Menu
O SkillsMP coletou 18 skills de mnzralee/claude-multi-agent-architecture. Abra uma skill para revisar a origem e os detalhes.
Mostrando 18 de 18 skills coletadas.
Run the multi-wave Software Engineering Review Board (SERB) over a proposed plan before execution. A read-only board of specialist agents gathers ground truth, critiques from architecture/testing/security/devops/quality lenses, then synthesizes a refined,…
Idioma do texto original: inglês
Design RESTful APIs with consistent conventions for resource URLs, response shapes, HTTP semantics, versioning, and security across every service in the project.
Idioma do texto original: inglês
Backend development skill for microservices following Clean Architecture, CQRS with a transactional outbox, the repository/use-case pattern, and a Testing-Trophy strategy.
Idioma do texto original: inglês
Switch Claude to telegraphic compressed-prose mode to reduce token usage in long sessions. Drops filler, articles where unambiguous, courtesy words, and meta-commentary. Preserves code, paths, identifiers, negations, numbers exactly. Use when context window…
Idioma do texto original: inglês
Git Commit Skill for creating well-structured, atomic commits following conventional-commits discipline
Idioma do texto original: inglês
A generator-plus-critic loop that improves output against an explicit rubric before acceptance. Use when you have clear acceptance criteria and iteration measurably helps (specs, prompts, important docs, tricky implementations). Includes a seed eval set for…
Idioma do texto original: inglês
Drive Playwright against a running application step-by-step, screenshot, analyze, decide, act. Applies to any web frontend regardless of stack.
Idioma do texto original: inglês
Plan a new module or feature area end-to-end using a structured Explore, Plan, and Document workflow before any code is written
Idioma do texto original: inglês
Coordinate complex development tasks using hierarchical agent teams with supervisors, prompt writers, debuggers, and work recorders. Encodes the TDD-with-agents protocol, premature-completion red flags, and cross-agent file-race avoidance.
Idioma do texto original: inglês
The Explore to Plan to Code to Commit workflow for any non-trivial change. Forces understanding and an explicit plan before edits, with a one-sentence skip heuristic for trivial work. Use when starting a feature, a refactor, or any change whose steps are not…
Idioma do texto original: inglês
Pull Request skill for creating well-structured, consistently formatted PRs using the GitHub CLI
Idioma do texto original: inglês
Endless-iteration discipline for long-arc goals. Bounded iterations with /clear between, persistent state, a 9-agent review-board escalation when stuck, brownfield-first audits, show-your-work artifact requirement, two-failure-clear trigger,…
Idioma do texto original: inglês
Code review skill covering security, correctness, type safety, and maintainability for any software project
Idioma do texto original: inglês
Methodical problem-solving approach for diagnosing and resolving code issues in any stack before attempting a fix
Idioma do texto original: inglês
Test-Driven Development workflow for implementing features with tests first; enforces the two-commit audit trail (failing-test commit, then green commit) and shows-your-work verification for agent-driven work.
Idioma do texto original: inglês
Comprehensive five-level validation checklist that every agent must pass before declaring any task or work package complete.
Idioma do texto original: inglês
Structured multi-phase verification of implementations before deployment, covering static analysis, testing, functional checks, security, and documentation
Idioma do texto original: inglês
Transform development sessions into compelling engineering stories that capture not just what happened, but why it mattered and what was learned. Covers journal discipline, session templates (planning, bug hunt, feature build, multi-agent orchestration), and…
Idioma do texto original: inglês