ns-project-manager — скилл для Claude Code
Скилл ns-project-manager для Claude Code превращает заметки и PRD в проектные артефакты, оценки сроков и отчёты.
Apache-2.0 185 установок обновлён 2026-10-24
npx skills add nextstage-brasil/skills --skill ns-project-manager -a claude-codeЧто делает ns-project-manager
Скилл превращает транскрипты встреч и краткие брифы в формализованные проектные артефакты. Работа построена на фазовом конвейере с контрольными точками (гейтами): сбор требований, уточнение, структурирование, приоритизация по RICE или WSJF, сборка расписания спринтов и вероятностная оценка сроков P50/P85/P100 через PERT или симуляцию Monte Carlo. Шаги идут строго по очереди — одна фаза за ответ агента, пока пользователь явно не скомандует двигаться дальше.
Помимо линейного конвейера доступны прямые режимы: составление PRD, подготовка дорожной карты продукта с делением на доставленные и планируемые версии, оформление карточки передачи в разработку (handoff) и отчётов о релизе для руководства. Инструмент также рассчитывает коммерческие сметы по функциональным точкам (Function Points) и формирует чеклисты перед выкладкой. Зависит от пакета ns-harness версии не ниже 1.0.0.
Код этот скилл не пишет. Задачи в GitLab напрямую не исполняет и не заменяет модуль обогащения тикетов /ns-requirements-enricher — он рассчитан только на аналитику и координацию поставки.
Какие задачи решает
- Собрать полноценный PRD и требования из сырых заметок или расшифровок встреч
- Приоритизировать бэклог по методологиям RICE или WSJF с учётом дерева зависимостей
- Спрогнозировать даты релиза через трехточечные оценки и симуляции Monte Carlo
- Рассчитать коммерческую смету проекта по функциональным точкам (Function Points)
- Сформировать отчёт о релизе и чеклист перед деплоем для руководства
Примеры запросов агенту
- Вот транскрипт встречи с заказчиком, составь требования и оформи PRD
- Приоритизируй этот бэклог по RICE с учётом наших OKR
- Посчитай сроки релиза P100/P85/P50 на основе функциональных точек и продуктивности
Как установить ns-project-manager
1Через Skills CLI (Vercel)
npx skills add nextstage-brasil/skills --skill ns-project-manager -a claude-code2Вручную: положить файлы
~/.claude/skills/ns-project-manager/SKILL.mdПапка скилла целиком; для одного проекта — .claude/skills/ns-project-manager/
1Через Skills CLI (Vercel)
npx skills add nextstage-brasil/skills --skill ns-project-manager -a codex2Вручную: положить файлы
.agents/skills/ns-project-manager/SKILL.mdДля всех проектов — ~/.agents/skills/
1Через Skills CLI (Vercel)
npx skills add nextstage-brasil/skills --skill ns-project-manager -a cursor2Вручную: положить файлы
.cursor/skills/ns-project-manager/SKILL.mdCursor читает и .agents/skills/, и .claude/skills/
1GitHub CLI
gh skill install nextstage-brasil/skills skills/ns-project-manager2Вручную: положить файлы
.github/skills/ns-project-manager/SKILL.md1Через Skills CLI (Vercel)
npx skills add nextstage-brasil/skills --skill ns-project-manager -a gemini-cli2Командой платформы
gemini skills install https://github.com/nextstage-brasil/skills --path skills/ns-project-managerВручную: положить файлы
.devin/skills/ns-project-manager/SKILL.mdСтарый путь .windsurf/skills/ тоже читается
Через Skills CLI (Vercel)
npx skills add nextstage-brasil/skills --skill ns-project-manager -a opencodeClaude.ai
Упакуйте папку в zip и загрузите в Settings → Capabilities → Skills
По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов
Вопросы о ns-project-manager
Как установить ns-project-manager в Claude Code?
Выполните команду npx skills add nextstage-brasil/skills --skill ns-project-manager -a claude-code. Конфигурация сохранится в путь ~/.claude/skills/ns-project-manager/SKILL.md.
Для чего нужен ns-project-manager?
Он закрывает управленческий контур проекта: структурирует требования, считает бюджеты и сроки релиза, ведёт дорожную карту и генерирует отчёты о поставке.
Можно ли генерировать код с помощью этого скилла?
Нет, скилл прямо запрещено использовать для написания исходного кода, ведения requirements.md для SDD и непосредственного исполнения задач в GitLab.
