DataDog

Record gensim episodes on a remote Linux VM with the anomaly-detection recorder and fetch Parquet recordings for the Agent Anomaly Detection team's testbench evals. Use for "record a gensim scenario on a VM", "set up the gensim VM", or "record a batch of…

Create a pull request for the current branch with proper labels and description. Any agent opening a PR in this repo (via `gh pr create` or otherwise), whether invoked directly as /create-pr or as part of a larger task, MUST follow this skill's process rather…

Monitor the current PR's GitLab pipeline to completion, then report success, retry, auto-fix, or investigate a failure. Use when the user asks to follow, babysit, watch, or wait on a PR/pipeline, or just after pushing to / creating a PR.

Handle a CI failure that is reliably attributed to the current PR's own code changes. Trigger phrases include: - "handle this PR-caused CI failure" - "fix the CI regression" - "continue investigating this PR failure"

Classify a failed CI as either caused by an active incident, flakiness, or a true code regression. Use when a PR's pipeline is red and it isn't obvious whether the PR's own changes are at fault. Trigger phrases include: - "investigate this CI failure" -…

Write or extend Datadog Agent new-e2e tests, including fakeintake coverage and the GitLab wiring that runs them; derives scope from the current diff when no target is named. Not for running tests that already exist (run-e2e, run-windows-e2e), or for judging…

Add a new configuration field to the Datadog Agent (datadog.yaml) by declaring it in the config schema

Validate live GPU metrics on clusters running the Agent version under test and investigate missing metrics or tag failures. Use when asked to validate GPU metrics on live clusters, check a GPU Agent release, or run dda inv gpu.validate-metrics.

Create or modify contrib instrumentation, integration registration, manifests, and APM integration tests.

Create or modify LLMObs integration lifecycle, extraction, streaming, usage metrics, and tests.

Register a new environment variable / configuration option in dd-trace-py. Use whenever you add (or rename) a DD_*/_DD_*/OTEL_*/DATADOG_* environment variable so it is documented, validated, and tracked for cross-language feature parity. Covers…

Native crash log analysis for dd-trace-py

Run circular import detection against ddtrace and propose architectural fixes for any cycles found. Use this when adding or refactoring modules, or when the detect_circular_imports CI job reports new cycles on a PR.

Compare CPython source code between two Python versions to identify changes in headers and structs. Use this when adding support for a new Python version to understand what changed between versions.

Diagnose and fix slow base venv build times caused by unnecessary recompilation of native extensions (CMake, Cython, Rust) across test environment builds. Use when CI base venv builds are slow, when ext_cache isn't saving time, or when investigating warm…

Run the dependency direction detector against ddtrace and propose architectural fixes for any violations found. Use this when adding or refactoring modules under ddtrace/internal, ddtrace/contrib, or any product package, or when the detect_layering_violations…

Use when generating or refreshing a version's CHANGELOG.md section from author-provided metadata on PRs merged into develop.

Use when creating a new branch in dd-sdk-ios for a JIRA ticket, feature, or regular release. Use when choosing a branch name or base branch.

Use when committing changes in dd-sdk-ios. Use when writing commit messages, signing commits, or staging files before a commit.

Use when creating a pull request in dd-sdk-ios. Use when writing PR titles, PR body, or choosing the target branch.

Use when preparing a regular dd-sdk-ios release through changelog generation, version bumping, feature-doc verification, and opening the release PRs to master and develop.

Use when creating a git worktree for dd-sdk-ios, starting isolated work alongside another checkout, or when a fresh worktree fails to build or test — missing DD_SDK_COMPILED_FOR_TESTING symbols, "no such module 'OpenTelemetryApi'", or missing *.local.xcconfig…

Use when asked to run tests in the dd-sdk-ios project — whether a full module suite, a specific test class, or a single test method. Use when choosing between make, xcodebuild, or Xcode MCP for running iOS/tvOS/visionOS tests, or when tests must run under a…

Use when inspecting or changing build settings, compiler flags, Swift flags, deployment targets, active compilation conditions, Info.plist keys, or entitlements for a dd-sdk-ios Xcode target. Use when you would otherwise read or edit project.pbxproj directly.

Datadog API CLI with 49 command groups, 300+ subcommands. Skills and domain agents for monitoring, logs, APM, security, and infrastructure.

Load when investigating a failing PR CI pipeline or checking PR health. Attributes each CI failure as flaky, infra, or regression, proposes a targeted action, and reports code coverage.

Load when investigating a specific flaky test. Gets history, failure pattern, and category, then recommends fix, quarantine, or escalate.

