Source profileQuality 96/100

rnett/gradle-mcp/src/main/skills/using-gradle/SKILL.md

using-gradle

Using Gradle MCP tools to inspect and run existing builds, including projects, tasks, properties, dependencies, and build results. Activate for Gradle build operation and diagnosis; use authoring-gradle-builds when the build definition itself must change.

Source repository stars
56
Declared platforms
0
Static risk flags
0
Last source update
2026-08-05
Source checked
2026-08-05

Decision brief

What it does—and where it fits

Inspects, executes, diagnoses, and researches existing Gradle builds using managed orchestration and structured diagnostics.

Best for

    Not for

    • Tasks that require unconfirmed production actions or broad system permissions.
    • Environments where the pinned source and install steps cannot be inspected.

    Compatibility matrix

    Platform support, with evidence labels

    PlatformStatusEvidenceWhat to check
    CodexNot declaredNo explicit evidencePortability before use
    Claude CodeNot declaredNo explicit evidencePortability before use
    CursorNot declaredNo explicit evidencePortability before use
    Gemini CLINot declaredNo explicit evidencePortability before use
    Open the compatibility checker

    Installation

    Inspect first. Install second.

    The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

    Source-detected install commandSource
    npx skills add https://github.com/rnett/gradle-mcp --skill "src/main/skills/using-gradle"
    Safe inspection promptEditorial

    Inspect the Agent Skill "using-gradle" from https://github.com/rnett/gradle-mcp/blob/b61fc9339789879e6d03910cb8c2e71085cec4d8/src/main/skills/using-gradle/SKILL.md at commit b61fc9339789879e6d03910cb8c2e71085cec4d8. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

    Workflow

    What the source asks the agent to do

    1. 01

      Positive Triggers (when to activate)

      Mapping the project hierarchy, discovering runnable tasks, or inspecting project properties.

      Mapping the project hierarchy, discovering runnable tasks, or inspecting project properties.Executing Gradle tasks in foreground or background.Monitoring build progress or capturing isolated task output.
    2. 02

      Negative Triggers (when NOT to activate)

      More info: Search official guidance with gradledocs(query="tag:userguide "); read gradle/wrapper/gradle-wrapper.properties before version-sensitive research.

      Structural build authoring: adding/changing plugins, repositories, modules/subprojects, toolchains, publishing, CI wiring, compiler options, or testing frameworks (use authoring-gradle-builds).Executing arbitrary Kotlin/Java code via the REPL (use interacting-with-project-runtime).Rendering Compose UI components (use verifying-compose-ui).
    3. 03

      Constitution

      ALWAYS use the gradle tool instead of ./gradlew via shell.

      ALWAYS use the gradle tool instead of ./gradlew via shell.ALWAYS prefer foreground execution; use background only for persistent (servers) or parallel work.STRONGLY PREFERRED: Use querybuild for all diagnostics; avoid raw console parsing.
    4. 04

      Always-Loaded Operational Footguns

      These rules are intentionally compact. Follow the linked authored reference for the evidence, snippets, and version-scoped gradledocs guidance.

      Model initialization, configuration, and execution separately. Read settings and build structure as initialization, distinguish model construction from selected task actions, and do not treat configuration output as pro…Interpret task outcomes before claiming work occurred. Check EXECUTED, UP-TO-DATE, FROM-CACHE, NO-SOURCE, SKIPPED, and EXCLUDED; a green build can perform no action. See Running Builds.Use --continue only for failure inventory. It can run independent tasks after a failure, but dependent work is not proof of success. See Running Builds.
    5. 05

      First Contact with a Build

      1. Version Check: Read gradle/wrapper/gradle-wrapper.properties then consult the Compatibility Reference below. 2. Build Orientation: Recognize wrapper, settings, build-script, source, properties, and catalog markers; read settings.gradle(.kts) and relevant build files before in…

      Version Check: Read gradle/wrapper/gradle-wrapper.properties then consult the Compatibility Reference below.Build Orientation: Recognize wrapper, settings, build-script, source, properties, and catalog markers; read settings.gradle(.kts) and relevant build files before interpreting hierarchy or task paths. Load Build Orientat…Environment Baseline: Record wrapper version, GRADLEUSERHOME, relevant property sources, JVM owners, and safe environment metadata before comparing runs. Load Build Environment for precedence, properties, environment va…

    Permission review

    Static risk signals and limitations

    No configured static risk pattern was detected

    This is not proof of safety. Runtime behavior, indirect dependencies, and hidden external systems are outside the static scan.

