pm-ideate

pm-ideate is a skill for Claude Code, Codex from hiepdnh/Agentic-Development-Lifecycle. It costs 87 tokens per session (1,021 once invoked), scanned A, original, MIT.

An idea-refinement process that turns a vague software idea into a clearer concept with a problem statement and a list of work that is out of scope.

In plain words
What is it for?
Use it to explore several possible solutions, compare them through different viewpoints, and prepare an idea for a later specification.
Why use it?
It helps prevent the team from writing detailed requirements for the wrong problem or committing too early to one direction.

Skill for Claude CodeCodex

Part of the agentic-development-lifecycle plugin — 35 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/hiepdnh/agentic-development-lifecycle/pm-ideate
Any agent
npx skills add hiepdnh/Agentic-Development-Lifecycle --skill pm-ideate
Clone the repo
git clone --depth 1 https://github.com/hiepdnh/Agentic-Development-Lifecycle

Made for: Claude Code, Codex.

Or install agentic-development-lifecycle, the plugin that ships this one along with the rest of its 35 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pm-ideate

README.md
[![agentmods](https://agentmods.dev/badge/skills/hiepdnh/agentic-development-lifecycle/pm-ideate.svg)](https://agentmods.dev/skills/hiepdnh/agentic-development-lifecycle/pm-ideate)
Your own site
<a href="https://agentmods.dev/skills/hiepdnh/agentic-development-lifecycle/pm-ideate"><img src="https://agentmods.dev/badge/skills/hiepdnh/agentic-development-lifecycle/pm-ideate.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,021 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.01021
Opus 5 $0.00044 $0.00511
Sonnet 5 $0.00017 $0.00204
Haiku 4.5 $0.00009 $0.00102

Measured 5d ago against content hash 5a34812cecc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

pm-ideate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/pm-ideate/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: /pm-ideate

Role: PM / BA
Mục đích: Refine ý tưởng mờ nhạt thành concept rõ ràng TRƯỚC khi chạy /ba-spec. Tránh spec sai từ đầu.


Khi nào dùng

  • Yêu cầu từ stakeholder còn rất mơ hồ ("làm cái gì đó với dashboard")
  • Nhiều hướng khả thi, chưa rõ nên đi hướng nào
  • Muốn explore options trước khi commit vào spec

Hướng dẫn thực hiện

Bước 1 — Gate: Thu thập ý tưởng thô

## Tôi sẽ giúp làm rõ ý tưởng này.

Mô tả cho tôi nghe: vấn đề bạn đang muốn giải quyết là gì?
(Không cần hoàn chỉnh — rough idea cũng được)

Bước 2 — Diverge: Tạo 5-8 variations

Research trước khi tạo variations: Dùng web_search (nếu không có công cụ search, hỏi user) kiểm tra đã có sản phẩm/pattern nào giải quyết vấn đề tương tự chưa. Fold finding liên quan vào các variation bên dưới — tránh generate ý tưởng trong vacuum, bỏ qua prior art.

Phân tích ý tưởng qua các lens:

  • Inversion: Nếu làm ngược lại thì sao?
  • Simplification: Phiên bản đơn giản nhất có thể là gì?
  • Constraint removal: Nếu không có giới hạn thời gian/budget thì sao?
  • Analogy: Ngành khác giải quyết vấn đề tương tự như thế nào?
  • User focus: Nếu chỉ cần giải quyết cho 1 user cụ thể, làm gì?

Tạo 5-8 variations ngắn gọn (2-3 câu mỗi cái).

Bước 3 — Converge: Nhóm thành 2-3 hướng

Cluster các variations thành 2-3 strategic directions:

## Tôi thấy [N] hướng tiếp cận:

### Hướng A: [Tên — từ khóa đặc trưng]
[2-3 câu mô tả]
- Phù hợp khi: [điều kiện]
- Risk: [rủi ro chính]

### Hướng B: [Tên]
...

### Hướng C: [Tên] (nếu có)
...

Bước 4 — One-pager + "Not Doing" list

## Đề xuất hướng đi: [Hướng X]

**Problem statement**: [1 câu]
**Proposed solution**: [2-3 câu]
**Target users**: [Ai]
**Success metric**: [Đo thành công bằng gì]

### ❌ NOT Doing (quan trọng)
- [Điều 1 không làm trong scope này]
- [Điều 2 không làm]
- [Điều 3 không làm]

Bước 5 — Gate cuối: Xác nhận hướng đi

AskUserQuestion({
  questions: [
    {
      question: "\"Not Doing list\" có đúng không?",
      header: "Not Doing",
      multiSelect: false,
      options: [
        { label: "Đúng", description: "Not Doing list đã chính xác" },
        { label: "Còn trong scope", description: "Có mục vẫn đang trong scope — cần điều chỉnh" }
      ]
    },
    {
      question: "Success metric có measurable không?",
      header: "Metric",
      multiSelect: false,
      options: [
        { label: "Có", description: "Success metric measurable được" },
        { label: "Chưa đủ", description: "Cần sửa success metric cho rõ ràng hơn" }
      ]
    },
    {
      question: "Sẵn sàng chạy /ba-spec với hướng này chưa?",
      header: "Next step",
      multiSelect: false,
      options: [
        { label: "Sẵn sàng", description: "Chạy /ba-spec để viết spec chi tiết" },
        { label: "Cần explore thêm", description: "Cần explore thêm hướng khác trước khi spec" }
      ]
    }
  ]
})

Read the full file on GitHub · 126 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 126 lines · 87 tokens per session scan A 5a34812cecc7

Subscribe to this mod's changes

pm-ideate is a skill published in the GitHub repository hiepdnh/Agentic-Development-Lifecycle (6 stars, last pushed 8d ago), licensed MIT. It adds 87 tokens to every session and 1,021 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens