Agent skill

Cabloy Zova Source Reading

by cabloy in cabloy/cabloy

A skill your agent uses when the user wants to read, trace, or explain Zova frontend source code rather than scaffold new code: where a page/component/model/behavior/SSR flow is implemented, how a…

MITAuto-check passedDevelopment

Install Cabloy Zova Source Reading

skills CLI
$ npx skills add cabloy/cabloy --skill cabloy-zova-source-reading -a claude-code

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

GitHub CLI
$ gh skill install cabloy/cabloy cabloy-zova-source-reading --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-zova-source-reading .claude/skills/cabloy-zova-source-reading && 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-zova-source-reading
GitHub stars
982
Token cost
~3.1k tokens
SKILL.md length
1,480 words
Files
3 (incl. references)
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user wants to read, trace, or explain Zova frontend source code rather than scaffold new code: where a page/component/model/behavior/SSR flow is implemented, how a…

  • Works in 8 steps: Detect the active edition → Classify the analysis mode → Start from public Zova docs first → …
  • The user wants to read
  • SKILL.md covers Goals, Step 1: Detect the active…, Step 2: Classify the analysis… and Step 3: Start from public Zova…, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Cabloy Zova Source Reading is an agent skill from cabloy/cabloy. Use this skill when the user wants to read, trace, or explain Zova frontend source code rather than scaffold new code: where a page/component/model/behavior/SSR flow is implemented, how a runtime path works internally, why a plain controller field is reactive, how Zova differs from generic Vue 3 habits, or which files to read first. Trigger for requests about Zova source reading, runtime tracing, Vue-vs-Zova explanation, controller/bean/IoC mental models, or the Zova-native way to understand frontend behavior. Do…

Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/analysis-modes.md` and `references/core-reading-paths.md`).

It sits in Development, covering Project scaffolding. It works with Vue.js. 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 read
  • Explain Zova frontend source code rather than scaffold new code: where a page/component/model/behavior/SSR flow is implemented
  • How a runtime path works internally
  • Why a plain controller field is reactive

Example prompts

  • “/cabloy-zova-source-reading”

Workflow steps

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

  1. Detect the active edition
  2. Classify the analysis mode
  3. Start from public Zova docs first
  4. Choose the shortest correct source-reading path
  5. Explain Zova-native meaning first
  6. Distinguish source-confirmed behavior from interpretive comparison
  7. Stay inside the right workflow boundary
  8. Verification guidance

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

    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

Cabloy Zova Source Reading loads about 3.1k tokens when it runs, and up to ~5.5k if it reads all its reference files. Until then it costs about 158 tokens; SKILL.md has 1,480 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~158
When it runs · the whole SKILL.md, loaded when a task matches
~3.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.5k

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 cabloy/cabloy at commit a12cf91, republished under its MIT licence (© cabloy). 1,480 words, ~3,117 tokens.

Download SKILL.mdSave it as .claude/skills/cabloy-zova-source-reading/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
cabloy-zova-source-reading
description
Use this skill when the user wants to read, trace, or explain Zova frontend source code rather than scaffold new code: where a page/component/model/behavior/SSR flow is implemented, how a runtime path works internally, why a plain controller field is reactive, how Zova differs from generic Vue 3 habits, or which files to read first. Trigger for requests about Zova source reading, runtime tracing, Vue-vs-Zova explanation, controller/bean/IoC mental models, or the Zova-native way to understand frontend behavior. Do not use it for normal frontend scaffolding or backend/frontend contract regeneration.

Cabloy Zova Source Reading

Use this skill when the task is to understand, explain, or trace Zova frontend behavior in source code.

Goals

  1. detect whether the active repository is Cabloy Basic or Cabloy Start
  2. classify whether the user needs a source-entry map, a runtime-flow trace, or a Vue-vs-Zova explanation
  3. start from Zova-native public docs before diving into framework source
  4. explain Zova architecture in its own terms before translating it into Vue analogies
  5. separate source-confirmed runtime behavior from interpretive comparison
  6. finish with verification guidance that matches the analysis scope

Step 1: Detect the active edition

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 the analysis becomes UI-sensitive, SSR-site-sensitive, flavor-sensitive, or module-set-sensitive.

Step 2: Classify the analysis mode

Before reading files deeply, decide which kind of question the user is really asking.

