Agent skill

Writing Prds

by RefoundAI in RefoundAI/lenny-skills

Help users transform abstract ideas into actionable project specs that align engineering and design teams on the problem and success metrics.

MITAuto-check passedProduct & Project Management

Install Writing Prds

skills CLI
$ npx skills add RefoundAI/lenny-skills --skill writing-prds -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install RefoundAI/lenny-skills writing-prds --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/writing-prds .claude/skills/writing-prds && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
writing-prds
GitHub stars
1.4k
Token cost
~1.8k tokens
SKILL.md length
1,026 words
Files
3 (incl. references)
Skills in repo
76
Repo updated
First seen
Licence
MIT

At a glance

Help users transform abstract ideas into actionable project specs that align engineering and design teams on the problem and success metrics.

  • Works in 4 steps: Drafting the core problem - Assist in… → Establishing success metrics - Help… → Defining project boundaries - Guide the… → …
  • Tasks that involve PRD writing
  • SKILL.md covers How to Help, Core Principles, Templates & Frameworks and Questions to Help Users, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Writing Prds is an agent skill from RefoundAI/lenny-skills. Help users transform abstract ideas into actionable project specs that align engineering and design teams on the problem and success metrics.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/artifacts.md` and `references/guest-insights.md`).

It sits in Product & Project Management, covering PRD writing and Product metrics. The repository describes itself as: 86 product management skills from Lenny's Podcast for Claude Code and AI agents. Hiring, user research, strategy, shipping, and more. The licence is MIT.

When your agent uses it

  • Tasks that involve PRD writing
  • Tasks that involve Product metrics

Example prompts

  • “/writing-prds”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Drafting the core problem - Assist in articulating a concise problem statement that is agnostic of any specific solution.
  2. Establishing success metrics - Help define specific, measurable outcomes that will act as a filter for future feature requests.
  3. Defining project boundaries - Guide the user through narrowing fuzzy requests into a bounded concept using shaping techniques.
  4. Reviewing for clarity - Audit existing drafts for brevity, readability, and technical awareness to prevent micromanagement.

What it can do on your machine

Read from SKILL.md and the folder at commit 13598cc. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Writing Prds loads about 1.8k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 39 tokens; SKILL.md has 1,026 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~18k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from RefoundAI/lenny-skills at commit 13598cc, republished under its MIT licence (© RefoundAI). 1,026 words, ~1,753 tokens.

Download SKILL.mdSave it as .claude/skills/writing-prds/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
writing-prds
description
Help users transform abstract ideas into actionable project specs that align engineering and design teams on the problem and success metrics.

Writing Product Requirement Documents

Define clear problems and bounded solutions to maximize team velocity and creative output.

Help the user with writing product requirement documents using insights from 14 guests and posts across Lenny's Podcast and Newsletter.

How to Help

  1. Drafting the core problem - Assist in articulating a concise problem statement that is agnostic of any specific solution.
  2. Establishing success metrics - Help define specific, measurable outcomes that will act as a filter for future feature requests.
  3. Defining project boundaries - Guide the user through narrowing fuzzy requests into a bounded concept using shaping techniques.
  4. Reviewing for clarity - Audit existing drafts for brevity, readability, and technical awareness to prevent micromanagement.

Core Principles

Design for functional prototyping

Jenny Wen: "We used to go off and make this two-year, five-year, 10-year vision even. Now it becomes a vision that's three to six months out, and isn't necessarily creating this beautiful deck, sometimes just creating a prototype that points people in the right direction."

Design should focus on short term functional prototyping rather than static long term planning to keep up with AI driven engineering speeds.

Shape project boundaries early

Ryan Singer: "What we need to do in a shaping session is we come out with some kind of diagram where engineers, product and design, they're saying, "We understand that." So the first thing is we are not going to start something unless we can see the end from the beginning."

Use high intensity collaborative sessions with design and engineering to create a shared understanding of boundaries before development begins.

Center documents on the problem

From "Examples and templates of 1-Pagers and PRDs": "Problem-oriented: They crystallize the problem being solved in a few strong sentences—ideally near the top of the document—to focus the brainpower of every teammate in the same direction."

A successful PRD starts with a clearly defined problem and specific success metrics to ensure the team aligns on the why before the what.

Force clarity through brevity

From "My favorite product management templates": "A reminder of how valuable it is to keep these to one page, at least to start"

Limiting initial project documents to a single page forces the team to stay focused on core goals and helps prevent early complexity.

Document to move from chaos to clarity

Melanie Perkins: "So we have this concept of chaos to clarity and every idea starts in the chaos side, and then you have to work all the way to the other side, which is clarity. And so chaos can be an idea, it can be a problem, it can be a philosophy or a belief."

Writing down abstract ideas is the essential first step to transforming amorphous concepts into actionable projects.

