Agent skill

Composewebview Code Review

by parkwoocheol in parkwoocheol/compose-webview

Performs code quality checks and reviews for ComposeWebView.

MITAuto-check passedDevelopment

Install Composewebview Code Review

skills CLI
$ npx skills add parkwoocheol/compose-webview --skill composewebview-code-review -a claude-code

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

GitHub CLI
$ gh skill install parkwoocheol/compose-webview composewebview-code-review --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/parkwoocheol/compose-webview.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/code-review .claude/skills/composewebview-code-review && 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
composewebview-code-review
GitHub stars
103
Token cost
~2k tokens
SKILL.md length
588 words
Files
9 (incl. scripts)
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Performs code quality checks and reviews for ComposeWebView.

  • Works in 5 steps: Code Formatting → Multiplatform Completeness → Documentation Coverage → …
  • Checking code quality
  • SKILL.md covers Quick Review, Review Categories, Review Checklists and Automated Checks, plus 6 more sections
  • Runs Shell scripts from its folder; calls bash and git

What it does

Composewebview Code Review is an agent skill from parkwoocheol/compose-webview. Performs code quality checks and reviews for ComposeWebView. Validates expect/actual implementations, KDoc coverage, Spotless formatting, and multiplatform patterns. Use when reviewing PRs, checking code quality, or validating new features.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts (for example `checklists/feature_checklist.md`, `checklists/multiplatform_checklist.md` and `checklists/pr_checklist.md`).

It sits in Development, covering Code quality, Code review and Android development. It works with Android, Jetpack Compose and Kotlin. The repository describes itself as: A powerful, flexible, and feature-rich WebView wrapper for Jetpack Compose and Compose Multiplatform (Android, iOS, Desktop, Web). The licence is MIT.

When your agent uses it

  • Checking code quality
  • Validating new features

Example prompts

  • “Use the composewebview-code-review skill to perform code quality checks and reviews for ComposeWebView”
  • “/composewebview-code-review”

Requirements

  • A Bash shell

Workflow steps

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

  1. Code Formatting
  2. Multiplatform Completeness
  3. Documentation Coverage
  4. Testing Coverage
  5. Architecture Compliance

What it can do on your machine

Read from SKILL.md and the folder at commit 209044a. 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

    Ships 3 files in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • bash
    • 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

Composewebview Code Review loads about 2k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 588 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from parkwoocheol/compose-webview at commit 209044a, republished under its MIT licence (© parkwoocheol). 588 words, ~1,999 tokens.

Download SKILL.mdSave it as .claude/skills/composewebview-code-review/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
composewebview-code-review
description
Performs code quality checks and reviews for ComposeWebView. Validates expect/actual implementations, KDoc coverage, Spotless formatting, and multiplatform patterns. Use when reviewing PRs, checking code quality, or validating new features.

ComposeWebView Code Review & Quality

This skill automates code quality checks and assists with pull request reviews for the ComposeWebView multiplatform library.

Quick Review

Run complete review workflow:

bash
bash .agents/skills/code-review/scripts/review_checklist.sh

This executes all quality checks: formatting, expect/actual validation, KDoc coverage, and tests.

Review Categories

1. Code Formatting

Check formatting (non-destructive):

bash
./gradlew spotlessCheck

Auto-fix formatting:

bash
./gradlew spotlessApply

Spotless enforces ktlint rules. REQUIRED before all commits.

2. Multiplatform Completeness

Check expect/actual pairs:

bash
bash .agents/skills/code-review/scripts/check_expect_actual.sh

Verifies:

  • Every expect declaration has corresponding actual implementations
  • All platforms (Android, iOS, Desktop, JS, WASM) are covered
  • No orphaned actual declarations
3. Documentation Coverage

Verify KDoc:

bash
bash .agents/skills/code-review/scripts/verify_kdoc.sh

Checks:

  • All public APIs have KDoc comments
  • KDoc includes @param and @return where applicable
  • No placeholder documentation (e.g., "TODO")
4. Testing Coverage

Ensure tests exist for:

  • Common functionality in commonTest
  • Platform-specific features in platform test sources
  • Critical paths (WebView loading, JS bridge, state management)

Run tests:

bash
bash .agents/skills/development/scripts/test_all.sh
5. Architecture Compliance

Verify adherence to project patterns:

  • State management via WebViewState (see .agents/knowledge/architecture.md)
  • Controller separation via WebViewController
  • Proper platform abstraction (expect/actual)

See reference/common_patterns.md for patterns.