Mode A: source-location mode

Use this mode when the user is asking questions like:

  • where should I start reading?
  • which files are relevant?
  • what order should I read the source in?
  • where is this implemented in Zova?
Mode B: runtime-flow mode

Use this mode when the user is asking questions like:

  • how does this work internally?
  • why is this field reactive?
  • where does $computed / $params / $query come from?
  • how does page/controller/component render enter the runtime?
Mode C: Vue-vs-Zova comparison mode

Use this mode when the user is asking questions like:

  • how should I understand this relative to Vue 3?
  • is this just Vue with classes?
  • what is the Zova way instead of the generic Vue way?
  • how do controller / bean / model / render roles map to Vue concepts?

If a request spans more than one mode, answer in this order:

  1. source-location mode
  2. runtime-flow mode
  3. Vue-vs-Zova comparison mode

That order reduces the risk of drifting into premature analogy before the source path is understood.

Step 3: Start from public Zova docs first

Do not begin by forcing the problem into generic Vue terminology.

Start from the public frontend reading docs in repo-docs/frontend/.

Primary reading surfaces
  • repo-docs/frontend/reading-zova-for-vue-developers.md
  • repo-docs/frontend/zova-vs-vue3-comparison.md
  • repo-docs/frontend/zova-reactivity-under-the-hood.md
  • repo-docs/frontend/zova-source-reading-map.md
  • repo-docs/frontend/page-guide.md
  • repo-docs/frontend/component-guide.md
  • repo-docs/frontend/css-in-js-guide.md

For compact procedural summaries inside the skill bundle, also use:

  • references/analysis-modes.md
  • references/core-reading-paths.md

For locale-sensitive schema/form questions, also read:

  • repo-docs/frontend/api-schema-guide.md
  • repo-docs/frontend/a-openapi-under-the-hood.md
  • repo-docs/frontend/form-guide.md
  • repo-docs/frontend/zova-form-under-the-hood.md
Core architecture surfaces

Use these when the question needs broader architectural context:

  • repo-docs/frontend/introduction.md
  • repo-docs/frontend/foundation.md
  • repo-docs/frontend/design-principles.md
  • repo-docs/frontend/ioc-and-beans.md
  • repo-docs/frontend/page-guide.md
  • repo-docs/frontend/component-guide.md
  • repo-docs/frontend/model-architecture.md
  • repo-docs/frontend/page-route-guide.md
  • repo-docs/frontend/behavior-guide.md
  • repo-docs/frontend/ssr-architecture-overview.md

Step 4: Choose the shortest correct source-reading path

After reading the public docs, choose the smallest source path that answers the question.

Use these bundled references to keep the workflow compact:

  • references/analysis-modes.md
  • references/core-reading-paths.md

Use the public repo-docs/frontend/zova-source-reading-map.md as the fuller explanation layer, but use the bundled references first when they are enough for the current task.

Locale-sensitive schema and form path

When a translated schema title, renderer, or validation surface remains stale after a locale change, read in this order:

  1. the public API Schema Guide and A-OpenAPI Under the Hood guide;
  2. the public Form Guide and Zova Form Under the Hood guide when a ZForm consumes the schema;
  3. zova/src/suite-vendor/a-zova/modules/a-openapi/src/monkey.ts to verify that the active locale replaces the selected ModelSdk;
  4. zova/src/suite-vendor/a-zova/modules/a-openapi/src/model/sdk.ts to inspect selector-scoped schema queries and createApiSchemas(...) facade lifetime;
  5. zova/src/suite-vendor/a-zova/modules/a-openapi/src/bean/sys.sdk.ts to verify locale headers and schema caches;
  6. the generated API-schema bean and the actual page/model consumer that stores or derives the facade;
  7. zova/src/suite-vendor/a-zova/modules/a-form/ only after confirming which schema the form owner supplies, and whether automatic body iteration was replaced by a default body slot.

The key distinction is between a genuinely stale generated contract and a valid schema facade captured from an earlier locale. $computed is only locale-safe when its dependency path reacquires the current schema source; wrapping an old facade or transformed snapshot does not make it current.

Raw-this reactivity boundary

When an author reports that a controller field changed but a TSX render, $computed, or $watch did not react, inspect this lifecycle boundary before recommending framework-neutral rewrites:

  1. inspect zova-core/src/bean/beanContainer.ts BeanContainer._prepareBeanInstanceCommon(...) to verify that new BeanClass(...) occurs before the framework exposes the reactive/proxied bean;
  2. inspect BeanContainer._initBeanInstance(...) to verify that __init__() is invoked only after preparation;
  3. check whether a class-field arrow callback or construction-time bind(this) captured raw this and later writes bean state;
  4. distinguish this from a callback created in __init__(), whose lexical this is the exposed bean; and
  5. verify whether the dependent render read through that same exposed identity.

