claude-osdu

Generate daily OSDU briefing notes by aggregating GitLab MRs, SPI fork health, vault goals, and brain knowledge into an insightful daily note. Use when the user says "gm", "good morning", "briefing", "daily briefing", "morning standup", "what's on my plate", or "start my day". Not for: ad-hoc status checks or single-service queries.

Fork management lifecycle for Azure OSDU SPI service forks — three-branch strategy, upstream sync, cascade integration, conflict resolution, template propagation, and multi-repo status monitoring across 8 service forks. Use when checking sync status, reviewing cascades, resolving conflicts, triggering manual syncs, managing fork_upstream/fork_integration/main branches, or coordinating template updates across osdu-spi-* repos. Not for: infrastructure deployment (use iac skill), OSDU GitLab services (use osdu plugin), or tool installation (use setup skill).

Comprehensive health assessment of deployed SPI environments — cluster infrastructure, Azure PaaS resources, workloads, and OSDU platform services. Use when the user asks about SPI environment health, cluster status, Azure PaaS health, CosmosDB status, Service Bus health, or wants a report on their deployed SPI environments. Trigger on phrases like "report on my SPI environment", "environment health", "how is my cluster", "cluster status", "is CosmosDB healthy", or "what's deployed". Not for: deploying or modifying infrastructure (use the iac skill), fork management (use the forks skill), installing tools (use the setup skill), or CIMPL environments (use cimpl:health).

Infrastructure as Code for Azure SPI — Terraform modules, Azure PaaS services (CosmosDB, Service Bus, Storage, Key Vault), Helm/Kustomize deployments, AKS Deployment Safeguards, azd integration, multi-partition support, and systematic debugging for the osdu-spi-infra repository. Use when working with SPI Terraform, Azure PaaS provisioning, azd up/down, Workload Identity, multi-partition resources, feature flags, blue/green stacks, deployment failures, or infrastructure verification. Not for: fork management (use the forks skill), CIMPL infrastructure (use cimpl:iac), OSDU platform services, or tool installation (use setup skill).

Check and install CLI tool dependencies required by SPI skills. Use when the user says "setup", "check dependencies", "what do I need installed", or when a skill fails with "command not found". This does NOT set up a specific project. It ensures the tools needed by SPI skills are present on the machine. Not for: project-specific setup, IDE configuration, or environment provisioning.

Cross-repository status aggregation for SPI service forks — issues, pull requests, workflow runs, and alerts across all fork repos in a single dashboard. Highlights cascade-blocked issues, human-required labels, failing workflows, and pending sync/template-sync PRs. Configurable org via SPI_ORG. Use when checking overall fork health, asking what's open across repos, looking for blocked cascades, pending reviews, needing a dashboard of all SPI fork activity, or monitoring the state of the engineering system. Trigger on "status", "dashboard", "what's open", "any blocked cascades", "pending PRs across forks", "fork health overview", "failing workflows", "issues across repos". Not for: triggering syncs or cascades (use forks skill), infrastructure health or cluster status (use health skill), deploying (use iac skill), tool installation (use setup skill).

Ship local changes through a review-commit-push workflow. Performs a lite code review, runs quality checks, commits with a conventional commit message, pushes to remote, and creates a merge request (GitLab) or pull request (GitHub). Auto-detects the remote platform and available tools (worktrunk, aipr). Use when the user wants to send, ship, submit, or push their work, create an MR or PR, or says "send it", "ship it", "push my changes", or "I'm done, send this up". Not for: reviewing someone else's MR (use mr-review), contributing to another developer's MR (use contribute), or setting up tools (use setup).

Load OSDU datasets (reference data, TNO, Volve, NOPIMS) into any OSDU instance. Use when the user asks to load test data, bootstrap an instance, populate reference data, check what data is loaded, list available datasets, or load specific datasets like TNO/Volve/NOPIMS. Also triggers on "what datasets are available", "is reference data loaded", "load all data", or "how do I get test data into my OSDU instance". Supports CIMPL (auto-detected via kubectl) and Azure ADME (via environment variables). Not for: querying existing records (use OSDU MCP tools), schema management (use schema MCP tools), or building/testing services (use maven or acceptance-test).

Check and install CLI tool dependencies required by these skills. Use when the user says "setup", "check dependencies", "what do I need installed", or when a skill fails with "command not found". This does NOT set up a specific project. It ensures the tools needed by skills are present on the machine. Not for: project-specific setup, IDE configuration, or environment provisioning.

