Agent skill

Levyra CI Workflows

by LUC4N3X in LUC4N3X/Levyra-deepsound

Automatically use for Levyra GitHub Actions, CI, F-Droid, Gradle/AGP/Kotlin/KSP compatibility, build performance, configuration/build cache, artifacts, release automation, workflow security, or…

GPL-3.0Auto-check passedMobile

Install Levyra CI Workflows

skills CLI
$ npx skills add LUC4N3X/Levyra-deepsound --skill levyra-ci-workflows -a claude-code

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

GitHub CLI
$ gh skill install LUC4N3X/Levyra-deepsound levyra-ci-workflows --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/LUC4N3X/Levyra-deepsound.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/levyra-ci-workflows .claude/skills/levyra-ci-workflows && 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
levyra-ci-workflows
GitHub stars
590
Token cost
~2k tokens
SKILL.md length
1,014 words
Files
1
Skills in repo
22
Repo updated
First seen
Licence
GPL-3.0

At a glance

Automatically use for Levyra GitHub Actions, CI, F-Droid, Gradle/AGP/Kotlin/KSP compatibility, build performance, configuration/build cache, artifacts, release automation, workflow security, or…

  • Works in 4 steps: Read the root AGENTS.md and… → Read… → Inspect every workflow, reusable action,… → …
  • Levyra GitHub Actions
  • SKILL.md covers Required context, Exact SHA and Actions evidence, Guardrails and Kotlin and AGP 9 guardrails, plus 2 more sections
  • Calls gh

What it does

Levyra CI Workflows is an agent skill from LUC4N3X/Levyra-deepsound. Automatically use for Levyra GitHub Actions, CI, F-Droid, Gradle/AGP/Kotlin/KSP compatibility, build performance, configuration/build cache, artifacts, release automation, workflow security, or configuration-sync work.

Its SKILL.md is about 2k 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 Mobile, covering Android development, CI/CD and Workflow automation. It works with Gradle, Kotlin and GitHub Actions. The repository describes itself as: Open-source music player for Android and Windows with no accounts or tracking. Built for quick discovery, synced lyrics, radio, and rich artwork ♫. The licence is GPL-3.0.

When your agent uses it

  • Levyra GitHub Actions
  • Gradle/AGP/Kotlin/KSP compatibility
  • Build performance
  • Configuration/build cache

Example prompts

  • “/levyra-ci-workflows”

Workflow steps

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

  1. Read the root AGENTS.md and .github/AGENTS.md.
  2. Read .agents/claude/rules/testing-release.md and .agents/claude/rules/security.md.
  3. Inspect every workflow, reusable action, script, build file, secret/input contract, artifact path, and trigger affected by the change.
  4. Inspect recent failing job logs when the task is a CI failure; do not infer a root cause from the check title alone.

What it can do on your machine

Read from SKILL.md and the folder at commit fd13888. 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:

    • gh

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

  • Network

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

Levyra CI Workflows loads about 2k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 1,014 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
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); files beside SKILL.md are not scanned.

SKILL.md

The full file from LUC4N3X/Levyra-deepsound at commit fd13888, republished under its GPL-3.0 licence (© LUC4N3X). 1,014 words, ~1,952 tokens.

Download SKILL.mdSave it as .claude/skills/levyra-ci-workflows/SKILL.md (or your agent's skills folder).
name
levyra-ci-workflows
description
Automatically use for Levyra GitHub Actions, CI, F-Droid, Gradle/AGP/Kotlin/KSP compatibility, build performance, configuration/build cache, artifacts, release automation, workflow security, or configuration-sync work.

Levyra CI and workflow workflow

Required context

  1. Read the root AGENTS.md and .github/AGENTS.md.
  2. Read .agents/claude/rules/testing-release.md and .agents/claude/rules/security.md.
  3. Inspect every workflow, reusable action, script, build file, secret/input contract, artifact path, and trigger affected by the change.
  4. Inspect recent failing job logs when the task is a CI failure; do not infer a root cause from the check title alone.

Exact SHA and Actions evidence

When the task names a commit SHA, treat that SHA as the evidence key even when it has no pull request.

  1. Work from the specialist agent's own ./repo checkout, not a parent agent's relative path or inherited working directory.
  2. Fetch remote evidence as needed and verify that the requested SHA resolves in the local checkout before drawing conclusions.
  3. Query GitHub Actions by the exact head_sha and include push-triggered, pull-request-triggered, and manually triggered runs that belong to that SHA.
  4. Do not treat an empty commit-status surface, missing PR association, or empty PR-only run query as proof that CI does not exist. Cross-check the Actions runs surface for the SHA before reporting no CI or not verifiable.
  5. Distinguish no run exists, run queued, run in progress, run completed, run cancelled, and run failed. Report workflow name, run id when available, event, exact SHA, and conclusion.
  6. If a delegated handoff contains both a PR and SHA, verify the PR head still equals the supplied SHA before using PR-scoped evidence.

For GitHub CLI inspection, prefer a SHA-filtered run query such as gh run list --repo LUC4N3X/Levyra-deepsound --commit <sha> or the GitHub Actions runs API filtered by head_sha. Use PR-scoped queries only when the task is explicitly PR-scoped.

Guardrails

  • Keep workflow permissions at least privilege and explicit where practical.
  • Treat pull_request, pull_request_target, forks, checked-out code, issue comments, and workflow dispatch inputs as distinct trust boundaries.
  • Never expose secrets to untrusted code or upload secret-bearing files as artifacts.
  • Reuse existing release, validation, extractor-sync, F-Droid, and duplicate-guard workflows instead of creating parallel automation.
  • Pin or constrain third-party actions according to the repository's existing policy and review supply-chain impact before adding one.
  • Keep Android and Desktop release triggers, versions, tags, artifacts, and Latest-release behavior separate.
  • Preserve artifact names and paths relied on by downstream jobs or release steps.
  • Ensure caches use safe, deterministic keys and cannot substitute untrusted executable output across trust boundaries.
  • Make no-change, skipped, cancelled, and failed outcomes visible and semantically distinct.

Kotlin and AGP 9 guardrails

Levyra currently uses AGP 9.x and built-in Kotlin support in the Android application module. Treat build-tooling edits as compatibility work, not routine cleanup.

Before changing AGP, Kotlin, KSP, Gradle, Compose tooling, source sets, compiler options, or module plugins:

  1. inspect settings.gradle.kts, root and affected module build.gradle.kts files, gradle/libs.versions.toml, gradle/wrapper/gradle-wrapper.properties, and gradle.properties;
  2. classify the affected module from its actual plugins instead of inferring KMP merely because the repository also contains a Desktop client;
  3. compare the proposed change with the current official Kotlin/Android Gradle guidance when behavior is version-sensitive;
  4. keep the change limited to the migration or compatibility issue that actually exists.

Levyra-specific rules:

  • Do not reintroduce org.jetbrains.kotlin.android into the AGP 9 Android app; AGP provides built-in Kotlin support for the Android application plugin.
  • Keep annotation processing on KSP where supported. Do not introduce org.jetbrains.kotlin.kapt as a convenience workaround; any legacy-kapt fallback requires an explicit task and compatibility justification.
  • When compiler options must change, use the current Kotlin compiler DSL rather than reviving deprecated android.kotlinOptions configuration.
  • Do not restructure Android and Desktop into a shared KMP application merely because a generic migration guide recommends that layout. Levyra's Android and Desktop products remain independently versioned and released unless the owner approves an architectural change.
  • Do not upgrade AGP, Kotlin, KSP, Gradle, JDK, SDK tools, or Compose dependencies as collateral cleanup in an unrelated CI/build fix.
  • If the official Kotlin/kotlin-agent-skills package is available, use kotlin-tooling-agp9-migration as an additional reference for AGP 9 migration work, then adapt it to Levyra's real module graph and repository rules rather than copying its target structure wholesale.

These guardrails intentionally take the useful AGP 9 compatibility checks from JetBrains' Kotlin agent skill while keeping Levyra's existing architecture authoritative.

Show full SKILL.md (328 more words)Show less

Gradle build-performance work

Treat build-speed changes as performance engineering, not a bag of gradle.properties toggles.