Avoid creative micromanagement

From "Five habits of highly annoying product managers": "There’s a fine line between articulating the important details of a project spec and spending three pages explaining one button. This annoying habit can apply to both the beginning of a project, telling designers and engineers exactly how a feature needs to work, and also at the end when you spec out each feature for days."

Over specifying features stifles the creativity of engineers and designers. Documentation should facilitate conversation rather than replace it.

Automate technical writing with AI

From "How AI will impact product management": "Describe what you want in human language, get an 80% complete draft, refine it, and then ship. This is already happening with tools like ChatPRD."

Use AI tools to generate the majority of technical documentation so product managers can focus on the final refinement and strategic nuance.

Show full SKILL.md (431 more words)Show less

Templates & Frameworks

  • Lenny's 1-Pager Template (Examples and templates of 1-Pagers and PRDs) - Lenny's personal template used anytime he starts a new project
  • 5 Elements of a Great 1-Pager/PRD (Examples and templates of 1-Pagers and PRDs) - An evaluation rubric for what makes a product spec effective, used both for writing and reviewing PRDs
  • AI Prompt: Write a PRD (Product manager is an unfair role. So work unfairly.) - A ChatGPT prompt template (GPT-4o and up) for drafting a PRD by dictating context via speech-to-text.
  • Breadboarding and Fat Marker Sketching (Ryan Singer) - Two collaboration techniques for shaping sessions that are more detailed than wireframes but less polished than Figma — designed to communicate the idea clearly
  • Technical PM Questions for PRDs and Feature Work (Become a more technical product manager) - Questions PMs should ask when writing PRDs or working on features to demonstrate technical awareness and improve collaboration
  • Five Attributes of a Strong Problem Statement (A Three-Step Framework For Solving Problems 👌) - Criteria for evaluating whether a problem statement is well-crafted, used when writing the Problem section of the 1-pager.
  • PRD Review Checklist (derived from Lenny's critiques) (Examples and templates of 1-Pagers and PRDs) - A checklist derived from Lenny's evaluation of the four real-world examples, identifying common pitfalls to check for
  • Duolingo One-Pager Template (How Duolingo builds product) - The template Duolingo uses for early-stage product review one-pagers to get feedback on feature ideas

See references/artifacts.md for the full list with details.

Questions to Help Users

  • "What is the single most important problem this project is solving for the user?"
  • "What specific metrics will we use to determine if this project is a success?"
  • "Which features or tasks are explicitly out of scope for this version?"
  • "Have we gathered feedback from engineering on the technical constraints yet?"
  • "How much time are we willing to spend on this problem before we move on?"
  • "Is this document brief enough that the entire team will actually read it?"

Common Mistakes to Flag

  • Using the word just - It undermines the expertise of engineers and risks burning them out on unrealistic promises of quick fixes.
  • Premature high fidelity mocks - It anchors the team to a specific solution before they have fully explored the problem space or technical constraints.
  • Ignoring non-goals - Failing to establish what you are not building leads to scope creep and loss of focus on the primary problem.
  • Waterfall handoffs - Excluding designers and engineers from early planning creates inefficiencies and misses opportunities for innovation.

Deep Dive

For all 24 sourced insights from 14 guests, see references/guest-insights.md

  • Shipping Velocity
  • Ai Assisted Prototyping
  • Building With Ai Agents
  • Product Tool Stack

© RefoundAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/writing-prds of RefoundAI/lenny-skills.

  • SKILL.md
  • references/artifacts.md
  • references/guest-insights.md

Open the folder on GitHubat commit 13598cc

Compare with similar skills

Writing Prds next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Writing Prds compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Writing Prds this skillRefoundAI/lenny-skills1.4k—~1.8kAutomated safety check: PassMIT
Prdjuanandresgs/claude-ctrl193—~2.9kAutomated safety check: PassNone
Product Manager Toolkitsickn33/agentic-awesome-skills47k3 repos~2.3kAutomated safety check: PassMIT
Ad SpecCorridorTech/PoseCap224—~2.2kAutomated safety check: NotesApache-2.0
Prd Writerholaboss-ai/holaOS11k—~571Automated safety check: PassCustom licence
Ad Specalexandremendoncaalvaro/CorridorKey-Runtime7561 repos~1.8kAutomated safety check: PassCustom licence

Similar skills

  • Prd

    juanandresgs/claude-ctrl

    Write structured feature specifications with problem statements, user journeys, use cases, functional requirements, and success metrics.

    193 GitHub stars~2.9k tokensUpdated 2 mo ago
    Product & Project ManagementAuto-check passed
  • Product Manager Toolkit

    sickn33/agentic-awesome-skills

    Essential tools and frameworks for modern product management, from discovery to delivery.

