li-prd-review

Original：🇨🇳 Chinese

Translated

PRD Expert Advisor Mode. Three well-known PM/CEO act as advisors, proactively review PRD, identify weak points and provide improvement solutions that can be directly written into the document. Users decide whether to adopt via accept/reject. Trigger methods: /li-prd-review, "Enhance PRD", "Expert Advisor", "Help me review this PRD", "Let experts review the PRD", "What are the loopholes in the PRD", "Help me optimize the PRD", "What other issues are there with the PRD". Even if users don't mention "PRD", this skill should be triggered as long as they want expert roles to review a product document and provide improvement solutions. DO NOT trigger for: PRD generation tasks (use li-prd), content script generation, topic analysis and other content creation tasks.

8installs

Sourcejiangjiax/li-skills

Added on2026-05-23

NPX Install

npx skill4agent add jiangjiax/li-skills li-prd-review

SKILL.md Content (Chinese)

View Translation Comparison →

li-prd-review: PRD Expert Advisor

Let well-known PM/CEO proactively identify weak points in PRD and provide improvement solutions, you decide whether to adopt or skip.

Can be used for any PRD, not dependent on li-prd generation.

Startup Process

Step 1: Locate the PRD

If the user triggers the function directly without providing PRD content, ask:

Paste the PRD here, or tell me the file path.

After obtaining the PRD, read the entire document first, do not give suggestions while reading—speak only after finishing the full reading, to avoid giving suggestions only after seeing the first issue.

Step 2: Select an Expert

Which role would you like to review? A. Tony Fadell (Author of Create, former Apple/Nest) — Customer journey, product story, experience moments B. YC Partner (Paul Graham style) — Validation data, moat, quantifiable metrics C. Lenny Rachitsky (Product growth expert) — Retention, aha moment, word-of-mouth growth D. All in turn

Step 3: Advisor Review

Read

references/advisors.md

to obtain the role's review perspective and character settings.

Play the selected role, identify the 2-3 weakest links. Put forward only one improvement suggestion each time, in a fixed format:

[Role Name]: There is an issue with [specific section/assumption]: [Issue description, 1-2 sentences]. Improvement Solution: [Specific modification content that can be directly written into PRD]. Would you like to adopt this change?

After the user responds:

Adopt → Immediately update the corresponding section of the PRD, state "Updated: [Section Name]", then give the next suggestion
Reject → Record the reason in one sentence, then continue with the next suggestion
Objection → Discuss and revise the solution before confirming

Step 4: Change Summary

After giving 2-3 suggestions from each role, output:

PRD Change Summary ([Role Name])

Section	Change Content	Status
[Section Name]	[One-sentence description of the change]	Adopted / Skipped

When selecting all roles (D), take turns with each role. Clearly state "Now let Lenny take a look" when switching roles, and output the respective change summary after each role finishes.

Advisor Execution Principles

No role overlap: If Tony is selected, only use Tony's perspective, do not mix in logic from other roles
Improvement solutions must be directly pasteable into PRD: Instead of "You should consider retention", it should be "Write this paragraph into Section X"
Update the document immediately after adoption: Make changes right away when adoption is confirmed, do not save all changes for the end

Additional Resources

references/advisors.md
— Review perspectives, alert triggers, and improvement solution examples for the three expert advisors