nextstage-brasil

@nextstage-brasil source repo

26 skills
0 followers
6 hours ago last updated

▌
Ns Coder · nextstage-brasil bundle
(NS) Ad-hoc coding — bug fixes, refactors, scripts, migrations — without full SDD. Entry priority 5: "just implement this", "quick fix", or coding without execution-handoff (C2 under ns-autonomous). Do NOT: ISSUE_URL (ns-execution-gitlab-issue), multi-day/version (ns-spec-driven), diagnosis-only (ns-investigator), when execution-handoff.md exists. Do NOT generate requirements/tasks/handoff.

0
installs
▌
Ns Harness · nextstage-brasil bundle
(NS) Harness boot + brownfield prepare. Triggers: /ns-harness, prepare this repo, harness prepare, generate architecture rules, architecture-rules.md, write AGENTS.md, reverse-engineer codebase, engenharia reversa, brownfield map, bootstrap brownfield, ns-harness-prepare, ns-architecture-rules, ns-agent-generator, ns-codebase-reverse-spec, ns-bootstrap-brownfield. Do NOT: coding, SDD, GitLab.

0
installs
▌
Ns Graphrag · nextstage-brasil bundle
(NS) GraphRAG process. Use for GraphRAG, knowledge graph over documents, multi-hop retrieval, entity/relationship extractors, indirect-link analytics, or grounded structured extraction — even if they only say RAG, NER, knowledge graph, or cited Q&A. Do NOT use for Postgres schema/mode alone (`ns-postgres-rag` first). Do NOT use for competing vector stores, free graph QL, or co-occurrence-as-edge.

0
installs
▌
Ns Reviewer · nextstage-brasil bundle
(NS) Senior Tech Lead review: SOLID, clean code, performance, security, testability. `Approved` only at score 10; score 9 = `Rejected`. Use after code changes, before PRs, at implementation closure, or code/PR/issue review gate — even without naming this skill. GitLab `ISSUE_URL`: Issue review mode. Do NOT write code-review-report.md. Do NOT use for root-cause debugging (ns-investigator).

0
installs
▌
Ns E2e Tests · nextstage-brasil bundle
(NS) Cypress E2E in independent tests-e2e/ at repo root (bootstrap when missing). DRY device-aware commands (shared/pages/device). Use when writing/refactoring Cypress specs, custom commands, scaffolding E2E, or implementing E2E tasks — not when planning E2E task markdown (ns-spec-driven references/e2e-test-task-generator.md). Mandatory discovery before specs.

0
installs
▌
Ns Autonomous · nextstage-brasil bundle
(NS) Autonomous execution engine — plans depth, resolves doubts from docs/specs, multi-agent work in an isolated worktree. Use for a local/pasted plan or "run this autonomously" without GitLab. Also Phase 2 under ns-execution-gitlab-issue (do not run standalone then). Not for single-step edits (ns-coder) or GitLab issues directly (ns-execution-gitlab-issue).

0
installs
▌
Ns Docs Writer · nextstage-brasil bundle
(NS) Human-facing project docs — README, docs/ guides, runbooks, contributor markdown. Use whenever the user asks for documentation, README updates, how-to guides, or docs/ content — even if they say "explain how to use" instead of "write docs". Do NOT use for code comments, API docblocks, requirements.md, or SDD version artifacts (use PM skills).

0
installs
▌
Ns Living Spec · nextstage-brasil bundle
(NS) Living domain specs under docs/specs/. Use after version closure when requirements, `Code Review: Approved`, and execution-handoff exist; ad-hoc when Approved behavioral diff + docs/specs/; appearance mode from ns-proto-creator / ns-proto-visual-guide (no Code Review gate). Incremental only. Do NOT run Version/Ad-hoc before `Code Review: Approved` (appearance mode excepted).

0
installs
▌
Ns Spec Driven · nextstage-brasil bundle
(NS) Spec-driven delivery — clarify, requirements, tasks (incl. unit/e2e), implement, resume/continue version from disk. Entry priority 2: feature specs, version work, multi-day scope, or "continue" / "resume version" when docs/versions/ has partial artifacts. Bare quick fixes: ns-coder. Do NOT: brownfield onboarding, architecture rules, /ns-harness prepare (never auto-run Prepare).

