Agent skill

Product Reviews

by RefoundAI in RefoundAI/lenny-skills

Help users design and facilitate product reviews that shift from status updates to strategic deep-dives, ensuring high-quality craftsmanship and organizational alignment.

MITAuto-check passed

Install Product Reviews

skills CLI
$ npx skills add RefoundAI/lenny-skills --skill product-reviews -a claude-code

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

GitHub CLI
$ gh skill install RefoundAI/lenny-skills product-reviews --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/product-reviews .claude/skills/product-reviews && 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
product-reviews
GitHub stars
1.4k
Token cost
~1.8k tokens
SKILL.md length
975 words
Files
3 (incl. references)
Skills in repo
76
Repo updated
First seen
Licence
MIT

At a glance

Help users design and facilitate product reviews that shift from status updates to strategic deep-dives, ensuring high-quality craftsmanship and organizational alignment.

  • Works in 4 steps: Assess review culture - Evaluate current… → Select a framework - Recommend the… → Draft review materials - Assist in… → …
  • 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

Product Reviews is an agent skill from RefoundAI/lenny-skills. Help users design and facilitate product reviews that shift from status updates to strategic deep-dives, ensuring high-quality craftsmanship and organizational alignment.

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`).

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.

Example prompts

  • “/product-reviews”

Workflow steps

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

  1. Assess review culture - Evaluate current review formats and identify bottlenecks or gaps in quality standards.
  2. Select a framework - Recommend the appropriate review stage or template based on the project's complexity and lifecycle.
  3. Draft review materials - Assist in framing problem statements, mapping the option space, and preparing pre-read documents.
  4. Facilitate the session - Provide techniques for gauging sentiment, managing dissent, and capturing clear decisions.

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

Product Reviews loads about 1.8k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 47 tokens; SKILL.md has 975 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
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
~10k

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). 975 words, ~1,762 tokens.

Download SKILL.mdSave it as .claude/skills/product-reviews/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
product-reviews
description
Help users design and facilitate product reviews that shift from status updates to strategic deep-dives, ensuring high-quality craftsmanship and organizational alignment.

Effective Product Reviews

Run rigorous alignment sessions that raise the quality bar and accelerate decision-making.

Help the user with effective product reviews using insights from 12 guests and posts across Lenny's Podcast and Newsletter.

How to Help

  1. Assess review culture - Evaluate current review formats and identify bottlenecks or gaps in quality standards.
  2. Select a framework - Recommend the appropriate review stage or template based on the project's complexity and lifecycle.
  3. Draft review materials - Assist in framing problem statements, mapping the option space, and preparing pre-read documents.
  4. Facilitate the session - Provide techniques for gauging sentiment, managing dissent, and capturing clear decisions.

Core Principles

Evaluate Frameworks, Not Solutions

From "How Figma builds product": "One thing I encourage for both is to first present the “option space”—it’s really powerful to have a framework that maps all possible solutions or problems and use that as a device to discuss high-level tradeoffs or philosophical differences."

High-quality decisions come from mapping the entire field of possible solutions rather than debating a single proposal in isolation.

Establish a Transparent Cadence

From "How Duolingo builds product": "Product review meetings happen every Tuesday and Thursday for a total of two hours. These two hours are divided into 20-minute slots that product teams sign up to present. The agenda of these meetings is product teams presenting their proposed product changes for the first 5 to 10 minutes and then reviewers asking questions and giving feedback for the rest of the time."

Recurring, short review slots prevent feedback bottlenecks and create a shared understanding of what constitutes quality across the organization.

Separate Problem from Solution

From "How Miro builds product": "Product reviews can focus on different stages of the product development lifecycle: P-Strat: long-term strategy and vision; P0: the opportunity and problem that we want to pursue; P1: the proposed solution; P2: what we launched and how it’s performing."

Structure reviews into distinct stages to ensure leadership agrees on the problem and the strategic direction before teams commit to high-fidelity design work.

Operationalize Quality Mantras

From "How Miro builds product": "One of the product leaders came up with the 'Mona Lisa principle'—simply put, everything we ship should be like a Mona Lisa painting, something we’d be proud of putting our name on. . . Every month, they review everything that was shipped and say what is high-quality or not."

Use simple metaphors or principles to build intuition across the team, helping everyone understand the bar for excellence without constant oversight.

Alignment Over Sales Pitches

From "How Snowflake builds product": "The goal of a product review isn’t to “sell” the leadership team on a new investment but to detail customer requirements, align on relative business priorities, and provide a clear direction of how to address these challenges."

Format reviews as collaborative sessions focused on consistent decision-making rather than internal marketing or selling an idea to leadership.

Focus on Rigorous Problem Clarification

Tomer Cohen: "I push a lot for what is actually your opinion, what is your potentially controversial opinion and the best principles have teeth. So saying that we should build a simple product for me is useless. Who doesn't want to build a simple product?"

Reviews should be deep-dives into specific problems and principled opinions, avoiding the trap of high-level status updates that provide no strategic value.

