → …
  • The user wants to plan a new business domain in this Cabloy repo
  • SKILL.md covers Goals, Step 1: Detect edition first, Step 2: Confirm that this is a… and Step 3: Default to suite-first…, plus 7 more sections
  • Calls npm

What it does

Cabloy Domain Planning is an agent skill from cabloy/cabloy. Use this skill whenever the user wants to plan a new business domain in this Cabloy repo, such as CRM, OA, training, ERP, or a similar long-lived domain. Trigger when the request is about deciding suite-first structure, proposing or validating providerId, suite, and module names, comparing naming options, confirming names before scaffolding, or keeping a custom naming path open. Prefer it before backend or frontend scaffolding when the main question is domain naming and structure rather than immediate file…

Its SKILL.md is about 2.1k 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 Development, covering Project scaffolding. The repository describes itself as: Cabloy is a Node.js fullstack framework for AI vibe coding, with AI Spec-Driven Development guiding work from confirmed specs to verifiable delivery. The licence is MIT.

When your agent uses it

  • The user wants to plan a new business domain in this Cabloy repo
  • A similar long-lived domain
  • The request is about deciding suite-first structure
  • Validating providerId

Example prompts

  • “/cabloy-domain-planning”

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. Detect edition first
  2. Confirm that this is a planning request
  3. Default to suite-first planning
  4. Collect or infer the planning inputs
  5. Validate the naming rules
  6. Propose names in a compact planning table
  7. Confirm naming and preserve the caller's workflow
  8. Hand off to CLI-first scaffolding only after confirmation
  9. Verification

What it can do on your machine

Read from SKILL.md and the folder at commit a12cf91. 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:

    • npm

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

  • Network

    No URLs in SKILL.md. Its commands use npm, 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

Cabloy Domain Planning loads about 2.1k tokens when it runs. Until then it costs about 137 tokens; SKILL.md has 1,060 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~137
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

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 cabloy/cabloy at commit a12cf91, republished under its MIT licence (© cabloy). 1,060 words, ~2,098 tokens.

Download SKILL.mdSave it as .claude/skills/cabloy-domain-planning/SKILL.md (or your agent's skills folder).
name
cabloy-domain-planning
description
Use this skill whenever the user wants to plan a new business domain in this Cabloy repo, such as CRM, OA, training, ERP, or a similar long-lived domain. Trigger when the request is about deciding suite-first structure, proposing or validating providerId, suite, and module names, comparing naming options, confirming names before scaffolding, or keeping a custom naming path open. Prefer it before backend or frontend scaffolding when the main question is domain naming and structure rather than immediate file generation.

Cabloy Domain Planning

Use this skill when the user is still deciding how to name and structure a new business domain.

Goals

  1. detect whether the active repository is Cabloy Basic or Cabloy Start
  2. classify the request as domain planning rather than immediate scaffolding
  3. default to suite-first planning for real business domains
  4. propose valid providerId, suite, and module names before any generation happens
  5. require explicit confirmation before handing off to scaffold commands
  6. always keep a custom naming path available for the user
  7. finish with the CLI-first next step and matching verification guidance

Step 1: Detect edition first

Check the repository root for these marker files:

  • __CABLOY_BASIC__
  • __CABLOY_START__

Interpretation:

  • only __CABLOY_BASIC__ present → this is Cabloy Basic
  • only __CABLOY_START__ present → this is Cabloy Start
  • both markers present → treat the repository as ambiguous or invalid and stop before making edition-specific assumptions
  • neither marker present → inspect the owning package scripts and nearby repository structure, then ask before making an edition-specific assumption

This matters most when examples, frontend flavors, or suite/module availability may differ between editions.

Step 2: Confirm that this is a planning request

Use this skill when the user is asking things such as:

  • how to plan a new CRM, OA, training, ERP, or similar business area
  • whether the work should start as a suite or only a module
  • how to choose providerId, suiteName, or first module names
  • whether a proposed name is valid
  • which naming option should be preferred before scaffolding

Do not use this skill once naming is already confirmed and the request is clearly about backend or frontend scaffolding. In that case, route to the appropriate scaffold skill.

Step 3: Default to suite-first planning

For real business work, prefer the suite-first path described in:

  • repo-docs/fullstack/suites-and-modules.md

Use this practical rule:

  • prefer a suite for the business domain boundary
  • prefer modules for the capabilities inside that domain
  • treat a standalone module as the exception for very small, disposable, or tutorial-only work

Do not jump into :create:module first when the real question is still the domain boundary.

Step 4: Collect or infer the planning inputs

Before proposing names, determine these inputs:

  1. the business domain term
    • examples: crm, oa, training
  2. whether the user already has a required namespace or provider prefix
    • examples: demo, biz, mycorp
  3. whether the work is backend-only, frontend-only, or fullstack
  4. whether the user wants a conservative functional naming style or a custom/branded naming style

If the user already provides names, validate them instead of replacing them silently.

Step 5: Validate the naming rules

Reuse the durable naming rules from:

  • repo-docs/fullstack/suites-and-modules.md
  • repo-docs/frontend/modules-and-suites.md
Suite short name rule

A suite short name follows:

text
{providerId}-{suiteName}

In this repository:

  • suiteName must use lowercase English letters only
  • suiteName must not contain another -

So a name such as crm-core is not valid as the suiteName segment.

When a proposed name is invalid:

  • explain whether the invalid part is providerId, suiteName, or the combined short name
  • do not collapse those layers into one vague error
  • provide the nearest valid alternatives when possible

For example:

  • crm-core is invalid as a suiteName
  • crm-core can still be a valid suite short name if it is interpreted as:
    • providerId = crm
    • suiteName = core
Module planning rule

Module names should represent capability ownership inside the suite.

Prefer names that:

  • map cleanly to a business capability
  • remain natural when they become resource owners, controller names, API paths, or menu/page anchors
  • avoid technical placeholder words such as base, core, or common unless the module is truly a shared technical layer

If more detail is needed, prefer expressing it in the module name rather than by making the suite name longer.

Show full SKILL.md (458 more words)Show less

Step 6: Propose names in a compact planning table

When the user has not finalized naming, propose:

  1. one recommended option
  2. one or two alternatives if there is a meaningful trade-off
  3. one custom naming path

The proposal should be compact and practical. Include:

  • providerId
  • suite short name
  • Vona suite full name
  • Zova suite full name
  • 3-6 likely first module names
  • which module should be scaffolded first

Use examples such as:

  • suite: demo-training
  • modules: training-student, training-course, training-record

When helpful, explain why the recommendation is better than obvious alternatives.

Step 7: Confirm naming and preserve the caller's workflow

If invoked by cabloy-spec-generation because naming was unresolved, this is a naming-only detour. Return the validated identity, capability names, proposed ownership, edition, and remaining naming questions to generation. Do not run scaffold commands or treat naming confirmation as generation, ADR, or execution approval. Generation resumes its selected complete/incremental/lightweight mode and confirmation gate.

For a direct scaffolding request, before suggesting execution, explicitly confirm:

  • providerId
  • suite short name
  • first module names
  • whether the user wants backend-only, frontend-only, or fullstack scaffolding

Do not treat silence as confirmation.

Always leave a custom path available, for example:

  • “If you want a different providerId, suite short name, or first module set, give the custom names and I will validate them against the repo rules.”

Step 8: Hand off to CLI-first scaffolding only after confirmation

For a naming-only detour, return to cabloy-spec-generation without source generation. Only a direct, explicitly confirmed scaffolding request routes to the real generators rather than hand-authoring structure. A completed spec baseline instead hands one bounded WBS candidate to cabloy-spec-execution for its own dossier approval.

Typical commands are:

bash
npm run vona :create:suite <suiteShortName>
npm run zova :create:suite <suiteShortName>
npm run vona :create:module <moduleName> -- --suite=<suiteShortName>
npm run zova :create:module <moduleName> -- --suite=<suiteShortName>

Then route to:

  • cabloy-backend-scaffold for backend generation and follow-up
  • cabloy-frontend-scaffold for frontend generation and follow-up
  • cabloy-workflow if the task becomes a broader cross-stack routing problem

Step 9: Verification

Always finish with a verification path that matches the scope.

Before generation, verify:

  • the proposed suite name follows the naming rule
  • the proposed module names are natural business capability owners
  • the command family still exists through npm run vona / npm run zova

After generation, verify with the narrowest useful checks first:

  • npm run vona :
  • npm run zova :
  • npm run deps:vona
  • npm run deps:zova
  • npm run tsc

For docs or AI-asset changes that accompany this workflow, also verify that referenced public docs and skill descriptions still tell a consistent story.

Response pattern

When helpful, structure the response around these points:

  1. detected edition
  2. suite-first recommendation
  3. recommended naming table
  4. alternatives and trade-offs
  5. custom naming path
  6. confirmation gate before scaffolding
  7. next CLI commands after confirmation
  8. verification steps

Keep the response practical. The value of this skill is to turn vague new-domain requests into a confirmed, valid, and CLI-ready naming plan before any scaffolding starts.

© cabloy, MIT. 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 .agents/skills/cabloy-domain-planning of cabloy/cabloy.

Open the folder on GitHubat commit a12cf91

Compare with similar skills

Cabloy Domain Planning 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.