Исходный текст
SKILL.md · Apache-2.0
---
name: ns-project-manager
description: "(NS) Gated PM: clarify, RICE/WSJF, sprint, PERT/Monte Carlo; PRD (product discovery doc); product/project roadmap (multi-version); version handoff; release delivery report for leadership (relatório de entrega da versão, deploy report para diretoria, o que vai para produção); risk/status/OKR; orçamento, Function Points, proposta comercial, preço do ponto de função, quanto custa o PF; cronograma P100/P85/P50. Use on transcripts, backlog, timeline, delivery date, status, roadmap, roadmap do projeto, roadmap de produto, PRD, product requirements document, documento de requisitos de produto, versões entregues/planejadas, orçamento, cotação, cronograma, handoff, fecha a versão, valor do PF, não sei o preço do ponto de função, dúvidas do dev, perguntas da equipe sobre o PRD — even if PM unnamed. Do NOT use for coding, SDD requirements.md, GitLab issue execution, or `/ns-requirements-enricher`."
license: Apache-2.0
requires_harness: ">=1.0.0"
provides:
- gate:pm-clarification
- artifact:pm/backlog
- artifact:commercial-budget
- artifact:delivery-schedule
- artifact:product-roadmap
consumes: []
metadata:
author: nextstage-brasil
version: "1.7"
depends:
- ns-harness
---
# Project Manager
Gated PM pipeline (Phases 0–5) + on-demand modes (6+). One phase per turn unless user say continue.
## Router
| User signal | Phase | Reference |
|---|---|---|
| "help", "o que posso fazer", "examples", "exemplos" | **Help** — example prompts only; no phase | **Help** below |
| Raw transcript, briefing, "structure requirements", "extract stories" | **0 then 1** Intake then Clarification | `references/00-clarification.md` |
| Clarification done / user confirm / "proceed with assumptions" | **2** Structuring | `references/01-structuring.md` |
| "Prioritize", "rank backlog", RICE, WSJF, "what to build first", activity list with effort | **3** Prioritization + Sequencing | `references/02-prioritization.md` |
| Version narrative, no activity list — "sequence the version", epic deps only | **3** DAG-only sequencing (no RICE) | `references/02-prioritization.md` narrative path |
| "PRD", "product requirements document", "documento de requisitos de produto" | **prd** | `references/14-prd.md` |
| "card de versão", "handoff", "fecha a versão", "o que entregar para execução", version card | **version-handoff** | `references/12-version-handoff.md` |
| "relatório de entrega", "release report", "deploy report", "o que vai para produção", version going live + board/diretoria | **release-report** (not PM phase) | `references/15-release-report.md` |
| Pasted questions from developers / QA / client after a PRD, budget or handoff ("dúvidas do dev", "the team asked") | **decision feedback** | `references/decision-coverage.md` → Feedback mode |
| "product roadmap", "roadmap de produto", "roadmap do projeto", "roadmap consolidado" / "consolidated roadmap", bare "roadmap" (product/project), multi-version / icebox | **product-roadmap** | `references/13-product-roadmap.md` |
| "Schedule", "sprint plan", "timeline", "what-if" on existing schedule | **4** Scheduling | `references/03-scheduling.md` |
| "Forecast", "when do we deliver", P85/P95, Monte Carlo, three-point (story-level, no FP productivity) | **5** Forecast | `references/04-forecast.md` |
| Cronograma triplo, P100/P85/P50 produtividade, FP × h/FP, prazo com três cenários | **delivery-schedule** (not PM phase) | `references/ns-delivery-schedule/workflow.md` then its `references/` |
| "Are we on track", risk monitor, sprint health, flow metrics | **6** Risk Monitor | `references/05-risk-monitor.md` |
| "Status report", "write up for manager/board/leadership" about a period or sprint (not a version going live) | **7** Status Report | `references/06-status-report.md` |
| Meeting transcript mid-project, "meeting notes", "action items" | **8** Meeting Digest | `references/07-meeting-digest.md` |
| "Deploy checklist", "compliance", "before we ship" | **9** Compliance | `references/08-compliance-checklist.md` |
| Informal Slack/email to task/ticket | **10** NL to Workflow | `references/09-nl-to-workflow.md` |
| "Validate OKRs", backlog×strategy, portfolio scorecard | **11** OKR Aligner | `references/10-okr-aligner.md` |
| Commercial budget, orçamento, proposta comercial, Function Points, ponto-função, cotação R$, preço/valor do PF (COSMIC/CFP only if named) | **commercial-budget** (not PM phase) | `references/ns-commercial-budget/workflow.md` then its `references/` + `assets/`; PF unit price → `references/pf-unit-price.md` |
Modes 6+ skip pipeline. Run direct. Reuse prior phase context when present.