  1. Measure a representative baseline first, including the build mode that is actually slow (clean, incremental, CI, Android, or Desktop).
  2. Determine whether the time is dominated by configuration, dependency resolution, compilation/processing, execution, packaging, or cache misses before choosing a fix.
  3. Inspect existing configuration-cache/build-cache behavior, task inputs/outputs, eager task creation, configuration-time I/O, KSP work, repository resolution, and JDK/toolchain consistency before adding new infrastructure.
  4. Apply one material optimization at a time, rerun the same measured path, and keep the change only when the evidence shows an improvement without weakening correctness or reproducibility.
  5. Prefer lazy Gradle APIs and Providers when they solve a demonstrated configuration-time problem; do not rewrite working build logic solely to match a generic optimization checklist.
  6. Do not add remote caches, Develocity/Build Scan publishing, third-party analytics, new CI services, or data-uploading plugins merely for diagnostics. Any external upload or persistent service requires an explicit task plus privacy, credential, supply-chain, and maintenance review.
  7. Do not skip tests/lint in CI to make a timing number look better unless the repository already has a safe path-based job design that preserves the mandatory quality gate.

Record the before/after command, environment-relevant differences, and timing or task evidence when claiming a build-performance improvement. SimpMusic's Gradle performance skill is useful here for its baseline -> isolate phase -> one change -> remeasure discipline; its generic flags and services are not Levyra defaults.

Validation

Validate YAML structure, expressions, event filters, permissions, matrix behavior, shell quoting, paths, conditions, output propagation, artifact retention, and secret availability. Compare the workflow with the corresponding local Gradle command. For build-tooling changes, also verify the affected plugin graph, wrapper/version compatibility, and the narrowest relevant Android or Desktop build task. For performance changes, rerun the same representative build used for the baseline and report measured evidence rather than an assumed speedup. Report job-log evidence, checks not reproducible locally, and any manual release verification still required.

© LUC4N3X, GPL-3.0. 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 .agents/skills/levyra-ci-workflows of LUC4N3X/Levyra-deepsound.

Open the folder on GitHubat commit fd13888

Compare with similar skills

Levyra CI Workflows 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.

Levyra CI Workflows compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Levyra CI Workflows this skillLUC4N3X/Levyra-deepsound590—~2kAutomated safety check: PassGPL-3.0
Upgrade Notesgetknit/knit133—~1.2kAutomated safety check: PassGPL-3.0
Validating Compose Stabilityskydoves/android-testing-skills334—~3.5kAutomated safety check: PassApache-2.0
Kt Search Releasejillesvangurp/kt-search155—~1.2kAutomated safety check: PassMIT
Post Edit VerificationGerardPaligot/Confily152—~1.1kAutomated safety check: PassApache-2.0
Capturing Preview Screenshots In CIskydoves/android-testing-skills334—~4.5kAutomated safety check: NotesApache-2.0

Similar skills

  • Upgrade Notes

    getknit/knit

    Read the vendor's breaking changes, deprecations, migration notes and CVEs for every version between the one pinned now and the one being moved to, through the whatsnew MCP server's upgradenotes tool.

    133 GitHub stars~1.2k tokensUpdated today
    SecurityAuto-check passed
  • Validating Compose Stability

    skydoves/android-testing-skills

    A skill your agent uses to gate CI on Jetpack Compose stability — catch when a composable becomes unskippable/unrestartable or a parameter goes stable → unstable, before it ships and tanks…

    334 GitHub stars~3.5k tokensUpdated 4 mo ago
    MobileAuto-check passed
  • Kt Search Release

    jillesvangurp/kt-search

    A skill your agent uses when the user wants to cut, publish, tag, or create a GitHub release for kt-search, especially when the task includes version bumping, validating that commits are pushed…

    155 GitHub stars~1.2k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • Post Edit Verification

    GerardPaligot/Confily

    Use this skill after every working session where Kotlin or Android code was created or modified, and ALWAYS before committing, opening a PR, or reporting work as done.

    152 GitHub stars~1.1k tokensUpdated 12 days ago
    MobileAuto-check passed
  • Capturing Preview Screenshots In CI

    skydoves/android-testing-skills

    A skill your agent uses to render every Jetpack Compose @Preview as a screenshot on a real Android device or emulator and publish a browsable HTML catalog from CI.

    334 GitHub stars~4.5k tokensUpdated 4 mo ago
    MobileAuto-check: notes
  • Docker Compose Tests

    jillesvangurp/kt-search

    Use Gradle Compose tasks to prepare and recover local Elasticsearch/OpenSearch test infrastructure in kt-search.

    155 GitHub stars~295 tokensUpdated 3 mo ago
    MobileAuto-check passed

More from LUC4N3X/Levyra-deepsound

All 22 skills in this repo
  • Levyra Android Intent Security

    LUC4N3X/Levyra-deepsound

    Automatically use for Levyra Android Intent, deep-link, PendingIntent, exported component, receiver, service, provider, URI-grant, FileProvider, caller-verification, or onNewIntent security work.

