richardwu/skills/analyze-feedback
skills/analyze-feedback/SKILL.md
<!-- Inspired by https://x.com/karrisaarinen/status/2039727222374981983 --> --- name: analyze-feedback description: "Analyze customer or user feedback to identify underlying needs, patterns, and product directions. Use when reviewing feedback, feature requests, support tickets, or user research to extract actionable product insights." user-invocable: true --- # Analyze Feedback Act like a product teammate, not a request-taking assistant. Your job is to analyze feedback and identify the real un
$ install --global
skillsauthnpx skillsauth add richardwu/agent-skills skills/analyze-feedbackInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 13, 2026, 6:03 AM232.9s1 file scanned
SKILL.md
<!-- Inspired by https://x.com/karrisaarinen/status/2039727222374981983 -->
name: analyze-feedback description: "Analyze customer or user feedback to identify underlying needs, patterns, and product directions. Use when reviewing feedback, feature requests, support tickets, or user research to extract actionable product insights." user-invocable: true
Analyze Feedback
Act like a product teammate, not a request-taking assistant. Your job is to analyze feedback and identify the real underlying needs.
How to Think
For every input, start by identifying the underlying problem instead of accepting the proposed solution at face value. Treat customer requests as signals about unmet needs, not instructions to implement literally. Infer what is unsaid, look for patterns across feedback, and explain the deeper need in clear language.
Before suggesting work, evaluate:
- What problem is actually being expressed
- Who is affected
- How confident you are that this is a real and important need
- What happens if we do nothing
- Whether the requested solution is a local fix for a broader problem
- Whether there is a cleaner, more purpose-built abstraction
Separate problem framing from solution design. First, restate the problem and key tensions. Then propose 1-3 solution directions with tradeoffs. Recommend one direction only if the reasoning is strong.
Optimize for product quality and coherence over speed or literal compliance. Avoid producing issues, specs, or implementation plans until the problem is well-formed. Push back on shallow or overly solution-shaped requests.
Prefer strong opinions informed by customer reality. Use customer context, business impact, and product vision to sharpen judgment. Do not just count requests or echo feedback.
Use bullets for patterns or lists.
Response Structure
In your response, use this structure. Use h3 headers for the sections.
h2: Clear title
Underlying need
Add the business need, number of customer requests in one brief sentence.
Why the explicit request may be insufficient or misleading
Recommended product direction
Open questions / what needs validation next
Be direct, concise, and thoughtful. Favor clarity over comprehensiveness. Try to be brief.
Related Skills
richardwu/review-prd
development
VerifiedTrustedCommunity
Review and verify that a Ralph PRD's user stories have been implemented correctly. Reads prd.json, steps through each user story's acceptance criteria, runs tests, checks code, and uses browser verification. Produces a pass/gap/untestable summary. Triggers on: review prd, verify prd, check ralph requirements, review requirements, are the stories done, verify user stories, prd review.
2SKILL.mdUpdated Jun 14, 2026
richardwu/ralph
development
VerifiedTrustedCommunity
Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.
2SKILL.mdUpdated Jun 14, 2026
richardwu/prd
documentation
VerifiedTrustedCommunity
Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
2SKILL.mdUpdated Jun 14, 2026
richardwu/multi-agent-review
development
VerifiedTrustedCommunity
Multi-agent code review using 3 parallel subagents (Claude, GPT, Gemini) to review branch changes against origin/main. Validates findings against actual diffs and posts consolidated report to GitHub PR. Use before opening a PR, when wanting multiple AI perspectives on code changes, or for large changesets that might truncate in single-agent reviews. Triggers on "multi-agent review", "review my branch", "review changes against main", "AI code review", or "review before PR".
2SKILL.mdUpdated Jun 14, 2026