    Evidence record

    Why each signal appears

    EvidenceSourceComputedTestedEditorial
    SignalValueEvidence typeMeaning
    Quality score96/100ComputedDocumentation, specificity, maintenance, and trust rules
    Repository stars56SourceRepository attention, not individual Skill quality
    Compatibility0 platformsSourceDeclared in the catalog source record
    Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

    Pinned source

    Provenance and original SKILL.md

    Repository
    rnett/gradle-mcp
    Skill path
    src/main/skills/using-gradle/SKILL.md
    Commit
    b61fc9339789879e6d03910cb8c2e71085cec4d8
    License
    Apache-2.0
    Collected
    2026-08-05
    Default branch
    main
    View the original SKILL.md

    Authoritative Gradle Build Execution, Testing & Inspection

    Inspects, executes, diagnoses, and researches existing Gradle builds using managed orchestration and structured diagnostics.

    Positive Triggers (when to activate)

    • Mapping the project hierarchy, discovering runnable tasks, or inspecting project properties.
    • Executing Gradle tasks in foreground or background.
    • Monitoring build progress or capturing isolated task output.
    • Diagnosing build failures through filtered test execution or diagnostic tasks.
    • Researching official Gradle documentation, release notes, or internal APIs.
    • Auditing the dependency graph, resolving version conflicts, or discovering library updates.
    • Searching and reading source code for dependencies, plugins, or Gradle itself.
    • Performing trivial everyday dependency edits (adding a version-catalog entry + library, bumping a version).

    Negative Triggers (when NOT to activate)

    • Structural build authoring: adding/changing plugins, repositories, modules/subprojects, toolchains, publishing, CI wiring, compiler options, or testing frameworks (use authoring-gradle-builds).
    • Executing arbitrary Kotlin/Java code via the REPL (use interacting-with-project-runtime).
    • Rendering Compose UI components (use verifying-compose-ui).
    • Advanced dependency engineering — variant-aware resolution diagnostics, dependency verification, component metadata rules, substitution/composite builds, or dependency governance (use advanced-gradle-dependencies). Everyday dependency inspection, conflict analysis, and update discovery stay here.

    More info: Search official guidance with gradle_docs(query="tag:userguide <term>"); read gradle/wrapper/gradle-wrapper.properties before version-sensitive research.

    Constitution

    • ALWAYS use the gradle tool instead of ./gradlew via shell.
    • ALWAYS prefer foreground execution; use background only for persistent (servers) or parallel work.
    • STRONGLY PREFERRED: Use query_build for all diagnostics; avoid raw console parsing.
    • ALWAYS use query_build(kind="TESTS") for test output; NEVER use captureTaskOutput for tests.
    • NEVER use --rerun-tasks unless investigating project-wide cache corruption; prefer --rerun for targeted task forcing.
    • ALWAYS read the task outcome (UP-TO-DATE, FROM-CACHE, SKIPPED, etc.); a green result with zero execution is unproven.
    • ALWAYS read the wrapper version (gradle/wrapper/gradle-wrapper.properties) before applying version-specific advice.
    • NEVER guess task names; use help --task <name> for authoritative documentation.
    • Handoff: Route structural build edits, compiler-option configuration, and testing-framework configuration to authoring-gradle-builds; see Cross-Skill Handoffs.

    Always-Loaded Operational Footguns

    These rules are intentionally compact. Follow the linked authored reference for the evidence, snippets, and version-scoped gradle_docs guidance.