State the consequence precisely: a proxy-based TSX render read can track normally, while a mutation through a raw construction-time callback changes the underlying field without notifying that dependency. An unrelated reactive update can later expose the changed value during another render.

Do not summarize this as “arrow functions are non-reactive,” and do not default to ref.value, toRaw, or generic Vue rewrites. Explain the Zova bean lifecycle first; recommend ordinary controller methods for normal actions, or closures created in __init__() only when a stable callback reference is required.

Step 5: Explain Zova-native meaning first

When answering, explain the Zova role first, then add Vue analogies only if they help.

Show full SKILL.md (601 more words)Show less
Required answer posture
  1. identify the Zova-native role first

    • page controller
    • component controller
    • render bean
    • style bean
    • model bean
    • service bean
    • behavior bean
    • route/SSR integration layer
  2. explain the source-confirmed runtime path second

  3. only then offer Vue analogies as approximate translations

Do not lead with statements like:

  • "this is basically just Vue setup with classes"
  • "this should really be a normal Vue composable"
  • "the right end state is probably ref.value"

Those translations can erase the actual Zova architecture.

For component-wrapper questions specifically, remember that controllerRef exposes the controller instance to the component consumer, not a generic DOM ref, and should not be treated as a generic Vue component-ref substitute without checking the current wrapper/controller source path.

Split Controller, Render, and Style access

When explaining a split page or component, establish role ownership before discussing access:

  • Controller owns state, actions, and lifecycle work.
  • Render owns TSX composition.
  • Style owns scoped CSS-in-JS setup.

The source-confirmed direct member lookup order is:

Current beanDirect member lookup order
ControllerController only
StyleStyle, then Controller
RenderRender, then Controller, then Style

State the shadowing caveat: an own member on the current bean takes precedence over each fallback surface. Recommend this.member for ordinary same-component companion access, such as Render reading Controller state or a Style-generated class.

Distinguish this normal fallback from explicit @Use() or bean/container access. Use explicit access only when the task needs a named or specific instance, selector or scope boundary, identity passing, lifecycle control, or other interop. Do not confuse generated type augmentation with runtime behavior: generated interfaces expose the type surface, while proxy fallback supplies missing companion members at runtime.

Step 6: Distinguish source-confirmed behavior from interpretive comparison

Always make the boundary explicit.

Source-confirmed behavior

This includes claims you can support directly from current source files, such as:

  • where a controller is created
  • where a bean becomes reactive
  • where route state is refreshed
  • where render is redirected
  • which helper wraps which Vue API
Interpretive comparison

This includes claims such as:

  • why Zova feels more object-oriented than Vue
  • how Zova growth paths differ from typical Vue growth paths
  • which analogy is the closest Vue mental model

These can be useful, but they should be labeled as interpretation rather than current-source fact.

Step 7: Stay inside the right workflow boundary

Use this skill for explanation and source reading.

Do not use it as the primary workflow when the real task is:

  • creating or refactoring frontend structures → prefer cabloy-frontend-scaffold
  • diagnosing backend/frontend contract drift → prefer cabloy-contract-loop
  • choosing whether the work belongs to backend, frontend, fullstack, docs, or AI guidance → prefer cabloy-workflow

Step 8: Verification guidance

Always finish with a verification path that matches the analysis task.

For source-reading answers

Verify:

  • the cited file paths exist
  • the described runtime path is actually visible in current source
  • the answer does not contradict the public frontend docs
For Vue-vs-Zova explanation answers

Verify:

  • the Zova-native explanation comes first
  • Vue analogies are marked as approximate, not authoritative
  • no claim quietly rewrites Zova back into generic Vue habits
For edition-sensitive frontend analysis

Verify:

  • the active edition marker was considered
  • Basic-only or Start-only UI assumptions were not silently generalized
  • SSR, theme, and flavor-sensitive statements match the active edition context

Response pattern

When helpful, structure the response around these points:

  1. detected edition
  2. analysis mode
  3. public docs to read first
  4. source path to inspect next
  5. Zova-native explanation
  6. optional Vue analogy
  7. verification notes or caveats

Keep the response practical. The value of this skill is to help AI and users read Zova source accurately and in the right architectural order, not to flatten Zova into generic Vue prose.

© 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

SKILL.md and 2 other files (references) in .agents/skills/cabloy-zova-source-reading of cabloy/cabloy.