Review Checklists

Feature Implementation

Copy and work through: checklists/feature_checklist.md

Quick checklist:

markdown
- [ ] Defined in commonMain with expect
- [ ] Implemented in all 5 platforms (Android, iOS, Desktop, JS, WASM)
- [ ] Public APIs have KDoc with @param/@return
- [ ] Tests added in commonTest and platform tests
- [ ] Spotless formatting applied
- [ ] Updated relevant documentation
- [ ] Follows existing patterns (State/Controller)
- [ ] Platform constraints considered (iOS, Desktop, WASM)
- [ ] Kotlinx Serialization used for JSON
- [ ] Null safety enforced (no !! operator)
- [ ] Immutability preferred (val over var)
Pull Request Review

Copy and work through: checklists/pr_checklist.md

Essential checks:

  • Code quality (formatting, naming, structure)
  • Multiplatform completeness
  • Test coverage
  • Documentation updates
  • Breaking change assessment
Multiplatform Validation

For complex platform work: checklists/multiplatform_checklist.md

Platform-specific considerations:

  • Android: WebView API usage, permissions
  • iOS: WKWebView constraints, message handlers
  • Desktop: CEF initialization, threading
  • Web (JS): IFrame limitations, postMessage bridge
  • Web (WASM): Same-origin policy, limited native features

Automated Checks

Complete Review Script
bash
bash .agents/skills/code-review/scripts/review_checklist.sh

Checks performed:

  1. ✅ Code formatting (Spotless)
  2. ✅ Expect/actual completeness
  3. ⚠️ KDoc coverage (warning only)
  4. ✅ All tests passing

Exit codes:

  • 0 - All checks passed
  • 1 - Critical issues found (formatting, tests, expect/actual)
Individual Checks

Expect/Actual:

bash
bash .agents/skills/code-review/scripts/check_expect_actual.sh

KDoc Coverage:

bash
bash .agents/skills/code-review/scripts/verify_kdoc.sh

Formatting:

bash
bash .agents/skills/development/scripts/format_check.sh

Common Issues & Solutions

See reference/review_guidelines.md for:

  • Common multiplatform pitfalls
  • Platform-specific gotchas (WKWebView, CEF)
  • Performance considerations
  • Breaking change checklist
Quick Fixes

Formatting issues:

bash
./gradlew spotlessApply

Missing actual implementation:

  1. Identify the expect declaration
  2. Add actual to all platform source sets
  3. Verify: bash .agents/skills/code-review/scripts/check_expect_actual.sh

Missing KDoc:

kotlin
/**
 * Brief description of what this does.
 *
 * @param param Description of parameter
 * @return Description of return value
 */
fun publicFunction(param: String): Result

Review Workflow

Before Submitting PR
  1. Format code:

    bash
    ./gradlew spotlessApply
  2. Run full review:

    bash
    bash .agents/skills/code-review/scripts/review_checklist.sh
  3. Fix any issues reported

  4. Run tests:

    bash
    bash .agents/skills/development/scripts/test_all.sh
  5. Commit and push

Show full SKILL.md (255 more words)Show less
During Code Review
  1. Check PR against checklist:

  2. Verify multiplatform completeness:

    bash
    bash .agents/skills/code-review/scripts/check_expect_actual.sh
  3. Review architectural patterns:

  4. Test locally:

    bash
    git checkout pr-branch
    bash .agents/skills/development/scripts/test_all.sh

Best Practices

Code Quality
  1. Consistent naming: Follow Kotlin conventions

    • Classes: PascalCase
    • Functions/properties: camelCase
    • Constants: UPPER_SNAKE_CASE
  2. Visibility modifiers:

    • public - External API
    • internal - Internal implementations
    • private - Encapsulated logic
  3. Immutability: Prefer val over var

  4. Null safety: Avoid !!, use safe calls ?. or ?:

Multiplatform
  1. Keep common code platform-agnostic
  2. Use expect/actual for platform specifics
  3. Document platform constraints
  4. Test on all platforms
Documentation
  1. All public APIs must have KDoc
  2. Include examples in documentation
  3. Document platform differences
  4. Keep docs up-to-date with code

CI/CD Integration

These checks can be integrated into GitHub Actions:

yaml
- name: Code Review Checks
  run: bash .agents/skills/code-review/scripts/review_checklist.sh

Scripts Reference

review_checklist.sh

Comprehensive review running all checks. Returns non-zero exit code if critical issues found.

check_expect_actual.sh

Validates that all expect declarations have actual implementations on all platforms.

verify_kdoc.sh

Checks KDoc coverage for public APIs. Warning-level (doesn't fail build).

  • Development: Development Skill
  • Architecture: .agents/knowledge/architecture.md
  • Code Style: .agents/knowledge/code_style.md
  • Workflows: .agents/knowledge/commands.md

Troubleshooting

Review Script Fails

Check output for specific failure:

  • Formatting → Run ./gradlew spotlessApply
  • Tests → Fix failing tests
  • Expect/actual → Implement missing actuals
False Positives

Expect/actual check counts declarations - may show warnings for:

  • Internal implementations
  • Platform-specific extensions

Review build errors for actual issues.

KDoc Warnings

Not all public APIs require extensive KDoc (e.g., simple getters). Use judgment, but prefer documentation.


Use this skill to maintain high code quality and consistent patterns across the ComposeWebView codebase.

