danielscholl

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).

Runtime orchestration of agent teams for parallel work. Use when the user says "create a team", "/orchestrate", or wants multiple Claude instances working together. Supports patterns: review (parallel code review), debate (competing hypotheses), plan (explore + plan + critique), build (parallel implementation), research (parallel investigation), cross-agent (multi-engine comparison via CLI bridges like Codex), and custom teams. This skill handles live team coordination at runtime — distinct from cadre:init which bootstraps static team definitions and agent configurations for a project. TRIGGERS - Use this skill when user says: - "/orchestrate review src/" or "review this code with a team" - "/orchestrate debate 'why does X fail'" or "investigate this bug with competing theories" - "/orchestrate plan 'add authentication'" or "plan this feature with a team" - "/orchestrate build 'calculator module'" or "build this with a team" - "/orchestrate research 'compare React vs Vue'" or "research this topic in paralle

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.

Generate tone-of-voice and brand-system files for use with the PPTX Generator and other brand-aware skills. TRIGGERS - Use this skill when user says: - "help me create a brand system" / "set up my brand" - "generate my tone of voice" / "create my voice guidelines" - "configure my brand for presentations" / "set up brand for slides" - "create brand files" / "initialize my brand" - Any request about defining brand identity, voice, or visual system for content creation Creates brand.json, config.json, brand-system.md, and tone-of-voice.md files.

Generate and edit presentation slides as PPTX files. Also create LinkedIn carousels and manage reusable slide layouts. TRIGGERS - Use this skill when user says: - "create slides for [brand]" / "generate presentation for [brand]" / "make slides for [brand]" - "create a carousel for [brand]" / "linkedin carousel" / "make a carousel about [topic]" - "edit this pptx" / "update the slides" / "modify this presentation" - "create a new layout" / "add a layout to the cookbook" / "make a [type] layout template" - "edit the [name] layout" / "update the cookbook" / "improve the [name] template" - "use the [workflow] workflow" / "qa-report workflow" / "rca-report workflow" - Any request mentioning slides, presentations, carousels, PPTX, or layouts with a brand name Creates .pptx files compatible with PowerPoint, Google Slides, and Keynote. Creates PDF carousels for LinkedIn (square 1:1 format).

Create and maintain GitHub Copilot CLI plugins — skills, agents, prompts, instructions, AGENTS.md, and MCP servers. Use when building a new Copilot plugin, adding skills or agents to an existing plugin, writing AGENTS.md routing, creating prompt files, configuring MCP servers, adding hooks, validating plugin structure, or asking how Copilot CLI plugins work. This is for Copilot CLI plugins — NOT Claude Code projects.

Four-layer test framework for Claude Code plugin skills. Use when validating plugin structure, testing trigger accuracy of skill descriptions, running multi-turn session scenarios, or comparing skill value (with vs without). Also use when creating new trigger evals, session scenarios, or debugging why a skill fires for the wrong prompts. NOT for writing unit tests, running pytest, or testing application code — this is for testing AI plugin skills only.

Initialize a multi-agent development team for any project. Use this skill whenever the user wants to set up, bootstrap, create, or design specialized agents for their codebase — including requests to "set up agents", "create a team", "organize work into agents", "bootstrap cadre", or "generate agent configuration". Also triggers for requests to scope agents to project directories (monorepo packages, microservices, frontend/backend splits). Handles both existing projects (analyzes codebase structure) and greenfield projects (interviews user first). Generates .claude/agents/*.md files, config.yaml, routing rules, and a local /cadre coordinator skill.

Deploy a validated build per SECTION C of a planning document. Reasoning-light most of the time but needs judgment when the dry-run output looks off - a strong reasoning model is the safe choice (switch with /model). Skill is generic - it does whatever SECTION C says (Vercel, Fly, Railway, clerk deploy, local-only). Refuses to deploy unless validation is confirmed clean.