  • SKILL.md
  • references/analysis-modes.md
  • references/core-reading-paths.md

Open the folder on GitHubat commit a12cf91

Compare with similar skills

Cabloy Zova Source Reading 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 Zova Source Reading compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cabloy Zova Source Reading this skillcabloy/cabloy982—~3.1kAutomated safety check: PassMIT
Fe Tools Template RecommenderMichealWayne/fe-tools207—~1kAutomated safety check: PassNone
Vtdfany-tdf/any-tdf778—~1.1kAutomated safety check: PassMIT
Jeecg Codegen Newjeecgboot/skills239—~2.4kAutomated safety check: PassApache-2.0
Mock CodegenChenyCHENYU/Robot_Admin1k—~1.2kAutomated safety check: PassMIT
Page CodegenChenyCHENYU/Robot_Admin1k—~3.5kAutomated safety check: PassMIT

Similar skills

  • Fe Tools Template Recommender

    MichealWayne/fe-tools

    Recommend the most suitable project template or initialization path from fe-tools project-templates based on product, framework, runtime, and delivery constraints.

    207 GitHub stars~1k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Vtdf

    any-tdf/any-tdf

    Build, review, and troubleshoot VTDF Vue 3 applications using exact component APIs, themes, icons, localization, and scaffolding.

    778 GitHub stars~1.1k tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed
  • Jeecg Codegen New

    jeecgboot/skills

    A skill your agent uses when user asks to generate JeecgBoot CRUD code, create a new module, add/modify fields on existing module, or says "代码生成", "生成代码", "创建模块", "新增功能", "建表", "加字段", "加一个字段"…

    239 GitHub stars~2.4k tokensUpdated 23 days ago
    DevelopmentAuto-check passed
  • Mock Codegen

    ChenyCHENYU/Robot_Admin

    A skill your agent uses when: generating mock data for development without a backend.

    1k GitHub stars~1.2k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Page Codegen

    ChenyCHENYU/Robot_Admin

    A skill your agent uses when: generating Vue 3 page code from either a page-spec JSON or a natural language description.

    1k GitHub stars~3.5k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Add Component

    indielayer/ui

    Add a new Vue component to @indielayer/ui with themes, tests, docs, and registry exports.

    222 GitHub stars~293 tokensUpdated 2 days ago
    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
  • 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.

    982 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • 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

Works with

Questions about Cabloy Zova Source Reading

What does Cabloy Zova Source Reading do?

A skill your agent uses when the user wants to read, trace, or explain Zova frontend source code rather than scaffold new code: where a page/component/model/behavior/SSR flow is implemented, how a…. Cabloy Zova Source Reading is an agent skill from cabloy/cabloy. Use this skill when the user wants to read, trace, or explain Zova frontend source code rather than scaffold new code: where a page/component/model/behavior/SSR flow is implemented, how a runtime path works internally, why a plain controller field is reactive, how Zova differs from generic Vue 3 habits, or which files to read first.

When should I use Cabloy Zova Source Reading?

Cabloy Zova Source Reading fits situations like: the user wants to read; explain Zova frontend source code rather than scaffold new code: where a page/component/model/behavior/SSR flow is implemented; how a runtime path works internally; why a plain controller field is reactive.

How do I install Cabloy Zova Source Reading in Claude Code?

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

How do I install Cabloy Zova Source Reading in Codex?

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

Can I use Cabloy Zova Source Reading 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-zova-source-reading -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-zova-source-reading, .gemini/skills/cabloy-zova-source-reading, .github/skills/cabloy-zova-source-reading and .opencode/skills/cabloy-zova-source-reading in your project.

What does Cabloy Zova Source Reading need to run?

SKILL.md names no scripts, command-line tools or credentials: Cabloy Zova Source Reading is instructions for the agent only.

Does Cabloy Zova Source Reading 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 Cabloy Zova Source Reading 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 Zova Source Reading use?

Cabloy Zova Source Reading 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 Zova Source Reading use?

About 3.1k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.4k tokens, read only when the agent opens those files.

What are the alternatives to Cabloy Zova Source Reading?

Skills that share tags, products or a category with Cabloy Zova Source Reading: Fe Tools Template Recommender (MichealWayne/fe-tools, 207 stars), Vtdf (any-tdf/any-tdf, 778 stars), Jeecg Codegen New (jeecgboot/skills, 239 stars) and Mock Codegen (ChenyCHENYU/Robot_Admin, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cabloy Zova Source Reading?

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.