0
installs
▌
Ns Investigator · nextstage-brasil bundle
(NS) Root-cause diagnosis from errors, logs, stack traces, failing tests, or CI — entry priority 4 when the user wants diagnosis WITHOUT implement ("why does X break?"). Use proactively on unclear test/CI failures if they have not asked to fix yet. Do NOT use for implement/fix (ns-coder), version scope (ns-spec-driven), GitLab ISSUE_URL execution, or pre-merge review (ns-reviewer).

0
installs
▌
Ns Postgres RAG · nextstage-brasil bundle
(NS) PostgreSQL retrieval — pgvector, hybrid FTS+vector, GraphRAG tables, multi-hop, 1MM+ scale. Use for RAG or GraphRAG on Postgres, pgvector, hybrid search, document links, entity merge, multi-hop, or 1MM+ retrieval — even if they say search, embeddings, or knowledge graph in SQL. Do NOT use for ontology/cite-or-refuse (`ns-graphrag`), app code, competing vector DBs, CrewAI, or generic web apps.

0
installs
▌
Ns Backend Tests · nextstage-brasil bundle
(NS) PHPUnit unit/integration in backend package (bootstrap tests/ when missing). Docker-only: phpunit --testdox --stop-on-failure --stop-on-error, 120s. Use when writing/refactoring PHPUnit, unit-test tasks, or scaffolding backend tests on greenfield Laravel/PHP — not when planning test task markdown (ns-spec-driven references/unit-test-task-generator.md).

0
installs
▌
Ns Proto Creator · nextstage-brasil bundle
(NS) Playwright reverse-prototyping — capture live UI; create/evolve single prototype/ (git history; never v1/v2). Use when prototyping from a URL, reversing a screen into prototype/, evolving a prototype, AS-IS flows/fields, or "prototype this app/page". Do NOT use for appearance MDs only (ns-proto-visual-guide), full SDD (ns-spec-driven), bare code fixes (ns-coder), or /ns-harness prepare.

0
installs
▌
Ns Agent Platform · nextstage-brasil bundle
(NS) After ADR: lock compute per five-block (dedicated/K8s vs serverless vs edge), multi-tenant, onboarding, LLM-gateway-as-product. Writes docs/specs/agent-platform.md. Use for compute topology, cold-start, tenant isolation, inherited thresholds, LLM gateway vs API Gateway. Do NOT: framework/graph (`ns-agent-architecture`, `ns-langgraph-agents`), provider-selection.md, coding.

0
installs
▌
Ns Best Practices · nextstage-brasil bundle
(NS) Security/compat/a11y + Vercel Web Interface Guidelines. Use when hardening security, fixing CSP/CORS/headers, reviewing UI / checking a11y / auditing UX, or Web Interface Guidelines — even without saying "best practices"; also ns-proto-creator close-out. Do NOT use for MR/SOLID (ns-reviewer), visual redesign (ns-frontend-design), or features (ns-coder / ns-spec-driven).

0
installs
▌
Ns Frontend Design · nextstage-brasil bundle
(NS) Distinctive production UI — layout, typography, motion, polish; avoids AI-slop aesthetics. Use when building/refining pages, components, dashboards, KPI/analytics views, charts, forms, design-brief work, or better UI/UX — even if they do not say "design". Load docs/context/design-brief.md when present. Do NOT use for backend-only, requirements writing, or full SDD (ns-spec-driven).

0
installs
▌
Ns Project Manager · nextstage-brasil bundle
(NS) Gated PM: clarify, RICE/WSJF, sprint, PERT/Monte Carlo; version handoff; risk/status/OKR; orçamento, Function Points, proposta comercial; cronograma P100/P85/P50. Use on transcripts, backlog, timeline, delivery date, status, orçamento, cotação, cronograma, handoff, fecha a versão — even if PM unnamed. Do NOT use for coding, SDD, GitLab issue execution, or `/ns-requirements-enricher`.

