Skip to content
SkillModel-led425 tokens in use

analyze-feature-requests

Groups customer feature requests into themes, checks strategic fit and ranks the top three by impact, effort and risk.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-product-discovery/skills/analyze-feature-requests
claude plugin marketplace add phuryn/pm-skills claude plugin install pm-product-discovery@pm-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing analyze-feature-requests costs

45tokens idle
425tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure22/25
  • Examples0/15
  • Output7/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity80
  • Maintenance76
  • Community60
  • Maturity32
  • Momentum40

analyze-feature-requests helps the agent triage a pile of customer requests against your product goal. It confirms the goal, groups requests into named themes, rates each theme’s strategic alignment and then picks the top three features.

For each top feature it gives the rationale, alternative solutions, high-risk assumptions and a low-effort way to test them. The skill leans on Opportunity Score from Dan Olsen and tells the agent to prioritize the underlying problems, since customers should not design the solutions.

What You Get

  • Feature requests grouped into named themes
  • A strategic alignment assessment for each theme
  • A top three list scored on impact, effort, risk and strategic fit
  • Rationale, alternative solutions and high-risk assumptions per top feature
  • A cheap way to test each risky assumption
  • An optional summary table or markdown document

Common Use Cases

  • Triaging a quarter of customer requests before roadmap planning
  • Turning a CSV export from a support or CRM tool into themes
  • Explaining to a stakeholder why a loud request ranks lower
  • Finding the problem behind several differently worded requests

What Makes It Unique

It frames requests as signals about opportunities (problems) and cites the Opportunity Score formula, importance times one minus satisfaction, normalized to a 0 to 1 scale, as the lens. Every top pick comes with the assumptions to test and a cheap test for each, which links triage to discovery work. It points to the prioritization-frameworks skill for templates and full framework details.

Under The Hood

A single SKILL.md of instructions with no scripts. The agent reads any spreadsheet, CSV or document you attach with its own file tools, and the skill says to save the result as markdown or a structured output document, so it can write a file. It does not tell the agent to fetch web pages, call APIs or run commands. Your product goal replaces $ARGUMENTS in the prompt.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers