Write a high-context PR description for any substantial PR. Use whenever creating or editing a pull request body — the description must let a reader with zero prior context understand what is being built, why, where it sits in the larger system, and exactly what changed, without digging through tickets or code.
Cut a versioned release — stamp the changelog, snapshot the roadmap, tag, create the platform release, publish, and sync. Use when asked to "cut a release", "ship vX.Y.Z", "tag a version", or when an unreleased changelog section is ready to go out.
Generate a status report. Use when asked for a status report, a standup summary, "what changed this week", or "what did we ship". Writes docs/status/ - .md, commits, and publishes — never paste an unrecorded status into chat.
Push work items to the team's configured ticketing system (GitHub Issues, Jira, Azure DevOps, GitLab, Linear...). Use when asked to sync tickets, after closing out a plan, or when items should be visible in the tracker. Push and pull.
Publish docs (roadmap, plans, user guide, status) to the team's configured wiki. Use when asked to publish/sync docs to the wiki, after cutting a roadmap snapshot, or when a plan/status report should be visible outside the repo.
Track work items — use when creating, updating, closing, or listing work items, or when discovering unplanned work mid-flight ("we also need to…", a bug found while doing something else).
Instructions for SpillwaveSolutions/wiki_ticket_sdd, a project described as: Local-first, git-native visible-WIP work tracking (worklog) + Claude Code plugin.
Local-first, git-native visible-WIP work tracking: plans become tickets, roadmaps stay generated, unplanned work gets recorded. Skills, /worklog: commands, and an ExitPlanMode capture hook.
Scaffold or upgrade the current repo as a worklog repo (bin/, git hooks, .work/, CI workflow, CLAUDE.md policy block), then detect and configure the repo's ticketing/wiki systems.
Regenerate the roadmap with ALL Mermaid diagrams (dependency graph, hierarchy, event-dated gantt) and republish it — runs in a background subagent, never blocks the main session.
This skill should be used when configuring or using the OpenCode CLI for headless LLM automation. Use when the user asks to "configure opencode", "use opencode cli", "set up opencode", "opencode run command", "opencode model selection", "opencode providers", "opencode vertex ai", "opencode mcp servers", "opencode…
Claude Code instructions for SpillwaveSolutions/notion_uploader_downloader, covering claude.md, project overview, essential commands, installation and configuration.
Bidirectional sync between Markdown and Notion. Upload .md files with images to Notion pages/databases, append to existing pages, or download Notion content back to markdown. Supports rich formatting, tables, code blocks, GitHub-flavored markdown, and recursive page hierarchy downloads with YAML frontmatter for…
Claude Code instructions for SpillwaveSolutions/cca-exam-prep-multi-agent-researcher, covering claude.md, what this project is, build and run commands, architecture and two-layer design: notebooks + package.
Build headless automation and agentic workflows with Google's Gemini CLI. Covers approval modes (default, autoedit, yolo), file permission model, Edit vs WriteFile tool selection, smartEdit configuration, GEMINI.md context files, settings.json hierarchy, and MCP server integration. Use when building CI/CD pipelines…