    47k GitHub starsUsed in 3 repos~2.3k tokens
    Product & Project ManagementAuto-check passed
  • Ad Spec

    CorridorTech/PoseCap

    Draft a feature-level specification at doc/specs/NNNN-<slug.md following the kit's six-layer artifact stack (Constitution → Domain → Product → Spec → Plan/Decisions → Code).

    224 GitHub stars~2.2k tokensUpdated 2 days ago
    Product & Project ManagementAuto-check: notes
  • Prd Writer

    holaboss-ai/holaOS

    Turn a feature idea into a clear PRD — problem, users, requirements, and success metrics.

    11k GitHub stars~571 tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed
  • Ad Spec

    alexandremendoncaalvaro/CorridorKey-Runtime

    Draft a feature-level specification at doc/specs/NNNN-<slug.md following the six-layer artifact stack (Constitution → Domain → Product → Spec → Plan/Decisions → Code).

    756 GitHub starsUsed in 1 repo~1.8k tokens
    Product & Project ManagementAuto-check passed
  • Prd V03 Outcome Definition

    mattgierhart/PRD-driven-context-engineering

    Define measurable success metrics (KPIs) tied to product type during PRD v0.3 Commercial Model.

    180 GitHub stars~1.9k tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed

More from RefoundAI/lenny-skills

All 76 skills in this repo
  • Customer Interviews

    RefoundAI/lenny-skills

    Help users conduct high-impact customer interviews that move beyond surface-level feature requests to identify root emotional frustrations and specific causal triggers.

    1.4k GitHub stars~1.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Time Energy Management

    RefoundAI/lenny-skills

    Help users master their personal output by shifting from reactive scheduling to intentional energy management, internal trigger mastery, and proactive boundary setting.

    1.4k GitHub stars~1.6k tokensUpdated 2 mo ago
    Auto-check passed
  • User Onboarding Activation

    RefoundAI/lenny-skills

    Help users reach their first moment of core value by optimizing the first-run experience, removing friction, and aligning product design with psychological triggers.

    1.4k GitHub stars~2.1k tokensUpdated 2 mo ago
    Auto-check passed
  • Acquisition Channels

    RefoundAI/lenny-skills

    Help users identify unique distribution advantages and master the lifecycle of acquisition channels to build a sustainable engine for growth and retention.

    1.4k GitHub stars~2.2k tokensUpdated 2 mo ago
    Auto-check passed
  • AI Assisted Prototyping

    RefoundAI/lenny-skills

    Help users build functional product prototypes from natural language or visual mocks using AI coding tools.

    1.4k GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed
  • AI Evals

    RefoundAI/lenny-skills

    Help users build robust infrastructure for measuring, monitoring, and iterating on AI product performance using human, code-based, and LLM-as-a-judge methodologies.

    1.4k GitHub stars~1.7k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Writing Prds

What does Writing Prds do?

Help users transform abstract ideas into actionable project specs that align engineering and design teams on the problem and success metrics. Writing Prds is an agent skill from RefoundAI/lenny-skills. Help users transform abstract ideas into actionable project specs that align engineering and design teams on the problem and success metrics.

When should I use Writing Prds?

Writing Prds fits situations like: tasks that involve PRD writing; tasks that involve Product metrics.

How do I install Writing Prds in Claude Code?

Run `npx skills add RefoundAI/lenny-skills --skill writing-prds -a claude-code`. Or copy the skill folder (skills/writing-prds in RefoundAI/lenny-skills) into .claude/skills/writing-prds in your project. Claude Code loads it when a task matches its description.

How do I install Writing Prds in Codex?

Run `npx skills add RefoundAI/lenny-skills --skill writing-prds -a codex`. Or copy the skill folder (skills/writing-prds in RefoundAI/lenny-skills) into .agents/skills/writing-prds in your project. Codex loads it when a task matches its description.

Can I use Writing Prds in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add RefoundAI/lenny-skills --skill writing-prds -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writing-prds, .gemini/skills/writing-prds, .github/skills/writing-prds and .opencode/skills/writing-prds in your project.

What does Writing Prds need to run?

SKILL.md names no scripts, command-line tools or credentials: Writing Prds is instructions for the agent only.

Does Writing Prds access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Writing Prds safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Writing Prds use?

Writing Prds is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Writing Prds use?

About 1.8k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 17k tokens, read only when the agent opens those files.

What are the alternatives to Writing Prds?

Skills that share tags, products or a category with Writing Prds: Prd (juanandresgs/claude-ctrl, 193 stars), Product Manager Toolkit (sickn33/agentic-awesome-skills, 47k stars), Ad Spec (CorridorTech/PoseCap, 224 stars) and Prd Writer (holaboss-ai/holaOS, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Writing Prds?

RefoundAI (a GitHub organization) maintains it in RefoundAI/lenny-skills, which has 1,381 GitHub stars. The repository holds 76 skills in this directory. The repository was last updated on July 16, 2026.

Source: RefoundAI/lenny-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.