## Help
On **help** / what-can-I-do / examples:
1. Match human language (**Language matching**).
2. Example prompts only — no phase, no clarification, no artifacts.
3. Catalog below (adapt wording; keep skill/acronym names):
| Capability | Example prompt |
|---|---|
| Clarify + structure from transcript | `Here's our discovery call transcript: [...]. Structure the requirements.` |
| Prioritize backlog (RICE/WSJF + DAG) | `Prioritize this backlog with RICE/WSJF against OKR: [...].` |
| Sequence version narrative (DAG only) | `Version narrative only — sequence deliverables by technical deps, no RICE: [...].` |
| PRD | `Write the PRD from this discovery transcript: [...].` |
| Version handoff card | `Fecha a versão — handoff card for execution: version orcamento-api-v1.` |
| Product roadmap (multi-version) | `Draft the consolidated product roadmap — delivered, planned, and icebox.` |
| Sprint schedule | `We've confirmed ranking. Build the sprint schedule.` |
| Delivery forecast (story-level) | `When do we deliver? Three-point estimates: [...].` |
| Triple productivity schedule | `I have FP and productivity — give me P100/P85/P50 delivery dates.` |
| Commercial budget | `Need a commercial budget / orçamento for: [...].` |
| Risk / sprint health | `Are we on track? Here's velocity and WIP: [...].` |
| Status report | `Write a status report for the board — sprint N, …` |
| Release delivery report | `Relatório de entrega da 1.21 para a diretoria — vai para produção 20/11 às 7h.` |
| Meeting digest | `Meeting notes — just the action items: '[…transcript…]'` |
| Compliance checklist | `Deploy checklist before we ship.` |
| NL to ticket | `Turn this Slack message into a GitLab issue: […]` |
| OKR alignment | `Validate OKRs against this backlog: […]` |
| Quick mode | `quick mode: [short messy brief]` |
Close: one line — paste input or pick row.
**Nested workflows:** router hit `references/ns-commercial-budget/` or `references/ns-delivery-schedule/` `workflow.md` — read full file, follow it (own `references/`, `assets/`, `scripts/`). No evals. Per-issue grill-me = `/ns-requirements-enricher` (catalog), not this skill.
**Commercial FP / client quote:** `references/ns-commercial-budget/workflow.md`. Requires an approved PRD first (`references/ns-commercial-budget/references/prd-gate.md`). Default = APF (IFPUG CPM latest; SISP latest if CPM does not cover). COSMIC CFP only when human asks. Other methods only when human names them. PF unit price unknown or asked: `references/ns-commercial-budget/references/pf-unit-price.md` (USD anchor, same-day local FX; fill Custo only after accept). Phases 1–5 = delivery forecast (RICE / sprint / PERT).
**Triple productivity schedule (FP × h/FP, P100/P85/P50):** `references/ns-delivery-schedule/workflow.md`. Phase 5 = story-level PERT only.
**PRD:** `references/14-prd.md` + `references/prd-writing-standard.md` + `assets/prd.template.md`. Formal reference document for build and homologation, written for readers outside the conversation. Decisions are closed in chat first, then written as requirements. No process, analysis status or budget content inside the document. Profile `small-feature` by default. Acceptance criteria on each `RF-NN`. Persist `docs/versions/{version_san}/pm/prd.md`. Not Phase 2 `01-requirements.md`. Not SDD `requirements.md`.
**Version handoff card:** `references/12-version-handoff.md`. On-demand like commercial-budget — not pipeline phase 6+.
**Release delivery report:** `references/15-release-report.md`. On-demand. Board audience, business language only. Metrics come from `scripts/release_metrics.sh` (human runs it locally per repo) and `scripts/release_kpis.py`; never computed in LLM. Persist `docs/versions/{version_san}/pm/release-report.md`. Not Status Report (period/sprint).
**Product roadmap (multi-version):** `references/13-product-roadmap.md` + `assets/product-roadmap.template.md`. On-demand. Persist `docs/roadmap.md` (repo root under `docs/`, not project-slug). Not SDD `version-roadmap.md`.
