Mike M
Community@SevWren · USA
Mindset: Improving yourself one day at a time -> made possible by utilizing today's technologies to fit your individual needs.
Agent Skills by Mike M
Showing 86 vetted skills indexed across 1 GitHub repositories.
SevWrenrepo-doc-audit
Audits repository documentation for contradictions, drift, and governance gaps across 18 sections.
SevWrensetup-pre-commit
Configures Husky pre-commit hooks with lint-staged, Prettier, typecheck, and tests.
SevWrenclaude-md-improver
Audit and prune CLAUDE.md files to stay under the 200-line limit.
SevWrenofficial-docs
Look up official Anthropic and Claude Code documentation via web search and fetch.
SevWrengit-guardrails-claude-code
Blocks dangerous git commands in Claude Code using a PreToolUse hook script.
SevWrenscaffold-exercises
Creates exercise directory structures with sections, variants, and readme stubs that pass linting.
SevWrenmigrate-to-shoehorn
Migrate TypeScript test files from `as` assertions to @total-typescript/shoehorn partial mocks.
SevWrenresearch
Investigate questions against primary sources and write cited findings to Markdown files.
SevWrendomain-modeling
Build and maintain project domain glossaries and architectural decision records.
SevWrenwayfinder
Plans large multi-session efforts as issue-tracker maps of investigation tickets resolved one at a time.
SevWrensetup-matt-pocock-skills
Configure a repository's issue tracker, triage labels, and domain doc layout for engineering skills.
SevWrendiagnosing-bugs
Diagnose hard bugs and performance regressions through a structured six-phase feedback-loop workflow.
SevWrencode-review
Reviews git diffs against coding standards and originating specs using parallel sub-agents.
SevWrento-tickets
Break plans and specs into tracer-bullet tickets with declared blocking edges.
SevWrenask-matt
Routes engineering situations to the appropriate skill or workflow in the repository.
SevWrenimprove-codebase-architecture
Scan a codebase for shallow modules and present deepening refactors as a visual HTML report.
SevWrento-spec
Synthesizes conversation context into a spec and publishes it to the project issue tracker.
SevWrencodebase-design
Designs deep modules with small interfaces, clean seams, and testable adapters.
SevWrentriage
Move GitHub issues and external PRs through a triage state machine with agent-ready briefs.
SevWrenprototype
Build throwaway interactive prototypes to validate logic models or explore UI design variants.
SevWrenzoom-out
Generates a high-level map of relevant modules and callers for unfamiliar code areas.
SevWrengrill-with-docs
Runs a structured interview to refine plans while generating ADRs and a glossary.
SevWrenimplement
Implement work from a spec or tickets using TDD, typechecking, and code review.
SevWrentdd
Guides test-driven development using the red-green loop with seam-based testing.
Frequently Asked Questions About Mike M
FAQPage SchemaWhat tasks can I accomplish using SevWren's skills?▼
You can audit repository documentation for contradictions and drift, improve CLAUDE.md and AGENTS.md files, run TDD and bug-diagnosis loops, perform multi-lens code reviews, create PRDs and architecture specs, plan sprints, scaffold exercises, and migrate TypeScript tests to @total-typescript/shoehorn.
Who are these skills designed for?▼
Software engineers, technical leads, and product-minded developers using Claude Code who want structured engineering practices: spec-driven development, domain modeling, adversarial review, sprint planning, and documentation governance. BMad agent personas also serve PM, analyst, architect, and UX roles.
How do I install and run these skills?▼
Skills are invoked inside Claude Code by name or trigger phrase; many are user-invocable only (disable-model-invocation). Run setup-matt-pocock-skills once to configure the issue tracker, triage labels, and domain doc layout before using the related engineering skills.
Are SevWren's skills free and open source?▼
The skills are published as public repositories on GitHub under the SevWren account with no listed commercial licensing or cost. Users can clone the skill folders into their Claude Code configuration and customize BMad behavior via the bmad-customize override skill.
What prerequisites or dependencies do these skills require?▼
A Claude Code environment is required, since skills rely on its hooks, sub-agents, and frontmatter system. Specific skills need extras: setup-pre-commit requires a Node.js repo for Husky and lint-staged, and migrate-to-shoehorn requires TypeScript tests using @total-typescript/shoehorn.