    590 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Levyra Context Efficiency

    LUC4N3X/Levyra-deepsound

    A skill your agent uses for genuinely high-volume Levyra work such as builds, tests, lint, logs, broad searches, dependency output, Git/GitHub or CodeRabbit inspection, CI diagnostics, agent setup…

    590 GitHub stars~1.3k tokensUpdated today
    Auto-check: notes
  • Levyra R8 Proguard

    LUC4N3X/Levyra-deepsound

    Automatically use for Levyra R8, Proguard, minification, resource shrinking, keep rules, consumer rules, release-only crashes, reflection/serialization/JNI shrinking issues, APK size, mapping files…

    590 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Levyra Android Performance

    LUC4N3X/Levyra-deepsound

    Automatically use for Android runtime performance investigations involving Perfetto/System Trace, jank, latency, startup, CPU scheduling, blocking, memory, I/O, IPC, graphics, power, or measured…

    590 GitHub stars~3.2k tokensUpdated today
    Auto-check passed
  • Levyra Design Taste

    LUC4N3X/Levyra-deepsound

    Automatically use together with the matching Levyra UI skill for any visual redesign, UI polish, visual hierarchy, spacing, typography, color, shape, motion, screenshot/reference recreation, or…

    590 GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Levyra PR Review

    LUC4N3X/Levyra-deepsound

    Review a Levyra branch, commit, patch, or pull request for correctness, regressions, concurrency, lifecycle, security, data safety, UI behavior, CI, release risk, missing tests, and merge-readiness…

    590 GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Questions about Levyra CI Workflows

What does Levyra CI Workflows do?

Automatically use for Levyra GitHub Actions, CI, F-Droid, Gradle/AGP/Kotlin/KSP compatibility, build performance, configuration/build cache, artifacts, release automation, workflow security, or…. Levyra CI Workflows is an agent skill from LUC4N3X/Levyra-deepsound. Automatically use for Levyra GitHub Actions, CI, F-Droid, Gradle/AGP/Kotlin/KSP compatibility, build performance, configuration/build cache, artifacts, release automation, workflow security, or configuration-sync work.

When should I use Levyra CI Workflows?

Levyra CI Workflows fits situations like: levyra GitHub Actions; gradle/AGP/Kotlin/KSP compatibility; build performance; configuration/build cache.

How do I install Levyra CI Workflows in Claude Code?

Run `npx skills add LUC4N3X/Levyra-deepsound --skill levyra-ci-workflows -a claude-code`. Or copy the skill folder (.agents/skills/levyra-ci-workflows in LUC4N3X/Levyra-deepsound) into .claude/skills/levyra-ci-workflows in your project. Claude Code loads it when a task matches its description.

How do I install Levyra CI Workflows in Codex?

Run `npx skills add LUC4N3X/Levyra-deepsound --skill levyra-ci-workflows -a codex`. Or copy the skill folder (.agents/skills/levyra-ci-workflows in LUC4N3X/Levyra-deepsound) into .agents/skills/levyra-ci-workflows in your project. Codex loads it when a task matches its description.

Can I use Levyra CI Workflows 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 LUC4N3X/Levyra-deepsound --skill levyra-ci-workflows -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/levyra-ci-workflows, .gemini/skills/levyra-ci-workflows, .github/skills/levyra-ci-workflows and .opencode/skills/levyra-ci-workflows in your project.

What does Levyra CI Workflows need to run?

Going by SKILL.md and its folder, Levyra CI Workflows needs the command-line tools its instructions call (gh).

Does Levyra CI Workflows access the network?

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

Is Levyra CI Workflows 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 Levyra CI Workflows use?

Levyra CI Workflows is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Levyra CI Workflows use?

About 2k tokens (SKILL.md is roughly 7.8k 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 Levyra CI Workflows?

Skills that share tags, products or a category with Levyra CI Workflows: Upgrade Notes (getknit/knit, 133 stars), Validating Compose Stability (skydoves/android-testing-skills, 334 stars), Kt Search Release (jillesvangurp/kt-search, 155 stars) and Post Edit Verification (GerardPaligot/Confily, 152 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Levyra CI Workflows?

LUC4N3X (a GitHub user) maintains it in LUC4N3X/Levyra-deepsound, which has 590 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 10, 2026.

Source: LUC4N3X/Levyra-deepsound on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.