Show full SKILL.md (428 more words)Show less

Templates & Frameworks

  • Product Review Stages (P-Strat, P0, P1, P2) (How Miro builds product) - A four-stage product review framework aligned to the product development lifecycle, each with defined templates and review criteria
  • Uncertainty × Impact 2x2 Review Cadence Rubric (Five principles for successfully managing managers) - A 2x2 matrix for skip leads to determine how closely to review delegated projects based on uncertainty and impact
  • Option Space (How Figma builds product) - A framework for product reviews where the presenter maps all possible solutions or problems before discussing specific directions, enabling better debate on tra
  • Alignment Scale Widget (Yuhki Yamashata) - A FigJam/Figma widget that shows a spectrum where reviewers click to place their avatar, enabling quick pulse checks on alignment during product reviews
  • Snowflake Product Review Document (Six-Pager) (How Snowflake builds product) - A six-page document shared one week before product reviews that outlines the customer problem, proposed solution, and key data for leadership review
  • Notion's Four-Stage Product Review Process (How Notion builds product) - A structured check-in process at four key milestones in product development, replacing unstructured working sessions. Primarily async with a shift to synchronou
  • Async Product Review Workflow with Talktracks (How Miro builds product) - A workflow for making product reviews more efficient by shifting presentations to async and focusing meetings on discussion
  • Project Murder Board (Nabeel S. Qureshi) - A peer-review process for new projects where a 2-page plan is aggressively critiqued by smart outsiders.

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

Questions to Help Users

  • "What stage of the product development lifecycle is this project currently in?"
  • "Have you mapped out the full range of possible solutions or are you presenting a single path?"
  • "What is the specific, nuanced problem statement you are trying to solve?"
  • "How does this project rank on the uncertainty versus impact matrix?"
  • "Are there dissenting opinions within the team that should be surfaced during this review?"
  • "What are the principled opinions that the team is bringing to this discussion?"

Common Mistakes to Flag

  • Treating reviews as status updates - This wastes leadership time and fails to address strategic blockers or quality issues.
  • Reviewing too late in the process - Teams become wedded to a solution, making leadership feedback feel like a demoralizing roadblock rather than guidance.
  • Seeking consensus instead of alignment - Waiting for everyone to agree slows down development and often results in watered-down product decisions.
  • Debating solutions before agreeing on the problem - This leads to circular arguments where stakeholders are optimizing for different goals.

Deep Dive

For all 12 sourced insights from 12 guests, see references/guest-insights.md

  • Executive Communication
  • Managing Up
  • Running Meetings
  • Written Communication

© 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/product-reviews of RefoundAI/lenny-skills.

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

Open the folder on GitHubat commit 13598cc

Compare with similar skills

Product Reviews 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.

Product Reviews compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Product Reviews this skillRefoundAI/lenny-skills1.4k—~1.8kAutomated safety check: PassMIT
Cumulative Layout Shiftthedaviddias/Front-End-Checklist74k—~438Automated safety check: PassMIT
ShiftLeoYeAI/openclaw-master-skills2.2k—~4.1kAutomated safety check: PassMIT
Shiftshift-editor/shift349—~663Automated safety check: PassApache-2.0
Shifting Clinical Datesmaziyarpanahi/openmed5.5k—~1.7kAutomated safety check: PassApache-2.0
Interactive Workshop Facilitationdeanpeters/Product-Manager-Skills7.2k1 repos~1.5kAutomated safety check: PassCustom licence

Similar skills

  • Cumulative Layout Shift

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing slow page loads, heavy assets, or rendering delays related to Minimize cumulative layout shift.

    74k GitHub stars~438 tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed
  • Shift

    LeoYeAI/openclaw-master-skills

    Multi-identity delegation for OpenClaw. An agent skill from LeoYeAI/openclaw-master-skills.

    2.2k GitHub stars~4.1k tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Shift

    shift-editor/shift

    Work with fonts in the Shift font editor. An agent skill from shift-editor/shift.

    349 GitHub stars~663 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Shifting Clinical Dates

    maziyarpanahi/openmed

    Apply consistent per-patient date shifting in OpenMed that preserves intervals between events while satisfying HIPAA Safe Harbor's date rule.

    5.5k GitHub stars~1.7k tokensUpdated today
    Legal & ComplianceAuto-check passed
  • Interactive Workshop Facilitation

    deanpeters/Product-Manager-Skills

    Supplies the shared pacing protocol other interactive skills use: one question per turn, visible progress, and safe interruptions.

    7.2k GitHub starsUsed in 1 repo~1.5k tokens
    Agent WorkflowsAuto-check passed
  • Rca Facilitator

    hashgraph-online/awesome-codex-plugins

    Interactive root cause analysis facilitator — runs a structured 5-Why why chain session, challenges each answer with evidence requirements, detects symptomatic and circular reasoning, and produces a…

    1.3k GitHub stars~2.4k tokensUpdated yesterday
    DevelopmentAuto-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 Product Reviews

What does Product Reviews do?

Help users design and facilitate product reviews that shift from status updates to strategic deep-dives, ensuring high-quality craftsmanship and organizational alignment. Product Reviews is an agent skill from RefoundAI/lenny-skills. Help users design and facilitate product reviews that shift from status updates to strategic deep-dives, ensuring high-quality craftsmanship and organizational alignment.

How do I install Product Reviews in Claude Code?

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

How do I install Product Reviews in Codex?

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

Can I use Product Reviews 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 product-reviews -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/product-reviews, .gemini/skills/product-reviews, .github/skills/product-reviews and .opencode/skills/product-reviews in your project.

What does Product Reviews need to run?

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

Does Product Reviews 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 Product Reviews 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 Product Reviews use?

Product Reviews 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 Product Reviews 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 8.3k tokens, read only when the agent opens those files.

What are the alternatives to Product Reviews?

Skills that share tags, products or a category with Product Reviews: Cumulative Layout Shift (thedaviddias/Front-End-Checklist, 74k stars), Shift (LeoYeAI/openclaw-master-skills, 2.2k stars), Shift (shift-editor/shift, 349 stars) and Shifting Clinical Dates (maziyarpanahi/openmed, 5.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Product Reviews?

RefoundAI (a GitHub organization) maintains it in RefoundAI/lenny-skills, which has 1,382 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.