dynatrace-oss

Manage AI resources (skills, commands, agents) using aimgr CLI. Use when user asks to: (1) Install/uninstall resources, (2) Manage repository, (3) Discover/recommend resources for a project, (4) Troubleshoot aimgr issues.

Claude-specific skill for testing

"This has invalid YAML

First skill in mixed repository

First test skill for discovery testing

Second test skill for discovery testing

Skill nested several directories deep

Automated test generation for functions and components

Use this skill when the AI assistant should simplify recently changed files after implementation work, using recent-change scope guardrails and parallel reuse/quality/efficiency review lenses. Do not use this skill for whole-repository cleanup sweeps, architecture rewrites.

Use this skill for beads-centric planning, issue structure, execution orchestration, acceptance review gates, beads setup/runtime troubleshooting, beads health checks, and beads follow-up bug/task filing when users ask to capture tracker bugs/tasks (for example with repro and expected vs actual), even without explicitly saying beads. Trigger only for beads tracker workflow requests. Do not trigger for opencode-coder mode/runtime controls (stealth mode, team mode, OPENCODE_CODER_DISABLED), observability or production-log triage into bugs, external task-sync/import-export workflows (GitHub issues/Jira), docs lifecycle/taxonomy cleanup, simplify cleanup, GitHub releases, or general coding tasks.

Use this skill only for core opencode-coder plugin/runtime workflows: init/setup guidance, mode/runtime behavior, plugin-runtime status/doctor troubleshooting, plugin/runtime debug-log analysis, plugin/runtime bug reporting, and session dump export.

Use this skill whenever the user wants to create, refresh, review, reorganize, audit, slim, standardize, or fix project documentation; define canonical docs taxonomy; update AGENTS.md routing; or clean up stale, confusing, misrouted, or hollow docs. Trigger even when the user says things like 'our docs are messy,' 'does AGENTS still match the repo?,' 'help standardize the docs,' or 'review the docs before changing anything.'

GitHub backend for task synchronization. Syncs beads issues with GitHub issues bidirectionally using gh CLI. Use when: (1) User wants to sync with GitHub specifically, (2) Task-sync skill delegates to GitHub backend, (3) User mentions 'GitHub issues', 'gh sync', or 'import from GitHub'. Implements import (GitHub → beads), export (beads → GitHub), and bidirectional workflows.

Internal dev skill for working IN the opencode-coder plugin repo. Use when the AI assistant needs to: (1) Analyze OpenCode logs using the log-analyzer tool, (2) Run or understand dev commands (analyze-logs, fix-bugs, import-tasks, release), (3) Execute the release workflow, (4) Triage and import bugs from GitHub issues, (5) Understand plugin internals for development

Create or adapt skills for OpenCode, improve existing skills through iterative test-and-review loops, and package finished skills. Use when users want to author a skill from scratch, revise skill behavior, run qualitative/quantitative evaluations, or prepare a distributable .skill bundle.

Bidirectional synchronization between beads and external task systems (GitHub, Jira, etc.). Use when: (1) User wants to sync tasks or issues with external systems, (2) Import external issues into beads, (3) Export beads to external systems, (4) User mentions 'sync', 'GitHub issues', 'Jira tickets', 'import bugs', or 'export tasks'. Orchestrates workflow and delegates to backend-specific skills.

Create and update dashboard and workflow documentation

Load when working in the Dynatrace Snowflake Observability Agent (DSOA / SnowAgent) codebase or planning DSOA work. Provides full project context: plugin architecture, tech stack, code style mandates (pylint 10.00/10, black, sqlfluff), testing patterns (mock/live dual mode), documentation rules, build pipeline, delivery process (4-phase), and anti-patterns. Required before writing any DSOA code, tests, SQL, or docs.

Create and update Dynatrace dashboards for DSOA telemetry

Create and update Dynatrace workflows for DSOA automation

Create and update DSOA plugins — full development lifecycle from planning through validation

Review a pull request and process review comments left by others

AI-guided QA walkthrough for DSOA releases. Automates version detection, deployment commands, notebook deployment, and interactive test walkthrough. Use when a QA engineer needs to execute the DSOA release test suite.

Create and update Snowflake synthetic test setups for DSOA telemetry validation

Investigate incidents, debug performance issues, analyze logs, and manage observability resources in Dynatrace using the dtctl CLI. Use this skill whenever the user asks about error rates, latency spikes, service health, crash-looping pods, web vitals, SLO status, open problems, root cause analysis, log patterns, trace analysis, or building dashboards — even if they don't mention Dynatrace by name. Also covers DQL queries, workflow management, notebook and dashboard creation, settings configuration, and any operations against a Dynatrace environment.

Explain and operate the dtctl release process, which is automated by release-please. Use this skill whenever the user says "release", "ship it", "cut a release", "new version", "bump version", "publish", or asks how dtctl releases work, why a release PR exists, or how to trigger/finish a release.

Perform a thorough quality review of a pull request or feature branch before merging. Use this skill whenever the user asks to review a PR, check if code is production-ready, assess quality, verify docs are updated, or asks "is this ready to merge?", "review this PR", "check quality", "is this production ready?", or similar. Also use when reviewing your own work before submitting.

Guidance for implementing OpenTelemetry auto-instrumentation for various runtimes in dtwiz

Deploy Dynatrace observability with dtwiz — analyze systems, get ranked recommendations, and install monitoring (OneAgent, Kubernetes, Docker, OTel, AWS, Azure, GCP). Use when the user wants to set up, manage, or ingest data into Dynatrace monitoring. Covers ingesting metrics, logs, and traces from AWS, Azure, GCP, Kubernetes, containers, or hosts into Dynatrace via dtwiz.

How dtwiz discovers, identifies, and correlates running OS processes to project directories across Unix and Windows

Step-by-step skill for investigating production issues using the Dynatrace MCP Server. Covers problem triage, log analysis, entity lookup, vulnerability review, and DQL queries.

Query and investigate Dynatrace Managed (self-hosted) environments from the CLI. Use this skill when the user asks about problems, incidents, entities, events, logs, metrics, SLOs, or security vulnerabilities in a Dynatrace Managed cluster — even if they don't mention dtmgd by name. Covers connectivity checks, entity topology, time-series metric queries, log search, and full feature parity with the Dynatrace Managed MCP Server.