David McInnis
Community@mcinnisd
David McInnis publishes user-invoked software engineering skills covering test-driven development, systematic debugging, code review, git worktrees, and codebase auditing.
Agent Skills by David McInnis
Showing 16 vetted skills indexed across 1 GitHub repositories.
mcinnisdusing-git-worktrees
Creates isolated git worktree workspaces with detection, setup, and baseline test verification.
mcinnisddeep-test
Prunes redundant tests and detects critical coverage gaps through multi-phase test suite auditing.
mcinnisddeep-audit
Audits codebases for architectural alignment, deduplication, and widget contract integrity with human review.
mcinnisdtest-driven-development
Enforces red-green-refactor test-driven development workflow for writing code with failing tests first.
mcinnisdsystematic-debugging
Diagnose software bugs through a four-phase root cause investigation process.
mcinnisdusing-superpowers
Guides discretionary invocation of superpowers skills across AI coding harnesses.
mcinnisddispatching-parallel-agents
Dispatch concurrent subagents to investigate independent test failures across separate problem domains.
mcinnisdexecuting-plans
Executes implementation plans task by task with verification and blocker escalation.
mcinnisdfinishing-a-development-branch
Guides merging, pushing, or preserving a completed development branch after verifying tests.
mcinnisdbrainstorming
Guides collaborative dialogue to turn ideas into approved design specs.
mcinnisdwriting-plans
Writes detailed implementation plans with bite-sized TDD tasks and exact file paths.
mcinnisdrequesting-code-review
Dispatch a code reviewer subagent to evaluate git diffs against requirements.
mcinnisdreceiving-code-review
Guides AI agents to verify, evaluate, and implement code review feedback with technical reasoning.
mcinnisdwriting-skills
Create and test agent skills using test-driven development with pressure scenarios.
mcinnisdverification-before-completion
Enforces running verification commands before claiming task completion or success.
mcinnisdsubagent-driven-development
Executes implementation plans by dispatching fresh subagents per task with per-task and final code reviews.
Frequently Asked Questions About David McInnis
FAQPage SchemaWhat tasks can I perform using David McInnis's skills?▼
You can practice test-driven development, debug systematically, brainstorm ideas into specs, write and execute implementation plans, dispatch parallel subagents, request and receive code reviews, audit codebases for duplication and architectural drift, prune bloated test suites, and verify work before completion.
Who are these skills designed for?▼
Software engineers and development teams who follow disciplined engineering practices. The skills target practitioners doing test-driven development, structured debugging, code review cycles, branch management with git worktrees, and large-scale codebase audits requiring architectural alignment and issue tracking.
How are these skills invoked at runtime?▼
Every skill in the manifest is user-invoked, with disable-model-invocation set to true in the native frontmatter. This means they never trigger automatically; the developer explicitly calls each skill, such as deep-test, deep-audit, or systematic-debugging, when needed during a session.
What is the deep-test skill and how does it differ from deep-audit?▼
Deep-test performs a dual mandate: deleting redundant or tautological tests while finding critical coverage gaps to fix or ticket, then executing tests dynamically and creating issues. Deep-audit instead reviews the whole codebase for architectural alignment, deduplication, and widget/schema integrity.
What prerequisites or dependencies do these skills require?▼
The manifest specifies no external dependencies, runtimes, or paid services. Skills rely on a standard git-based development environment for worktrees and branch finishing, plus issue tracking integration referenced as Wayfinder/GitHub issues for the deep-audit and deep-test capabilities.