© parkwoocheol, 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 8 other files (scripts) in .agents/skills/code-review of parkwoocheol/compose-webview.

  • SKILL.md
  • checklists/feature_checklist.md
  • checklists/multiplatform_checklist.md
  • checklists/pr_checklist.md
  • reference/common_patterns.md
  • reference/review_guidelines.md
  • scripts/check_expect_actual.sh
  • scripts/review_checklist.sh
  • scripts/verify_kdoc.sh

Open the folder on GitHubat commit 209044a

Compare with similar skills

Composewebview Code Review 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.

Composewebview Code Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Composewebview Code Review this skillparkwoocheol/compose-webview103—~2kAutomated safety check: PassMIT
Code Reviewerjewbetcha/opentrace1162 repos~1.1kAutomated safety check: NotesMIT
Task Workflowikarenkov/Modo343—~2.4kAutomated safety check: PassNone
Release Changelogsk2andy/candy-browser508—~593Automated safety check: PassMPL-2.0
Git GitHub Opsc5inco/compose-pokedexer143—~1.3kAutomated safety check: PassMIT
Stewardyschimke/compose-ai-tools117—~2kAutomated safety check: PassApache-2.0

Similar skills

  • Code Reviewer

    jewbetcha/opentrace

    Comprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go.

    116 GitHub starsUsed in 2 repos~1.1k tokens
    DevelopmentAuto-check: notes
  • Task Workflow

    ikarenkov/Modo

    Spec-driven workflow for non-trivial work. An agent skill from ikarenkov/Modo.

    343 GitHub stars~2.4k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • Release Changelog

    sk2andy/candy-browser

    Create or update Candy Browser's English, image-rich, versioned release notes for the in-app What's New presentation and the matching GitHub release.

    508 GitHub stars~593 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Git GitHub Ops

    c5inco/compose-pokedexer

    Handles Pokedexer Git and GitHub workflows: inspect changes, prepare commit messages, manage branches and pushes, and create or update issues and pull requests with safe file-based inputs.

    143 GitHub stars~1.3k tokensUpdated 6 days ago
    DevelopmentAuto-check passed
  • Steward

    yschimke/compose-ai-tools

    Drive a pull request on this repository to green — which fast checks to run before pushing, how to read a red check, and what to do about a review comment.

    117 GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Kotlin Specialist

    Jeffallan/claude-skills

    Applies idiomatic Kotlin 1.9+ patterns for coroutines and Flow, multiplatform code, Jetpack Compose on Android and Ktor servers, checked with detekt and ktlint.

    12k GitHub stars~1.5k tokensUpdated 6 days ago
    DevelopmentAuto-check passed

More from parkwoocheol/compose-webview

  • Composewebview Development

    parkwoocheol/compose-webview

    Builds, tests, and formats ComposeWebView multiplatform library.

    103 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Composewebview Documentation

    parkwoocheol/compose-webview

    Manages MkDocs documentation site and API references for ComposeWebView.

    103 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Composewebview Code Review

What does Composewebview Code Review do?

Performs code quality checks and reviews for ComposeWebView. Composewebview Code Review is an agent skill from parkwoocheol/compose-webview. Performs code quality checks and reviews for ComposeWebView.

When should I use Composewebview Code Review?

Composewebview Code Review fits situations like: checking code quality; validating new features.

How do I install Composewebview Code Review in Claude Code?

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

How do I install Composewebview Code Review in Codex?

Run `npx skills add parkwoocheol/compose-webview --skill composewebview-code-review -a codex`. Or copy the skill folder (.agents/skills/code-review in parkwoocheol/compose-webview) into .agents/skills/composewebview-code-review in your project. Codex loads it when a task matches its description.

Can I use Composewebview Code Review 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 parkwoocheol/compose-webview --skill composewebview-code-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/composewebview-code-review, .gemini/skills/composewebview-code-review, .github/skills/composewebview-code-review and .opencode/skills/composewebview-code-review in your project.

What does Composewebview Code Review need to run?

Going by SKILL.md and its folder, Composewebview Code Review needs a shell for the scripts in its folder and the command-line tools its instructions call (bash and git). Our summary lists: A Bash shell.

Does Composewebview Code Review 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 Composewebview Code Review 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Composewebview Code Review use?

Composewebview Code Review 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 Composewebview Code Review use?

About 2k tokens (SKILL.md is roughly 8k 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 Composewebview Code Review?

Skills that share tags, products or a category with Composewebview Code Review: Code Reviewer (jewbetcha/opentrace, 116 stars), Task Workflow (ikarenkov/Modo, 343 stars), Release Changelog (sk2andy/candy-browser, 508 stars) and Git GitHub Ops (c5inco/compose-pokedexer, 143 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Composewebview Code Review?

parkwoocheol (a GitHub user) maintains it in parkwoocheol/compose-webview, which has 103 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on August 28, 2026.

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