Marco Ferreira
Community@mpmf
Marco Ferreira (mpmf) publishes 14 software engineering discipline skills covering test-driven development, systematic debugging, git worktrees, code review, and plan execution.
Agent Skills by Marco Ferreira
Showing 14 vetted skills indexed across 1 GitHub repositories.
using-git-worktrees
Creates isolated git worktree workspaces with baseline test verification before feature implementation.
test-driven-development
Enforces red-green-refactor test-driven development workflow before writing production code.
systematic-debugging
Diagnose bugs through a four-phase root cause investigation process before proposing fixes.
using-superpowers
Enforces skill discovery and invocation before any AI response or action.
dispatching-parallel-agents
Dispatch concurrent agents to investigate independent failures across separate problem domains.
executing-plans
Executes written implementation plans task-by-task with verification checkpoints and review gates.
finishing-a-development-branch
Guides completion of development branches through structured merge, pull request, or cleanup options.
brainstorming
Guides collaborative design exploration and produces approved spec documents before implementation.
writing-plans
Generates detailed multi-task implementation plans with TDD steps from feature specifications.
requesting-code-review
Dispatch a code reviewer subagent to evaluate git changes against requirements before merging.
receiving-code-review
Guides verification and implementation of code review feedback with technical rigor.
writing-skills
Create and test agent skills using test-driven development with subagent pressure scenarios.
verification-before-completion
Enforces running verification commands before claiming work is complete or passing.
subagent-driven-development
Executes implementation plans by dispatching fresh subagents per task with two-stage review.
Frequently Asked Questions About Marco Ferreira
FAQPage SchemaWhat tasks can I accomplish with mpmf's skills?▼
The 14 skills cover the full development cycle: brainstorming requirements, writing implementation plans, test-driven development, systematic debugging, git worktree isolation, dispatching parallel tasks, requesting and receiving code review, verifying completion with evidence, and finishing branches via merge, PR, or cleanup.
Who should use these development discipline skills?▼
Software engineers and developers who want structured, repeatable practices for feature implementation, bug fixing, and code review. They suit anyone enforcing test-first development, evidence-based completion claims, and rigorous review verification rather than blind acceptance of feedback.
How do the skills fit into a daily coding session?▼
Skills are invoked at specific trigger points: brainstorming before creative work, writing-plans before touching code, test-driven-development before implementation, systematic-debugging when bugs appear, and verification-before-completion before committing or opening pull requests.
What prerequisites or dependencies do these skills require?▼
The manifest specifies no external dependencies. Skills rely on standard development artifacts: a written spec or requirements for planning, an implementation plan for execution sessions, and git with worktree support for workspace isolation, plus test suites for verification steps.
How do the skills handle parallel or multi-step work?▼
dispatching-parallel-agents handles two or more independent tasks without shared state, subagent-driven-development executes independent plan tasks in the current session, and executing-plans runs written implementation plans in a separate session with review checkpoints.