Design and scaffold a beautiful frontend from SECTION A of a planning document. Best handled by a model strong at UI generation (switch with /model; Gemini-class models excel here). The skill only builds the UI surface - auth, API calls, and SDK integrations belong to the next step. Use when the user has a plan.md from the frontend-mix-plan skill and is ready to build the UI.

Gather context for a mixed-provider full-stack build before planning. This is cheap context gathering, not reasoning-heavy work, so a fast/low-cost model is plenty (switch with /model). It inspects the repo, reads the spec if you point it at one, and writes a context.md handoff the plan step feeds off. Use this FIRST, before frontend-mix-plan. Triggers on "explore a frontend", "gather context for a mixed-provider build", "frontend-mix explore", or when given a spec markdown to scope before planning.

Address validation failures recorded by the frontend-mix-validate step. Failures that survived two repair attempts need real judgment - switch to a strong reasoning model with /model. Reads validation-issues.md, fixes each failure at the source, re-runs the validation suite, writes resolution-summary.md. Use when frontend-mix-validate wrote validation-issues.md instead of validation-summary.md.

Wire up auth, backend API, and third-party SDK integrations into a UI scaffold by executing SECTION B of a planning document. Integration is reasoning-heavy - switch to a strong reasoning model with /model. The skill is plan-driven, not vendor-specific - it uses whatever auth/SDKs/APIs SECTION B says. Use when the design step has finished and ui-summary.md plus plan.md are ready.

Plan a full-stack web application by producing a three-section spec (UI / Integration / Deployment) that downstream provider-specific steps can execute. Reasoning-heavy - switch to a strong reasoning model with /model. Run AFTER frontend-mix-explore has produced a context.md. Pure planning - it reads the context handoff (and the spec it points to) and turns it into an actionable plan. Triggers on "plan a frontend", "plan the app for mixed-provider build", "frontend-mix plan", or when given a context.md to turn into a plan.

Runtime smoke-test a freshly validated mixed-provider build by driving the RUNNING app - load every route, exercise the primary interaction, check status codes and console errors. Grind work, so a fast/low-cost model is fine (switch with /model). Catches the class of bug static checks (typecheck/lint/build) miss - broken routes, dead buttons, soft-404s, runtime errors, and the page that loads 200 but renders unstyled. Use after frontend-mix-validate (or fix-validation) confirms the build is clean, and before frontend-mix-deploy.

Run the full validation suite (install, type-check, lint, build, tests) on a freshly integrated app and fix anything broken. Validation is grind work - a fast/low-cost model is the right tool (switch with /model). Two-attempt cap per step; failures are recorded for the fix-validation escalation step, not papered over. Use after the frontend-mix-integrate step finishes.

Provision users and service principals for OSDU/ADME preshipping environments. Use when setting up preshipping access, enabling preshipping for users or OIDs, bulk-provisioning for preshipping testing, or configuring pre-production OSDU environments.

Queries Azure Data Manager for Energy (ADME) users and entitlements via OSDU API. Use when listing ADME users, checking roles (Viewer, Editor, Admin, Ops), resolving GUIDs to names, or troubleshooting ADME access.

Queries Azure AD/Entra ID users and groups using Azure CLI. Use when listing users, searching groups, checking memberships, or troubleshooting Azure AD operations.

Expert guidance for using the GitHub CLI (gh) to manage GitHub issues, pull requests, Actions workflows, repositories, and other GitHub operations from the command line. Use this skill when the user needs to interact with GitHub resources or perform GitHub workflows.

Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.

Search the web using Brave Search API and fetch page content with HTML-to-markdown conversion. Use when user needs current information, online documentation, or specific URL content beyond knowledge cutoff.

GitLab CI/CD test job reliability analysis for OSDU projects. Tracks test job (unit/integration/acceptance) pass/fail status across pipeline runs. Use for test job status, flaky test job detection, test reliability/quality metrics, cloud provider analytics. Wraps osdu-quality CLI.

Multi-language greetings in 6 languages. Use for non-English greetings or multiple people.