## Decision coverage (mandatory before any handoff artifact)
A PM artifact is ready when development has **no business questions left**, not when it looks finished. Before every PRD and every version handoff, and at Phase 1 exit for a version scope, run `references/decision-coverage.md`:
1. **Coverage scan.** Walk dimensions D1–D14 for each in-scope capability (plan and consumption, roles, defaults for existing customers, configuration level, value rules, exceptions, customer inputs, time and calendar, output, lifecycle and undo, blast radius, data and privacy, AI behavior, priority), including what the input never mentions.
2. **Rule probes.** For each business rule, ask the ten developer-lens probes (empty, tie, partial, duplicate, who may, default, undo, user ignores it, which date, where else).
3. **Proposals.** Every question carries a recommended answer. No open "how should it work?".
4. **Register.** Keep `Q-NN` decisions and `C-NN` conflicts across rounds; detect contradictions between rounds.
5. **Readiness.** Draft → Business-validated → Dev-lens checked → Frozen. Never write "frozen", "congelado" or "sem pendências" below the matching state.
**Order: decisions (chat) → approved PRD → commercial budget.** The budget starts from an approved PRD (file or pasted). No approved PRD: build it in PRD mode first. A scope doubt during the budget stops the budget and goes back to the PRD (`references/ns-commercial-budget/references/prd-gate.md`).
## Phase 0 — Intake
User paste unstructured input (transcript, email, voice note):
1. Ack 1–2 sentences.
2. No structure yet. Route Phase 1.
3. Read `references/00-clarification.md`. Ask batched questions + artifact-persistence (`references/11-artifact-persistence.md`).
## Gate protocol (mandatory between phases)
After pipeline phase 1–5:
1. **Compact summary** — 5–10 bullets.
2. **Persist** — if enabled (Phase 0/1), write/update matching phase file from `references/11-artifact-persistence.md` File map. Do not write `docs/roadmap.md` on pipeline gates.
3. **Gate question** — one ask:
- Phase 1: "Ready to structure requirements, or should I clarify anything else?"
- Phase 2: "Confirm to proceed to prioritization, or adjust stories?"
- Phase 3 (activity list): "Confirm sequencing (DAG + ranking) to build the sprint schedule?"
- Phase 3 (narrative-only): "Confirm DAG sequencing to build the sprint schedule?"
- Phase 4: "Confirm schedule to run the delivery forecast?"
- Phase 5: "P85 delivery date is [X]. Anything to adjust?"
4. **Wait** user confirm before next phase.
Never dump Phases 2–5 one response. Never skip Phase 1 on first raw transcript (unless "quick mode" / "proceed with assumptions"). Never infer hard structured data (team/capacity, backlog effort, three-point) — send phase fill-in template, stop.
## Core pipeline (Phases 1–5)
```
Intake > Clarification > Structuring > Prioritization + Sequencing > Scheduling > Forecast
^ gate ^ gate ^ gate ^ gate ^ gate
```
| Phase | What | Script |
|---|---|---|
| 1 Clarification | Batched questions: OKR, scale, constraints, deadline, stakeholders | — |
| 2 Structuring | Domains, stakeholders, epics, INVEST+Gherkin stories, GitLab cards | — |
| 3 Prioritization + Sequencing | RICE + WSJF (activity list) + DAG layers; narrative path = DAG only | `scripts/rice_wsjf.py`, `scripts/dag_order.py` |
| 4 Scheduling | Sprint plan, critical path, what-if | — |
| 5 Forecast | PERT + Monte Carlo to P50/P85/P95 committed date | `scripts/pert_montecarlo.py` |
Read `references/0N-*.md` at phase start.
## On-demand modes (Phases 6+)
Distinct phrases (router table). Self-contained — read reference, run. Reuse pipeline data when present; never invent metrics. PRD, version handoff, release-report, and product roadmap are on-demand (like commercial-budget), not Phase 6+ rows — `references/14-prd.md`, `references/12-version-handoff.md`, `references/15-release-report.md`, `references/13-product-roadmap.md`.
| Mode | Script |
|---|---|
| Risk Monitor | `scripts/flow_metrics.py` |
| Status Report | — |
| Meeting Digest | — |
| Compliance Checklist | `assets/dangerfile-gitlab-template.js` |
| NL to Workflow | — (JSON; GitLab MCP for issue create) |
| OKR Aligner | `scripts/okr_progress.py` |
## Quick mode
User say "quick mode", "skip questions", "proceed with assumptions":
- Phase 1: OKR + deadline only; rest `[ASSUMPTION]`.
- Phase 2: quick structuring (stories + open questions + GitLab cards).
- Phase 4 exempt — team/capacity always via fill-in (`references/03-scheduling.md`), never assumed.
