Agent Skills by robertphyatt
Showing 14 vetted skills indexed across 1 GitHub repositories.
activate-professional-mode
Enforce human-approved workflow gates in Claude Code sessions.
elements-of-style
Rewrite technical writing using Strunk & White principles for concise active language.
testing-theatre-detection
Detect missing assertions, excessive mocking, and swallowed errors in JavaScript and Python test suites.
systematic-debugging
Investigate root causes of bugs before applying fixes.
plan-interruption
Detect plan interruptions, confirm user choice, and preserve plan state for resume.
code-review
Validate code changes against plans and generate review reports.
executing-plans
Execute implementation plans wave-by-wave using MCP state management.
adversarial-review
Automate five-phase adversarial code reviews with mandatory verification and findings reports.
setup-ollama-validation
Configure Ollama as the validation backend for professional mode hooks.
brainstorming
Guide structured ideation to produce a design brief.
writing-plans
Convert design documents into step-by-step implementation plans with file paths.
remembering-conversations
Dispatch a search agent to retrieve and synthesize past discussions with sources.
writing-skills
Draft and validate IronClaude skills using the RED-GREEN-REFACTOR workflow.
deactivate-professional-mode
Disable professional mode to permit direct code changes in Claude Code.