Find, filter, count, and connect software, teams, engineering work and delivery, infrastructure, and operational or security records through Pup's read-only Datadog entity graph. Use for inventory, ownership, dependencies, and status questions across…

Log management - search, pipelines, archives, and cost control.

Monitor management - create, update, mute, and alerting best practices.

File GitHub issues to the right repository (pup CLI or plugin)

Datadog CLI (pup). OAuth2 auth with token refresh.

Performance-overhead review of a code diff / branch / PR for the dd-trace-java tracer. Flags hot-path allocation, unbounded memory, repeated work, escaping objects, native-boundary crossings, and JVM-specific pitfalls (escape analysis, JNI / virtual-thread…

Enable one mechanically enforceable lint or static-analysis rule in blocking CI, preferring SpotBugs. Use when adding a SpotBugs detector, turning a repetitive PR review theme into a lint, adding a ForbiddenAPIs signature, or writing a custom Gradle source…

Diagnose and fix scope or continuation lifecycle failures in dd-trace-java instrumentation tests. Use when a test reports a continuation leak, double resolution, activation after resolve, or an unclosed scope. Reads the automatic diagnostic timeline, finds…

Write a new library instrumentation end-to-end. Use when the user ask to add a new APM integration or a library instrumentation.

Diagnose and fix scope or continuation lifecycle failures in dd-trace-java instrumentation tests. Use when a test reports a continuation leak, double resolution, activation after resolve, or an unclosed scope, or when strictTraceWrites(false) appears to hide…

Diagnose and resolve dd-trace-java CI failures from a module's muzzle task or the runMuzzle aggregate. Use when CI names muzzle/runMuzzle, reports Muzzle validation or version-range resolution failures, or starts failing after a newly published library…

Converts Spock/Groovy test files in a Gradle module to equivalent JUnit 5 Java tests. Use when asked to "migrate groovy", "convert groovy to java", "g2j", or when a module has .groovy test files that need to be replaced with .java equivalents.

Clarify or review Java Javadocs, Javadoc tags, and explanatory code comments for legibility, accuracy, and source alignment. Use when asked to simplify verbose or generated comments, edit documentation in a local file, class, or member, repair Javadoc markup,…

Implement a new POSIX command as a builtin in the safe shell interpreter

Improve test coverage for shell features and commands using reference test suites from yash, GNU coreutils, and uutils/coreutils

Read PR review comments, evaluate validity, implement fixes, push changes, and reply/resolve threads

Diagnose and fix CI failures on a GitHub PR by analyzing failing checks, reading logs, and applying fixes

Self-review a PR, fix all issues, and re-review in a loop until clean. Coordinates code-review, address-pr-comments, and fix-ci-tests skills.

Systematically review and improve every shell feature and builtin command. Iterates through each feature/command, runs code-review, fixes issues, and re-reviews until clean.

Comprehensive code review covering security, correctness, bash compatibility, test coverage, and code quality. Use for PRs, commits, or any code changes.

Fix failing tests by prioritising shell implementation fixes to match bash behaviour

Use when adding, debugging, fixing, or modifying instrumentation and plugins for third-party libraries in dd-trace-js. Triggers: "add a new integration", "instrument a library", any *Plugin base class (Tracing/Database/Cache/…

Validate v5 compatibility when adding or modifying Test Optimization or test framework integration tests in dd-trace-js.

Use when a dd-trace-js change introduces or substantially changes a class hierarchy, module boundary, shared helper layer, public API, or duplicated behavior across multiple types. Triggers: architecture decision, design review, refactor shared behavior, new…

Use when classifying, investigating, or fixing a suspected flaky test, intermittent test result, nondeterministic CI test failure, timing race, hang, or test-order dependency in dd-trace-js. Classifies infrastructure and deterministic failures before…

Use when adding, debugging, or modifying LLMObs plugins for an LLM library in dd-trace-js. Triggers: "add LLMObs support", "instrument chat completions / streaming / embeddings / agent runs / orchestration / tool calls / retrieval", "LLMObsPlugin",…

Use when writing, modifying, or debugging tests for an LLMObs plugin in dd-trace-js. Triggers: "write LLMObs tests", "test an LLMObs plugin", "assertLlmObsSpanEvent", "useLlmObs", "getEvents", any MOCK_* matcher ("MOCK_STRING" / "MOCK_NOT_NULLISH" /…

Use when adding, modifying, debugging, or reviewing dd-trace-js serverless platform integrations that create root invocation spans for AWS Lambda, Azure Functions, Google Cloud Functions, or similar runtimes. Triggers: serverless integration, function…

Pre-PR preparation flow for the dd-sdk-android project — verifies branch naming, runs local CI checks (compile, tests, linter) and regenerates checked-in generated files so CI passes on the first push. Accepts optional combinable arguments: lint, test,…

Create or update Graphite PR stacks for dd-sdk-android. Use when splitting a feature branch into stacked PRs, restacking branches after committed changes, or submitting updates to an existing stack. Accepts create or update.