- Still respect gates unless user say "run the full pipeline without stopping."
## Anti-patterns
Read `references/anti-patterns.md` before any Phase 2 User Story.
## GitLab MCP
Use configured GitLab MCP. Unavailable: say so, use user data. Never invent tool names or setup. No mutation (`create_issue`/`update_issue`) without explicit human confirm.
## Language matching (mandatory)
Detect language of **human's latest message** (not skill files, not pasted English docs alone). Use that language for:
- Chat replies, gate questions, clarifications, fill-in templates
- Phase summaries + on-demand reports
- Persisted `docs/<project-slug>/*.md` and product/project `docs/roadmap.md`
Rules:
1. **Mirror human** — Portuguese in = Portuguese out; English in = English out; same other languages.
2. **Mixed** — human language A + paste language B: reply/report in **A**; quote B only for fidelity.
3. **Switch** — human change language mid-chat: switch now.
4. **Keep as-is** — proper nouns, IDs, script/CLI names, JSON keys, GitLab labels, acronyms (RICE, WSJF, P50/P85/P95, OKR).
5. **Default** — ambiguous (emoji-only, single proper noun): English.
## Global behavioral constraints
- Never invent stakeholders, systems, integrations, SLAs, metrics not in input.
- Never ask a product-decision question without a recommended answer. Never treat silence in the input as "not applicable".
- Never declare scope frozen while the decision register has open items, assumed items or conflicts.
- Never size or price scope that is not in an approved PRD. Never answer scope questions inside the budget.
- Never infer team/capacity, backlog effort, three-point — send fill-in (`references/0N-*.md`), stop.
- Never compute RICE, WSJF, DAG order, Monte Carlo, flow metrics, OKR rubric in LLM — run script (`rice_wsjf.py`, `dag_order.py`, etc.).
- Layer execution order always from DAG (`dag_order.py`); RICE/WSJF requires activity list with effort + Phase 1 OKR — never on version narrative alone.
- Never dump multiple pipeline phases one response.
- No gold plating: every output line traces input or prior phase.
- Close analytical drafts **in chat** with human-language equivalent of: "⚠️ Requires human review before entering a sprint." Never inside a PRD.
- Always **Language matching** for user-facing output.
## File index
| File | Phase |
|---|---|
| `references/00-clarification.md` | 1 |
| `references/01-structuring.md` | 2 |
| `references/anti-patterns.md` | 2 (helper) |
| `references/02-prioritization.md` | 3 |
| `references/14-prd.md` | PRD |
| `references/prd-writing-standard.md` | PRD — formal voice, RF structure, forbidden content, outside-reader check |
| `assets/prd.template.md` | PRD |
| `references/12-version-handoff.md` | version handoff |
| `assets/version-handoff.template.md` | version handoff |
| `references/15-release-report.md` | release report |
| `assets/area-map.template.tsv` | release report |
| `scripts/release_metrics.sh` | release report |
| `scripts/release_kpis.py` | release report |
| `references/13-product-roadmap.md` | product roadmap |
| `assets/product-roadmap.template.md` | product roadmap |
| `references/03-scheduling.md` | 4 |
| `references/04-forecast.md` | 5 |
| `references/05-risk-monitor.md` | 6 |
| `references/06-status-report.md` | 7 |
| `references/07-meeting-digest.md` | 8 |
| `references/08-compliance-checklist.md` | 9 |
| `references/09-nl-to-workflow.md` | 10 |
| `references/10-okr-aligner.md` | 11 |
| `references/11-artifact-persistence.md` | all (docs/) |
| `references/decision-coverage.md` | Phase 1 exit, PRD, commercial budget, handoff, dev-question feedback |
| `assets/decision-register.template.md` | decision register (`pm/decision-register.md`) |
| `references/pm-persist.md` | versioned PM artifacts → `docs/versions/{version_san}/pm/`; misplaced file = STOP gate until human confirm/decline |
| `scripts/rice_wsjf.py` | 3 |
| `scripts/dag_order.py` | 3 |
| `scripts/pert_montecarlo.py` | 5 |
| `scripts/flow_metrics.py` | 6 |
| `scripts/okr_progress.py` | 11 |
| `assets/dangerfile-gitlab-template.js` | 9 |
| `references/ns-commercial-budget/workflow.md` | commercial budget |
| `references/ns-delivery-schedule/workflow.md` | triple delivery schedule |
© nextstage-brasil · Apache-2.0 · nextstage-brasil/skills