Clone OSDU GitLab repositories and infrastructure repos to the workspace. Supports single service, category, or all repos with bare-clone worktree or standard git clone. Use when the user asks to clone an OSDU repo, set up the workspace, download source code for a service, or clone infrastructure repos. Not for: building or testing cloned repos (use maven or acceptance-test), or checking repo status (use glab or osdu-activity).

Comprehensive health assessment of deployed AZD environments — cluster infrastructure, workloads, and OSDU platform services. Use when the user asks about environment health, cluster status, or wants a report on their deployed environments. Trigger on phrases like "report on my environments", "environment health", "how is my cluster", "cluster status", "environment status", or "what's deployed". Not for: deploying or modifying infrastructure (use the iac skill), installing tools (use the setup skill), or application-level debugging.

Infrastructure as Code for Azure — Terraform modules, Azure Verified Modules (AVM), Helm/Kustomize deployments, AKS Deployment Safeguards, azd integration, and systematic debugging. Use when working with Terraform, AVM, azurerm, azapi, helm_release, kubernetes_manifest, AKS safeguards, deployment failures, policy violations, infrastructure verification, or any IaC architecture decisions. Also use for debugging infrastructure issues and verifying deployments are complete. Not for: application code, OSDU service APIs, CI/CD pipeline execution, or project-specific setup (use the setup skill for missing CLI tools).

Check and install CLI tool dependencies required by these skills. Use when the user says "setup", "check dependencies", "what do I need installed", or when a skill fails with "command not found". This does NOT set up a specific project. It ensures the tools needed by skills are present on the machine. Not for: project-specific setup, IDE configuration, or environment provisioning.

Run Java acceptance or integration tests from an OSDU service repository against a live deployed environment. Resolves environment configuration, auth credentials, and SSL truststore automatically. Use when the user says 'run acceptance tests for partition', 'test the storage service against my environment', 'execute integration tests for legal', or 'verify partition with acceptance tests'. Not for: test reliability analysis (use osdu-quality), building services (use build-runner), checking environment health (use health), or unit tests without a live service.

Use when reading from, writing to, or organizing the OSDU brain Obsidian vault — the project's long-term memory and knowledge base. Trigger this skill whenever the user mentions the vault, brain, daily notes, daily briefing, reports, knowledge base, decision records, incident reports, dependency reports, QA reports, meeting notes, architecture notes, or asks to "remember", "store", "log", or "write up" anything related to project operations. Also trigger when generating MR summaries, pipeline analysis, RCA write-ups, dependency audits, or any content destined for the brain vault. Use when the user says "vault", "brain", "daily note", "remember this", "store this", "log this", "write up", or references knowledge base operations. Not for: ad-hoc chat answers, one-time commands, or information already in git history.

Execute build/test commands and return structured summaries. Use for Maven, Node, or Python builds during dependency remediation. Use when the user says "build", "compile", "test", "verify", "run tests", "maven verify", "unit tests", or "build summary". Not for: deployment, CI/CD pipeline management, or code generation.

Scan the Obsidian vault for stale knowledge notes and contradictory decisions. Flags notes not verified in 90+ days, detects scope conflicts in decisions, and respects human-corrected notes that never decay. Use when the user says "consolidate", "clean up the vault", "check for stale notes", or during periodic vault hygiene. Not for: writing new notes or ingesting new knowledge (use brain or learn skills instead).

Push local changes into someone else's merge request by creating a sub-MR that targets their source branch. Handles fork creation, branch setup, commit, push, sub-MR creation, and drafts a comment on the parent MR. Use when the user wants to contribute to an existing MR, push changes into another developer's branch, or help fix something on someone else's MR. Not for: shipping your own work as a new MR (use send), or reviewing an MR without contributing code (use mr-review).

Analyze project dependencies for available updates, overlay CVE data, and create an actionable risk-scored remediation report. Supports Maven projects with Python and Node.js planned. Use when the user asks to scan dependencies, check for vulnerabilities, generate a dependency report, or says "what needs updating". Not for: applying dependency updates (use remediate), or general project build issues (use build-runner).

