Skip to content
Business
Skill

/product-manager

When you want to plan, build, or check an app from idea through launch readiness — web, Apple, mobile, or extensions. Writes the brief, picks the stack (Next.js + TypeScript + Prisma by default, Swift on Apple), designs complete UX states, defines roles and agent access,

From plugin
makerskills
91325 skills

Claude Code

$ npx -y skills add coreyhaines31/makerskills --skill product-manager --agent claude-code

SKILL.md

product-manager.SKILL.md
name: product-manager
description: "When you want to plan, build, or check an app from idea through launch readiness — web, Apple, mobile, or extensions. Writes the brief, picks the stack (Next.js + TypeScript + Prisma by default, Swift on Apple), designs complete UX states, defines roles and agent access, measures performance before optimizing, and produces a readiness report where missing evidence is never a pass. Four modes: spec (plan v1), check (launch readiness), audit (ranked improvements, including what a new model changes), fleet (a named list of apps). Triggers on \"/product-manager,\" \"act as my product manager,\" \"PM this app,\" \"build me an app,\" \"plan v1,\" \"spec this app,\" \"is this app ready to launch,\" \"launch readiness,\" \"audit my apps,\" \"what's missing before we ship,\" \"do a comprehensive audit,\" \"how could we improve my app,\" \"a new model just came out.\" Not for launch marketing or growth (see launch), integration plumbing (see toolify), CI cost (see ci-audit), or managing a project backlog/kanban (see project-manager)."
metadata:
  version: 0.7.1

/product-manager — Take an app from idea to launch-ready

Most apps that fail at launch don't fail on the main feature. They fail on what nobody specced: a client who can download another client's files, an invite button that sends twice on a slow network, a backup nobody ever restored, a cache keyed on project ID that leaks internal notes. This skill makes you decide those things up front, and then proves them before calling anything ready.

It ends at **launch-ready**, not launched. Promotion, SEO, launch posts and growth go to the marketing skills.

Mental model

  • **Applicability, not parity.** A local macOS timer doesn't need organizations. A collaborative SaaS does. Choose a platform profile, then check what applies.
  • **Evidence, not vibes.** Every requirement ends up as pass, gap, not assessed, or justified N/A. Missing evidence isn't a pass.
  • **Measure, then fix.** Broken before slow. Baseline before cache.
  • **Complement the model.** Build what gets *more* useful as models improve.

Step 0 — Pick the mode

| Mode | When | Output | |---|---|---| | **spec** | New app or v1 plan | Brief, stack, UX states, access model, test plan | | **check** | Existing app, "are we ready?" | Readiness report (read-only by default) | | **audit** | Existing app, "how could this be better?", or a new model just shipped | Ranked findings, model lens, comparison with the last audit (read-only) | | **fleet** | A named list of apps | One short report per app + a cross-app summary |

Ask which mode if it isn't obvious.

**What each step does per mode:**

| Step | spec | check / fleet | audit | |---|---|---|---| | 1 Brief | Write it; pick profile + stack | Infer it from the repo, confirm the gaps; keep the existing stack | Load the brief and the last audit; infer if missing | | 2 UX | Design the states | Audit the states that exist → report rows | UX lens → findings | | 3 Trust | Define the model | Audit it → report rows | Trust lens → findings | | 4 Build + proof | Plan units and tests | Map existing tests to journeys; note gaps | Proof and agent-ready-codebase lenses → findings | | 5 Performance | Plan baselines only (nothing to measure yet) | Measure with existing evidence | Performance lens, existing evidence only | | 6 Report | Baseline report, mostly *not assessed*, verdict *unproven* | Full readiness report | Audit report from `references/audit.md`. No launch verdict |

Skipping a step under time pressure is fine. Its rows become *not assessed*, never pass.

**Where output goes.** Spec: `docs/product/spec.md` in the app's repo. Show it before writing, and if there's no repo, show it in chat and ask where it should live. Check: show the report in chat and offer to save `docs/product/readiness-<YYYY-MM-DD>.md`. Audit: show it in chat and offer to save `docs/product/audits/<YYYY-MM-DD>-<model-slug>.md`. The next audit reads it to show what changed. Fleet: one report per app plus a summary table in chat.

**Read-only and approvals.** In **check**, **audit** and **fleet**, stay read-only unless the user asks for fixes. If they ask for a fix, draft it on a branch and keep the report's statuses unchanged until it's verified. Record the exact revision and environment: for web, branch/commit plus staging/prod; for native, OS version, hardware, and debug/release/signed build. When you lack access to something (deploy logs, production data), mark it *not assessed* instead of working around it. In **fleet**, use the list the user gives you. Don't go discovering every repo.

| Action | Needs | |---|---| | Reading code, config, existing logs and stats | Nothing beyond access | | Read-only queries against production (stats, plain EXPLAIN on a SELECT) | A yes naming the exact statements, with a read-only role | | Anything that executes writes, sends mail, charges, migrates, flushes a cache (incl. EXPLAIN ANALYZE on writes, test suites with live keys) | A sandbox (restored copy, branch DB, fake mailer, test-mode keys) **and** a yes naming the exact command | | Submitting or publishing anything (notarization, store, deploy, posts) | The user runs it, or gives a yes naming the exact command. Check mode never submits on its own. Hold off if the credential it relies on was just leaked |

Check for live keys in the test env and real addresses in fixtures before calling anything sandboxed. If a composed skill isn't installed, say so and use this skill's references.

Audit mode

Read `references/audit.md` and follow it. It runs Steps 1–5 as lenses on the existing app, plus a **model lens**: inventory every model call, get current model facts from the **claude-api** skill or official docs (never memory), and ask what the new model makes obsolete, newly possible, removable or stale. A **defensibility lens** scores the moats that still hold when code is cheap. Findings are ranked by impact, confidence and effort, and each

Read more
@coreyhaines31-2
Ships withmakerskills

AI agent skills for the personal operator's craft. Decisions, research, second-brain workflows, content rotation, scenario modeling, CFO cadence, domain hunts, and the meta-skills to author more. Built for founders and indie operators.

Stars on GitHub

Momentum

stars in total
913
Star history of coreyhaines31/makerskills on GitHub, a chart by star-history.com

Other skills on makerskills.

castmate

castmate

When you want to pull in the right AI model for the right job: hand a task to another agent CLI (Codex, Claude, Gemini, Grok,…

ci-audit

ci-audit

When you want to cut GitHub Actions minutes and wait time across one repo or a whole portfolio. Measures queue, setup and run…

company-brain

company-brain

Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so an agent can answer…

company-cfo

company-cfo

Monthly CFO workflow for a company or agency — pull raw data from bank + payment processor + payroll + expense management,…

decide

decide

When you have a decision to make and want a structured workflow that picks the load-bearing questions, walks through them,…

More skills from other plugins.

opc-asset-ops

opc-asset-ops

Turn repeatable outputs of a one-person company into compounding assets. Use when Codex needs to explain asset-compounding…

@easychen@easychenInstall Skill
dbs

dbs

dontbesilent 商业工具箱的技能调度台,根据当前问题和反馈选择下一步,在对话中直接执行、澄清、组合或对照尝试 Skill。用户不知道从哪里开始、需要调整处理方法、第一次使用…

dbs5d11k
@dontbesilent2025@dontbesilent2025Install Skill

Questions about product-manager.

Which coding agents can use product-manager?
product-manager installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.