Code review for dd-sdk-android. Use when reviewing a feature branch or pull request for performance issues, binary compatibility, threading bugs, main-thread blocking, and other defects.

Commit-message conventions for dd-sdk-android. Use when drafting or reviewing commit messages and PR titles, making a requested commit, or generating messages for other skills.

Unit-test conventions for dd-sdk-android. Use when creating, editing, or reviewing Kotlin unit tests and test fixtures with JUnit 5, Mockito, Elmyr Forge, and AssertJ.

Use when verifying SDK event payloads in the Android SDK sandbox, debugging what events are emitted, or validating request bodies via logcat with the sample Kotlin app.

Environment validation checklist. Run this FIRST when starting a new Claude session to verify the environment is ready for optimization work. Checks Rust toolchain, ci/ scripts, build, benchmarking tools, profilers, memory tools, git state, and SMP CLI.

Prepare a lading release. Updates CHANGELOG.md, bumps version in Cargo.toml, updates Cargo.lock, commits, and creates a PR.

Coordinates optimization attempts. Captures baselines, implements changes, invokes review, and records outcomes.

Reviews optimization patches using a 5-persona peer review system. Requires unanimous approval backed by benchmarks.

Full optimization workflow with git branch creation, commits, and optional PR. Wraps /lading-optimize-hunt with git automation.

Finds a valid optimization target in lading. Returns a filled target.yaml template with pattern, technique, target, file, bench, and fingerprint. Use before /lading-optimize-hunt or when selecting a new optimization target.

Create a new pathrunner exploit module from pathfinding.cloud path definition

Batch-create pathrunner exploit modules from a list of pathfinding-labs coverage gaps, using a rolling pool of concurrent sub-agents that enable → build → test → disable each lab. Verify stage iteratively fixes pathrunner-side failures (default budget 5 per…

Clean up AWS resources after testing a pathrunner module against a pathfinding-labs scenario

List pathfinding-labs scenarios that don't have pathrunner modules yet

Enable, disable, and swap pathfinding-labs scenarios via plabs, serializing terraform applies through a shared lock so concurrent agents don't collide

Test a pathrunner exploit module against a deployed pathfinding-labs scenario. Supports iterative fix-and-retry — the skill can loop up to N times, diagnosing pathrunner-side failures and applying fixes between runs.

Run Saluki's Panoramic correctness and integration tests non-interactively and investigate their machine-readable results. Read this before running `panoramic`, `make test-integration`, or `make test-correctness`, or when diagnosing a test from its artifacts.

Update the vendored configuration schema

Architecture and working rules for Saluki's configuration system and inventory. Read this when working with lib/agent-data-plane-config*, lib/datadog-agent/config*, GenericConfiguration, schema_overlay.yaml, SalukiConfiguration, DatadogConfiguration, or typed…

Write a Reno release-note fragment under `releasenotes/notes/` for a change, or determine that a change needs the `changelog/no-changelog` label instead. TRIGGER when: user asks for a release note, a changelog entry, or a changelog fragment; the release-note…

Analyze agent-data-plane binary size to identify top crates and modules contributing to binary size, and evaluate optimization opportunities. TRIGGER when: user asks about binary size, code size, shrinking the binary, binary optimization, reducing binary…

Trigger CI for an external contributor's pull request by mirroring their fork branch onto DataDog/saluki under an `<owner>/<branch>` name. External forks don't run CI by default for security reasons; this skill lets an authorized maintainer push the fork's…

Analyze Azure DevOps CI failures in dd-trace-dotnet using live build data or supplied logs. Use for failing builds, PR checks, and snapshot-versus-span-count diagnosis.

Review committed SDK changes before push, or review a requested diff, range, branch, or PR for correctness, security, design, performance, maintainability, repository conventions, and cross-SDK consistency.

Add or change lint rules and static analysis in dd-trace-dotnet. Use when adding a lint rule, Roslyn analyzer, diagnostic, BannedSymbols entry, StyleCop/editorconfig severity, CppCheck suppression, or Clang-Tidy check, or when the user asks how to enforce a…

Update/bump the libdatadog native library version in dd-trace-dotnet. Use when the user asks to bump, update, or upgrade libdatadog, or mentions a new libdatadog release version.

Dev/test workflow for tracer engineers working on the Datadog .NET tracer — build a local Datadog.AzureFunctions NuGet package, deploy it to a test Azure Function App, trigger it, and analyze traces/logs to verify instrumentation behavior. Use this skill…