Fix FOSSA NOTICE file from failed MR pipeline. Downloads the updated NOTICE artifact from a GitLab CI fossa-check-notice job and commits it. Use when the user mentions FOSSA failure, NOTICE file update, fossa-check-notice job failure, or needs to fix a FOSSA pipeline error. Not for: license scanning setup, dependency vulnerability analysis (use maven scan), or general pipeline debugging (use glab).

Expert guidance for using the GitLab CLI (glab) to manage merge requests, issues, CI/CD pipelines, repositories, and API operations from the command line. Use when the user mentions GitLab, merge requests (MRs), glab commands, CI/CD pipelines on GitLab, GitLab issues, or needs to interact with a GitLab instance — even if they don't explicitly say 'glab'. Also trigger when the user is working in a repo with a GitLab remote and wants to create MRs, check pipeline status, review code, or manage issues. Not for: bulk cross-project OSDU queries (use osdu-activity), contributor analysis (use osdu-engagement), or test reliability metrics (use osdu-quality).

Use when Agent is asked to study, learn, or absorb knowledge from external sources (GitLab wikis, documentation pages, URLs, or pasted content) and produce curated knowledge notes in the vault. Use when the user says "learn about", "study", "absorb", "index", "pull in docs for", or wants to populate the vault with reference material from an external source. Not for: quick one-off lookups or answers that don't need to be persisted in the vault.

Maintainer actions for MR trusted branch sync. Check sync status between source and trusted branches, then push to the trusted branch so the child pipeline can run. Use when the user says 'allow MR', 'sync trusted branch', 'trigger trusted tests', or asks to review and approve an MR for pipeline execution. Not for: code review or pipeline analysis (use mr-review), creating or merging MRs (use glab), or test reliability (use osdu-quality).

Maven dependency version checking and security vulnerability scanning. Check Maven artifact versions, find updates, scan for CVEs with Trivy, and analyze POM files. Use when the user asks about Maven dependency versions, needs to check for updates, wants to scan for vulnerabilities in a Java project, or needs POM file analysis. Not for: building or running Java tests (use build-runner or acceptance-test), or general Java project setup.

Review a GitLab merge request with code analysis and pipeline diagnostics. Fetches the diff, analyzes changes by risk area, checks pipeline status, classifies job failures, and produces a structured verdict. Use when the user says "review MR", "look at this MR", "is this safe to merge", "check the pipeline for MR X", or pastes a GitLab MR URL without other instruction. Not for: shipping your own changes (use send), contributing to someone else's MR (use contribute), or syncing trusted branches (use maintainer).

OSDU platform monitoring across 30+ GitLab services using the `osdu-activity` CLI — the only way to query OSDU MRs, pipelines, and issues in bulk. Use when the user asks about open MRs across OSDU services, OSDU pipeline failures, OSDU CI status, failed jobs by cloud provider, milestone progress (M25/M26), or issue tracking across the platform. Not for: glab CLI syntax help, actions on a single non-OSDU repo (creating/merging MRs in cimpl-azure-provisioning), contributor rankings (use osdu-engagement), or test flakiness (use osdu-quality).

Engineering contribution analysis for OSDU platform projects. Measures code contributions, reviews, and ADR engagement across teams. Use when analyzing contributors, commit activity, reviewer patterns, team engagement, ADR participation, or contribution trends. Not for: test reliability (use osdu-quality), pipeline status (use osdu-activity), or single-repo glab operations.

OSDU QA Testing - Environment management, API test execution, failure analysis, and report generation. Use when running OSDU API tests, analyzing failures, comparing environments, generating QA reports, or managing test environments. Not for: unit testing application code or build compilation (use build-runner instead).

CI/CD test reliability analysis for OSDU platform projects. Detects flaky tests, calculates pass rates, provides cloud provider metrics, and analyzes acceptance test parity. Use when analyzing test health, pass rates, flaky tests, test reliability, CI quality, pipeline test results, test coverage gaps, or acceptance test parity. Not for: open MRs or pipeline status (use osdu-activity), contributor rankings (use osdu-engagement), running acceptance tests locally (use acceptance-test), or single-repo glab operations.

Execute dependency remediation from an analysis report with validation, risk-tiered commits, and code fixes. Applies updates incrementally with build verification after each change. Use when the user has a dependency analysis report and wants to apply the recommended updates, or says "remediate", "fix dependencies", "apply updates". Not for: scanning dependencies (use dependency-scan), or general code fixes unrelated to dependency versions.