Menu
SkillsMP a collecté 61 skills depuis agustinusnathaniel/maestria. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 61.
Universal agent rules contract: universal floors, orchestration, delegation, context management, handoff, blind review, bounded autonomy, authorization checkpoints, process lifecycle, iteration, and commit and branch safety. Load once per session and apply to…
Langue du texte source : anglais
Universal Maestria rules for evidence, safety, authorization, delegation, review, bounded repair, and branch discipline.
Langue du texte source : anglais
Cross-cutting methodology rules for all specialists
Langue du texte source : anglais
Global behavioral constraints and best practices for maestria-powered Oh My Pi agents. Covers orchestration conventions, delegation rules, context management, commit policy, pipeline patterns, and branch discipline.
Langue du texte source : anglais
Global behavioral constraints and best practices for maestria-powered Pi agents. Covers orchestration conventions, delegation rules, context management, commit policy, pipeline patterns, and branch discipline.
Langue du texte source : anglais
Universal agent rules contract: universal floors, orchestration, delegation, context management, handoff, blind review, bounded autonomy, authorization checkpoints, process lifecycle, and commit and branch safety. Load once per session and apply to routing,…
Langue du texte source : anglais
Maestria methodology dispatcher for Claude Code. Routes work (direct/focused/full), delegates to specialist agents (maestria:adventurer, maestria:architect, maestria:builder, maestria:diagnose, maestria:planner, maestria:reviewer, maestria:writer), and…
Langue du texte source : anglais
Codebase reconnaissance workflow for mapping unfamiliar code, tracing call chains, and reporting verified context without implementing changes.
Langue du texte source : anglais
Architecture decision workflow for comparing implementation approaches, boundaries, threat models, and ADR decisions.
Langue du texte source : anglais
Focused implementation workflow for one atomic, verifiable feature, fix, test, or refactor.
Langue du texte source : anglais
Systematic regression-tracing workflow from symptom and error evidence to root cause, fix, and prevention.
Langue du texte source : anglais
Maestria workflow dispatcher for Codex CLI: route work, use specialist skills, preserve handoffs, and keep independent review explicit.
Langue du texte source : anglais
Phased implementation planning workflow with dependencies, verification criteria, timelines, and rollback points.
Langue du texte source : anglais
Independent code review workflow covering correctness, security, performance, maintainability, and quality gates.
Langue du texte source : anglais
Structured documentation workflow for READMEs, API docs, architecture documents, changelogs, and decision records.
Langue du texte source : anglais
Maestria dispatcher for Cursor. Delegates to specialist agents (adventurer, architect, builder, diagnose, planner, reviewer, writer) via Task. Enforces maker/checker split, handoff contracts, and workflow modes (fein/sonar/blitz). Use for multi-step or…
Langue du texte source : anglais
Research and exploration -- gathers information from any source
Langue du texte source : anglais
Architecture and design -- evaluates options, makes decisions, designs solutions across any domain
Langue du texte source : anglais
Focused production -- implements, creates, and produces output
Langue du texte source : anglais
Root cause analysis -- investigates problems and finds causes
Langue du texte source : anglais
Methodology orchestrator -- runs single-thread by default, delegates to specialists for complex tasks
Langue du texte source : anglais
Planning -- breaks down work into ordered, verifiable steps
Langue du texte source : anglais
Quality gates -- validates output, checks for issues, ensures correctness
Langue du texte source : anglais
Content creation -- produces clear, structured documentation and prose
Langue du texte source : anglais
Codebase reconnaissance agent for deep code understanding. Maps unknown territory - traces call chains, maps module relationships, generates structured reports for downstream specialists. Use for: understanding unfamiliar code, tracing dependencies, gathering…
Langue du texte source : anglais
Architecture decisions using decision matrices and ADRs. Evaluates options with weighted criteria, clarifies business context first. Use for: technology choices, implementation approaches, trade-off analysis.
Langue du texte source : anglais
Focused implementation agent for atomic tasks. Executes one verifiable unit of work with minimal context. Use for: targeted fixes, feature implementation, refactors, adding tests.
Langue du texte source : anglais
Systematic 6-step regression tracing. From error message to root cause to prevention. Use for: cryptic errors, regressions, production bugs.
Langue du texte source : anglais
Methodology + delegation + swarm usage for the maestria workflow
Langue du texte source : anglais
Create detailed implementation plans with phased dependencies, timelines, and success criteria. Breaks down complex features into verifiable milestones. Use for: complex features requiring multi-phase execution, when the plan needs review before building.
Langue du texte source : anglais
Code review with quality gates. Reviews code for correctness, edge cases, security, performance, maintainability, and adherence to conventions. Provides specific, actionable feedback. Use for: PR review, pre-commit review, architecture document review.
Langue du texte source : anglais
Documentation writing following structured patterns. Creates clear, comprehensive docs for code, APIs, systems. Use for: README files, API docs, architecture docs, changelogs, decision records.
Langue du texte source : anglais
Maestria agent orchestration dispatcher. Delegates work to 7 specialist subagents (adventurer, architect, builder, diagnose, planner, reviewer, writer) using spec-driven handoffs. Enforces maker/checker split, commit protocol, and role-based pipeline…
Langue du texte source : anglais
Maestria agent orchestration dispatcher. Delegates work to 7 specialist subagents (adventurer, architect, builder, diagnose, planner, reviewer, writer) using spec-driven handoffs. Enforces maker/checker split, commit protocol, and role-based pipeline…
Langue du texte source : anglais
Codebase reconnaissance skill. Maps unknown territory - traces call chains, maps module relationships, generates structured recon reports for downstream work. Read-only role intent: exploration and reporting only, never implementation or design. Use for:…
Langue du texte source : anglais
Architecture decisions using decision matrices and ADRs. Evaluates options with weighted criteria, clarifies business context first. Use for: technology choices, implementation approaches, trade-off analysis, threat modeling, or ADR decisions.
Langue du texte source : anglais
Focused implementation skill for atomic tasks. Executes one verifiable unit of work with minimal context and a clean diff. Use for: targeted fixes, feature implementation, refactors, adding tests.
Langue du texte source : anglais
Systematic 6-step regression tracing: from error message to root cause to prevention. Use for: cryptic errors, regressions, production bugs, unclear root causes.
Langue du texte source : anglais
Maestria methodology dispatcher for Prime Agent. Routes work (direct/focused/full), selects and loads the specialist skills (adventurer, architect, builder, diagnose, planner, reviewer, writer), and applies the maker/checker split, handoff contracts, and…
Langue du texte source : anglais
Create detailed implementation plans with phased dependencies, timelines, verifiable success criteria, and rollback points. Breaks complex features into verifiable milestones. Use for: complex features requiring multi-phase execution, when the plan needs…
Langue du texte source : anglais