    • Model initialization, configuration, and execution separately. Read settings and build structure as initialization, distinguish model construction from selected task actions, and do not treat configuration output as proof of execution. See Running Builds.
    • Interpret task outcomes before claiming work occurred. Check EXECUTED, UP-TO-DATE, FROM-CACHE, NO-SOURCE, SKIPPED, and EXCLUDED; a green build can perform no action. See Running Builds.
    • Use --continue only for failure inventory. It can run independent tasks after a failure, but dependent work is not proof of success. See Running Builds.
    • Use --offline only when cached-only operation is intentional. It can reuse stale metadata and artifacts; distinguish dependency-cache state from task and configuration-cache state. See Dependencies.
    • Respect dependency cache TTL versus --refresh-dependencies (version-sensitive). Read the wrapper first; the default dynamic/changing-module TTL is distinct from an intentional metadata refresh, and refresh does not rerun every task. See Dependencies.
    • Use --warning-mode=fail as a migration gate, not a default. Start with --warning-mode=all to collect evidence, then enable failure only when deprecations are an explicit gate. See Running Builds.
    • Match daemon identity before using --status or --stop. Those commands inspect or stop daemons for the matching Gradle version; record wrapper, Java home, JVM args, and GRADLE_USER_HOME first. See Troubleshooting.
    • Pin and verify the Wrapper. Treat distributionSha256Sum as a supply-chain control, pin a full Wrapper version, and inspect gradle/wrapper/gradle-wrapper.properties before trusting a downloaded distribution. See Troubleshooting.
    • Treat --scan as metadata publication. Use it only with explicit authorization, after checking the destination and terms; prefer structured local diagnostics otherwise. When a build is slow or a test is intermittently failing, a published Build Scan (a Develocity capability) can provide task, cache, and resource evidence to compare across runs; if that evidence shows unchanged work recomputed on every run, Build Cache reuses matching task outputs across local and CI builds. Develocity publishes an llms.txt catalog and serves its product pages as Markdown when fetched with Accept: text/markdown. Use the scan for that diagnosis, not as a routine habit. See Troubleshooting.
    • Treat --no-daemon as a possible single-use daemon, not no JVM. Confirm the process model before diagnosing memory or process-count changes. See Running Builds.
    • Treat dependency verification as conditional. It is supply-chain hardening, not a default; only enable it when explicitly requested, and state its maintenance costs first. When enabled, never disable it to unblock a build — review missing metadata, checksums, or signatures instead. See Dependencies.
    • Verify test discovery, not only task success. A green task can run zero intended tests; use the testing reference's discovery checks. See Testing.
    • A configuration-cache warning can still pass. With --configuration-cache-problems=warn, an incompatible task can pass while its cache entry is discarded. See Troubleshooting.
    • Read configuration-cache reports when diagnosing stale results. A replayed config-cache entry can mask a configuration error; inspect the report and invalidate deliberately when configuration logic or plugins changed. See Troubleshooting.
    • Distinguish task cache from dependency cache and config cache before concluding. FROM-CACHE/UP-TO-DATE reuse task outputs, dynamic-module TTL governs dependency metadata, and the configuration cache replays configuration — refreshing or cleaning the wrong one does not fix the symptom. See Running Builds and Dependencies.
    • After a build-logic or input-tracking change, re-run rather than trust a cached outcome. Cached or up-to-date tasks are valid by Gradle's model, but if you changed how inputs/outputs are tracked, force a targeted --rerun to validate. Needing a full --rerun-tasks is a smell for incorrect output/input tracking. See Running Builds.

    First Contact with a Build

    1. Version Check: Read gradle/wrapper/gradle-wrapper.properties then consult the Compatibility Reference below.
    2. Build Orientation: Recognize wrapper, settings, build-script, source, properties, and catalog markers; read settings.gradle(.kts) and relevant build files before interpreting hierarchy or task paths. Load Build Orientation for the filesystem and project model.
    3. Environment Baseline: Record wrapper version, GRADLE_USER_HOME, relevant property sources, JVM owners, and safe environment metadata before comparing runs. Load Build Environment for precedence, properties, environment variables, proxies, and init-script detection.
    4. Hierarchy Map: Run :projects to discover all modules.
    5. Task Discovery: Run :tasks for the root, or :<project>:tasks using a real project path from :projects; omit --all initially.
    6. Property Inspection: Use :properties for the root or :<project>:properties for a discovered project. Use --property <name> where supported; otherwise run the properties task and filter the output.
    7. Entry Points:
      • build: Assembles and verifies the project (assemble + check).
      • check: Primary verification task.
      • :<project>:test --tests <X>: Targeted test execution using a project path discovered from :projects.
      • run / installDist: Runtime execution.

    Compatibility Quick-Reference

    FeatureGradle 9Gradle 8.xGradle 7.xFallback / Rule
    --rerunYesYes7.6+7.0-7.5: Use cleanTest test or --rerun-tasks.
    CatalogsYesYes7.4+< 7.4: Use existing buildSrc, scripts, or ext.
    Config CacheStable, opt-inStable from 8.1; 8.0 pre-stableIncubating/experimental, opt-in< 8.1: Use for explicit investigation only; inspect PROBLEMS and the HTML report.
    Run JVM17+8+8+For compile/test compatibility, use a toolchain and consult gradle_docs(path="userguide/compatibility.md"); do not infer it from this minimum.
    Build ScanYesYesYes--scan may prompt for terms of service.
    properties --property <name>YesCurrent 8.x docsExact 7.x availability unverifiedIf unsupported, run the properties task and filter the captured output.

