Agent skills for Microsoft Copilot

Automates the end-to-end release lifecycle including versioning, changelogs, GitHub releases, and multi-platform mirror synchronization.

Automates the entire software release lifecycle including SemVer versioning, CHANGELOG generation, GitHub Releases, and cross-platform…

Conducts automated multi-angle reviews of code, development plans, and project scope to ensure high-quality software delivery.

Initializes and configures the Claude Code Harness environment for high-quality autonomous development workflows.

Displays Harness UI dashboard for monitoring and task management.

Automates software development tasks through an autonomous Plan-Work-Review cycle with multi-backend support.

Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check…

Adaptive content summarization - auto-detect content type and produce relevant summary

Automate time tracking, project management, and invoicing workflows in Harvest -- log hours, manage projects, clients, and tasks through…

Competitive intelligence - extract features, pricing, tech stack from competitor sites

Multi-page deep crawling - documentation sites, wikis, knowledge bases

Web change monitoring - track changes on pages, detect updates, changelog diffs

Single page smart extraction - articles, docs, blog posts to clean markdown

Structured data extraction - tables, pricing, products, API endpoints with schema

Design UI/UX systems with style guides, palettes, typography, and component specs for new interfaces

Operate explicit orchestrator, implementer Triggers: "agent-native factory", "role-shaped agent panes", "persistent workers".

Audit local AI coding-agent sessions with agenttrace.

Optimize content for AI Overviews (formerly SGE), ChatGPT web search, Perplexity, and other AI-powered search experiences.

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories…

Capture architectural decisions made during Claude Code sessions as structured ADRs.

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then…