Cabloy Domain Planning compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cabloy Domain Planning this skillcabloy/cabloy982—~2.1kAutomated safety check: PassMIT
Python Pep Authorpproenca/dot-skills215—~2.1kAutomated safety check: PassMIT
Nx Generatenomcopter/react-mosaic4.8k7 repos~1.9kAutomated safety check: PassCustom licence
PonytailDavidObando/gsharp5657 repos~1.7kAutomated safety check: PassMIT
Run Nx Generatornrwl/nx29k2 repos~592Automated safety check: NotesMIT
Conductor Setupgemini-cli-extensions/conductor3.8k—~4.2kAutomated safety check: PassApache-2.0

Similar skills

  • Python Pep Author

    pproenca/dot-skills

    Drafting Python Enhancement Proposals (PEPs) — proposing a Python language feature, a standard library change, an interoperability standard, or an informational/process document for the Python…

    215 GitHub stars~2.1k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Nx Generate

    nomcopter/react-mosaic

    Generate code using nx generators. An agent skill from nomcopter/react-mosaic.

    4.8k GitHub starsUsed in 7 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Ponytail

    DavidObando/gsharp

    Forces the laziest solution that actually works, simplest, shortest, most minimal.

    565 GitHub starsUsed in 7 repos~1.7k tokens
    DevelopmentAuto-check passed
  • Run Nx generators with prioritization for workspace-plugin generators.

    29k GitHub starsUsed in 2 repos~592 tokens
    DevelopmentAuto-check: notes
  • Conductor Setup

    gemini-cli-extensions/conductor

    Scaffolds the project and sets up the Conductor environment.

    3.8k GitHub stars~4.2k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Builds or extends a custom Mirage virtual filesystem adapter for an API, database, object store or app data, with a working mount configuration and filesystem tests.

    3.7k GitHub stars~2.5k tokensUpdated today
    DevelopmentAuto-check passed

More from cabloy/cabloy

All 12 skills in this repo
  • A skill your agent uses to create or maintain Cabloy suite specifications under repo-specs, including PRD, SRS, PDP/WBS, acceptance planning, progress, and suite ADRs.

    982 GitHub stars~3.2k tokensUpdated today
    Auto-check: notes
  • This skill must be used only when the user explicitly invokes /cabloy-worktree-environment or explicitly asks to perform the named Cabloy worktree-environment setup.

    982 GitHub stars~2.8k tokensUpdated today
    Auto-check: notes
  • This skill should be used when the user needs the Vona backend scaffold/extend path in this Cabloy repo, especially to choose the right npm run vona generator or CRUD command and the required…

    982 GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • A skill your agent uses whenever a Cabloy task crosses the Vona-to-Zova contract boundary: backend DTO, controller, validation, entity, inferred DTO, or OpenAPI changes that should drive SDK…

    982 GitHub stars~5.1k tokensUpdated today
    Auto-check passed
  • A skill your agent uses whenever the user wants the Zova frontend path in this Cabloy repo: create or extend pages, components, api or model beans, route/query/params work, metadata refresh…

    982 GitHub stars~4.1k tokensUpdated today
    Auto-check passed
  • A skill your agent uses whenever the user wants to update a field on an existing Cabloy backend resource: add a new persisted field, refine validation, add enum-like constraints, attach or change…

    982 GitHub stars~3.4k tokensUpdated today
    Auto-check passed

Questions about Cabloy Domain Planning

What does Cabloy Domain Planning do?

A skill your agent uses whenever the user wants to plan a new business domain in this Cabloy repo, such as CRM, OA, training, ERP, or a similar long-lived domain. Cabloy Domain Planning is an agent skill from cabloy/cabloy. Use this skill whenever the user wants to plan a new business domain in this Cabloy repo, such as CRM, OA, training, ERP, or a similar long-lived domain.

When should I use Cabloy Domain Planning?

Cabloy Domain Planning fits situations like: the user wants to plan a new business domain in this Cabloy repo; A similar long-lived domain; the request is about deciding suite-first structure; validating providerId.

How do I install Cabloy Domain Planning in Claude Code?

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

How do I install Cabloy Domain Planning in Codex?

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

Can I use Cabloy Domain Planning 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 cabloy/cabloy --skill cabloy-domain-planning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cabloy-domain-planning, .gemini/skills/cabloy-domain-planning, .github/skills/cabloy-domain-planning and .opencode/skills/cabloy-domain-planning in your project.

What does Cabloy Domain Planning need to run?

Going by SKILL.md and its folder, Cabloy Domain Planning needs the command-line tools its instructions call (npm).

Does Cabloy Domain Planning access the network?

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

Is Cabloy Domain Planning 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 Cabloy Domain Planning use?

Cabloy Domain Planning is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cabloy Domain Planning use?

About 2.1k tokens (SKILL.md is roughly 8.4k 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 Cabloy Domain Planning?

Skills that share tags, products or a category with Cabloy Domain Planning: Python Pep Author (pproenca/dot-skills, 215 stars), Nx Generate (nomcopter/react-mosaic, 4.8k stars), Ponytail (DavidObando/gsharp, 565 stars) and Run Nx Generator (nrwl/nx, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cabloy Domain Planning?

cabloy (a GitHub organization) maintains it in cabloy/cabloy, which has 982 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 10, 2026.

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