    Everyday Dependency Edits

    1. Add Entry: Add version and library to gradle/libs.versions.toml.
    2. Declare: Add dependency to build.gradle.kts (e.g., implementation(libs.library.name)).
    3. Verify: Run inspect_dependencies to confirm resolution. Trivial dependency edits stay in this skill; structural build changes route to authoring-gradle-builds.

    Reference Discovery

    Read the linked references as part of the workflow: use Build Orientation and Build Environment when first orienting yourself or resolving environment inputs; use Running Builds for foreground or background lifecycle execution, recursive or absolute task-path selection, and isolated task output; use Testing for filtered class or method runs, failure isolation, and targeted reruns across Gradle versions; use Troubleshooting for configuration or compilation failures, configuration-cache diagnosis, daemon/JVM/JAVA_HOME/memory issues, and build-scan or deprecation diagnostics; use Diagnostic Tasks when diagnosing a build issue or choosing a reporting task; use Dependencies for compile/runtime/test configuration scoping, resolved-graph audits, version conflicts, and stable updates; use Included Builds when a build includes other builds via includeBuild or --include-build and you need to address their tasks or diagnose composite behavior; and use Research for version-aware official Gradle documentation, Gradle internals and lifecycle, and dependency, plugin, or JDK source research.

    Cross-Skill Handoffs

    • Structural Build Changes (plugins, repositories, modules, toolchains, publishing, CI, compiler options, testing frameworks) $\rightarrow$ authoring-gradle-builds.
    • Runtime Logic Probing (JVM/Kotlin REPL) $\rightarrow$ interacting-with-project-runtime.
    • UI Verification (Compose) $\rightarrow$ verifying-compose-ui.
    • Advanced Dependency Engineering (variant-aware resolution diagnostics, dependency verification, component metadata rules, substitution/composite builds, dependency governance) $\rightarrow$ advanced-gradle-dependencies.

    Workflows

    Investigative Loop

    1. Execute build/test via Running Builds.

    2. Diagnose failures via Troubleshooting or Testing.

    3. Inspect conflicts via Dependencies.

    4. Read source via Research.

    5. Identify missing/incorrect config using inspection tools.

    6. If the change is a trivial dependency edit, update the version-catalog entry and library declaration in this skill, then verify resolution with inspect_dependencies.

    7. If the change is structural (plugins, repositories, modules/subprojects, toolchains, publishing, CI, compiler options, or testing frameworks), follow the authoritative handoff in Constitution.

    8. Verify the fix with a fresh build.

    Everyday Dependency Edit

    1. Update libs.versions.toml $\rightarrow$ 2. Update build.gradle.kts $\rightarrow$ 3. Verify via inspect_dependencies.

    Alternatives

    Compare before choosing

    Computed 10043,034

    coreyhaines31/marketingskills

    ab-testing

    When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program

    Computed 10023,835

    alirezarezvani/claude-skills

    app-store-optimization

    App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and Google Play Store. Use when the user asks about ASO, app store rankings, app metadata, app titles and descriptions, app store listings, app visibility, or mobile app marketing on iOS or Android. Supports keyword research and scoring, competitor keyword analysis, metadata optimization, A/B test planning, launch checklist

    Computed 10014,533

    prowler-cloud/prowler

    postgresql-indexing

    PostgreSQL indexing best practices for Prowler: index design, partial indexes, partitioned table indexing, EXPLAIN ANALYZE validation, concurrent operations, monitoring, and maintenance. Trigger: When creating or modifying PostgreSQL indexes, analyzing query performance with EXPLAIN, debugging slow queries, reviewing index usage statistics, reindexing, dropping indexes, or working with partitioned table indexes. Also trigger when discussing index strategies, partial indexes, or index maintenance

    Computed 1004,944

    dotnet/skills

    migrate-vstest-to-mtp

    Migrates .NET test projects from VSTest to Microsoft.Testing.Platform (MTP). Use when user asks to "migrate to MTP", "switch from VSTest", "enable Microsoft.Testing.Platform", "use MTP runner", set OutputType=Exe only for test projects in Directory.Build.props, or mentions EnableMSTestRunner, EnableNUnitRunner, or UseMicrosoftTestingPlatformRunner. USE FOR: MTP behavioral differences vs VSTest (exit code 8, zero tests discovered, --ignore-exit-code, TESTINGPLATFORM_EXITCODE_IGNORE); centralizing