0
installs
▌
Ns Agent Adaptation · nextstage-brasil bundle
(NS) Prompt vs RAG vs Agent vs Fine-Tune before framework. Writes `docs/specs/agent-design.md`. Use for agent design, agent vs RAG vs prompt vs fine-tune, plan/execute, memory, eval, guardrails — even without "adaptation". Do NOT: LangGraph/CrewAI ADR (`ns-agent-architecture`), LangGraph runtime (`ns-langgraph-agents`), Postgres RAG (`ns-postgres-rag`), GraphRAG (`ns-graphrag`), app coding.

0
installs
▌
Ns Langgraph Agents · nextstage-brasil bundle
(NS) LangGraph.js agent-api — bootstrap-agent-runtime, StateGraph, MCP, skill bind/inject, checkpointers, HITL/SSE. Use for new agent-api, LangGraph graphs, MCP wiring, orphan layout, bind parity, graph-spec sync, or "fix my LangGraph agent" / "wire MCP tools" / "translations in the graph". Do NOT use for CrewAI, generic web apps, or SDD-only with no agent-api.

0
installs
▌
Ns Gitlab Board Sync · nextstage-brasil bundle
(NS) Sync existing GitLab issues with local planning/execution — milestone, RF labels, status, assignee, estimates, spent time. Use during implementation when tasks link to GitLab issues or after plan-version-from-gitlab sync — not for creating new issues (use mcp-gitlab-usage). Always atomic set_issue_labels and three-step status cycle.

0
installs
▌
Ns Agent Architecture · nextstage-brasil bundle
(NS) Lock agent architecture ADR — LangGraph vs CrewAI, topology, HITL. Writes docs/specs/agent-architecture.md. Agent vs RAG vs fine-tune unlocked: stop; run ns-agent-adaptation first. Use for LangGraph/CrewAI, crews/graphs, HITL, multi-agent, ADRs, reverse-documenting agent, architecture defense. Do NOT: Prompt/RAG/Agent/Fine-Tune (ns-agent-adaptation), /ns-spec-driven Clarify, non-arch coding.

0
installs
▌
Ns Proto Visual Guide · nextstage-brasil bundle
(NS) Normative visual appearance guides (card/form/shell/overlay). MUST use for descrição normativa, guia visual, aparência, visual QA checklist, "how this looks", *-visual.md / *-painel-visual.md / *-appearance.md, or shell vs content / card vs form / carcaça vs formulário. Do NOT use for business rules, ERDs, layout math, API/auth, e2e, or ns-proto-creator.

0
installs
▌
Ns Gitlab CI Generator · nextstage-brasil bundle
(NS) Generate and adapt .gitlab-ci.yml for SaaS products with backend and frontend — test, build, E2E gate, deploy by branch. Use when the user asks for GitLab CI, pipeline setup, or CI/CD bootstrap for a monorepo product. Uses references/templates/gitlab-ci.template.yml as baseline. Out of scope for pure agent-runtime repos without backend+frontend layout.

0
installs
▌
Ns Requirements Enricher · nextstage-brasil bundle
(NS) Enrich requirements before autonomous execution. Use to enrich/expand requirements, grill-me, blocking product questions — GitLab ISSUE_URL or chat. Modes: Issue mode, Chat mode. Do NOT replace `/ns-spec-driven` Specify. Do NOT: ISSUE_URL execution (`ns-execution-gitlab-issue`), code review (`ns-reviewer`), start_execution_planning, PM intake, SDD Clarify.

0
installs
▌
Ns Execution Gitlab Issue · nextstage-brasil bundle
(NS) Execute a GitLab issue end-to-end — status gates, worktree isolation, atomic delivery, MR, mandatory review+fix loop. Use for external ISSUE_URL or SDD delivery unit (unit + issue_iid). External mode delegates coding to ns-autonomous; SDD unit mode uses ns-coder run-implementation. Needs mcp-gitlab-usage + ns-reviewer.

0
installs
▌
Code Routing Diagram · nextstage-brasil bundle
Maintainer-only skill for the nextstage-brasil/skills repo. Create or update the Mermaid flowchart that shows GitLab issue execution, coder entry, investigator, spec-driven, and autonomous handoffs. Use when working IN this repository and the user asks for routing diagram, coder flow mermaid, issue resolution chart, or after changing routing in ns-code-* skills. NOT installed via harness — lives in .cursor/skills/. Skills are source of truth; the diagram is derived from them. Do NOT invent routing in the diagram alone.

0
installs

26 published skills